DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-20 filed on 07/26/2022 and Amendments filed on 08/09/2024, 02/21/2025, and 06/25/2025 have been examined.
This Office Action is in response to the Applicant’s amendments and remarks filed on 12/04/2025. Claims 1, 16, and 20 have been amended. Claim 15 has been previously canceled by the Applicant. Claim 21 is a new claim that has been added to the claim set. Claims 1-14 and 16-21 are currently pending and addressed below.
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 01/07/2026 has been entered.
Response to Remarks/Arguments
Applicant’s accompanying amendments and arguments, on pages 9-10 of the Applicant Arguments/Remarks (hereinafter referred to as the “Remarks”), filed 12/04/2025, with respect to the claim objections and claim interpretation for independent claims 1, 16, and 20 stating “… Applicant has amended claims 1, 16, and 20 to actively recite the limitation - an off-grid, online search of motion primitives for the quantized pseudo-trailer configuration. Amended claims 1, 16, and 20 now recite perform an off-grid, online search of motion primitives for the quantized pseudo-trailer configuration… Applicant respectfully requests withdrawal of the objections to claims… In view of the amendment, the Applicant respectfully submits that the amended limitation does not invoke claim interpretation under 35 U.S.C. 112(f)…” have been considered and are persuasive. Therefore, the Examiner has withdrawn the claim objections and claim interpretation for claims 1, 16, and 20.
Applicant’s accompanying amendments and arguments, on pages 10-13 of the Applicant Remarks, filed 12/04/2025, with respect to the rejection of independent claims 1, 16, 20 and their corresponding dependent claims under 35 U.S.C 103 stating “… the cited references fail to teach or suggest wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized… The Applicant submits that Laine merely describes recording position and heading of the articulated vehicle along a traveled path with a predefine rate. The predefined rate refers to the rate at which measurements are recorded, i.e., recording at a specified distance interval or time interval, and not a time duration selected to achieve stabilization of the tractor-trailer relative angle… Laine's recorded positions and headings do not correspond to, and do not disclose, a stable circular configuration obtained by driving the trailer-based vehicle with a fixed steering angle for sufficient time such that a relative angle between the trailer and the tractor is stabilized… Therefore, Laine fails to teach or suggest wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized, as recited in amended claims 1, 16, and 20… The other cited references Jing, Dangel, Botros, and Yano do not remedy the above deficiencies of Laine… Since the cited references fail to combine to teach or suggest each and every element of the independent claims, Applicant submits that independent claims 1, 16, and 20, and claims that depend therefrom, are patentable and in condition for allowance. Accordingly, withdrawal of the rejections under 35 U.S.C. §103 is respectfully requested…” have been considered but are moot due to the amendments and added limitations provided above. Upon further consideration, a new ground(s) of rejection is made in view of Hafner et al. US 20140303849 A1 (“Hafner”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1-5, 16-18, and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Jing et al. US 20210294333 (“Jing”) in view of Dangel et al. US 20240300541 (“Dangel”), Laine US 20160114831 (“Laine”), Hafner et al. US 20140303849 A1 (“Hafner”), Botros “Lattice-Based Motion Planning with Optimal Motion Primitives” December 23, 2021 (“Botros”), and Yano US 20230050172 A1 (“Yano”).
For claim 1, Jing discloses a system for controlling a motion of a trailer-based vehicle (See at least [0039] of Jing – “The disclosed techniques may be used by an autonomous driving system on a tractor-trailer truck to generate an optimal driving path through a pre-mapped space using a pre-generated offline optimal path library. The space may include areas that are challenging for turning a tractor-trailer, such as areas with tight turns…”) from an initial state till a target state, wherein each state includes at least a location and a heading of the trailer-based vehicle (See at least [0032]-[0034] – “…the method uses the vehicle's current x and y coordinates reported from a localization method to find the nearest grid node on the discretized state space of the optimal path library, and then uses the vehicle's current heading angle value reported from a yaw angle measurement device to find the nearest orientation grid bin of the nearest location grid node… the entire optimal driving trajectory expands consecutively and autonomously starting from the initial pair indicating the vehicle's current location and orientation, leading to the desired terminal driving state on the map of the turning area represented by end pair of grid node and grid bin...”), wherein the trailer-based vehicle includes a tractor and at least one trailer attached to the tractor such that a motion of the tractor controls a motion of the trailer (See at least [0037] – “… the compact library may include optimal paths through a parking lot for an autonomous tractor-trailer vehicle that takes into account the wide turns taken by a tractor-trailer… avoidance of collision with fixed objects… prevent jackknifing of the tractor-trailer…”), the system comprising: a motion planner including a processor (See at least [0042] – “…The process generates an optimal path for a vehicle through a mapped area by evaluating all feasible path connections…” and [0067] – “FIG. 5A depicts an example of a hardware platform 500… implement the various modules described herein. The hardware platform 500 may include a processor 502…”) configured to
collect a set of motion primitives parameterized on a quantized pseudo-trailer-configuration from a finite set of quantized pseudo-trailer-configurations, each motion primitive configured to move the trailer-based vehicle from a pseudo-trailer-configuration induced initial state relating to the finite set of quantized pseudo-trailer-configurations to another pseudo-trailer-configuration induced target state having a same or different pseudo-trailer-configuration relating to the finite set of quantized pseudo-trailer-configurations (See at least [0051]-[0053] – “The method of finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer… From a search starting location… a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… the generated optimal path library finds the global optimal path and actions for any given vehicle location and orientation state within the map… The disclosed offline path library generation method may be exhaustive to any given discretized vehicle location and orientation within the mapped range, and all of the paths originating from a vehicle starting state converge into one optimal path for the mapped area. This property robustly handles all potential autonomous driving states in the defined map region… develops a dynamic resolution technique that dynamically generates the heading angle resolution grid values based on optimal solution local progressing at each position state instance… the optimal paths are stored… Each arc piece corresponds to an arc from one path state to another path state… The optimal path to an endpoint given the starting position and orientation can be extracted…”);
repetitively select a node based on corresponding cost, and apply motion primitives at the selected node based on a corresponding pseudo-trailer-configuration to add new nodes having pseudo-trailer-configurations belonging to a set of all possible values (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle… the path arc reaches to the lower layer position grid node…”, [0047] – “…one or more cost or performance metrics are applied to the arc path..”, [0051] – “… finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… Each state space node of the map region links the decisions of preceding choices to get to that node including accumulated historical action metric values and costs…”, [0054]-[0055] – “FIG. 2A depicts an illustration at 210 of a family of arc paths… Each arc segment begins at a node and ends at another node… The arc segments shown at 210 are all the possible arc segments origination at 212 before the optimal path is chosen from a starting location... FIG. 2B depicts an illustration at 250 of locations or points in a grid map with bins and nodes… Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations… evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256…” and [0077] – “… the offline server may perform the evaluating operation … assigning costs for all of the trajectory connections to a layer of grid nodes, and saving optimal trajectory connections to every reachable grid node and grid bin pair, and deactivating grid node and grid bin pairs for the next layer's search evaluation when at least one criteria is violated.… that relate to motion control … the linkage information for optimal trajectory connections is saved to the optimal path library”), wherein a tractor configuration, x,y,00, is arbitrary (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature … cause the tractor-trailer to move from (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t), which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”);
perform an offline search of motion primitives for the quantized pseudo-trailer configuration (See at least [0005] of Jing – “performing, by the offline server, an exhaustive search for an optimal vehicle driving trajectory for the discretized position space… includes evaluating driving trajectory connections between every two pairs of state space and grid nodes on two layers along a reference driving direction in the driving space to determine a best driving action leading to global optimal complete trajectories…”) and connect a sequence of multiple motion primitives into a motion path connecting the initial state with the target state, wherein a starting value of a quantized pseudo-trailer-configuration of a subsequent motion primitive in the sequence equals an ending value of a quantized pseudo-trailer-configuration of a previous motion primitive in the sequence (See at least [0006] – “generating a library of optimal paths for an autonomous driving vehicle is disclosed… determining, at the offline server, path arcs between an evaluated state space node and reachable state space nodes … a path arc curvature… a tractor vehicle steering angle and coordinates for one or more body locations of the autonomous driving vehicle along the path arc… the steering controller steering angle…”, [0037] – “The paths are optimal in that the paths provide avoidance of collision with fixed objects, the paths minimize steering changes…” and [0044] – “arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle after (x.sub.0, y.sub.0).… which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”); and
control the motion of the trailer-based vehicle according to the motion path (See at least [0056] – “… At 330, the bin with the closest heading angle to the vehicle heading is selected. At 340, the optimal parent layer node, bin, arc curvature, and arc length are read based on the matched grid node and the selected vehicle heading… At 350, the parent node location, arc curvature, and arc length are converted to a steering command to send to the autonomous steering controller…”).
Jing fails to specifically disclose a processor configured to collect a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space.
However, Dangel, in the same field of endeavor teaches a processor (See at least [0110] of Dangel – “… the vehicle control unit 360 can control the vehicle thanks to signals obtained from trajectories optimized upon execution of the present methods by the processors…”) configured to collect a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space (See at least [0053] – “… at high velocities … resulting model involves eight states (longitudinal force/acceleration, steering angle, v.sub.x, v.sub.y, yaw-rate, s, w, relative heading)… At low velocities, the vehicle model used may for example be a simpler kinematic model with four states only (x and y coordinates, velocity and heading…” and [0098] of Dangel – “…It is advantageous to simplify the mathematical optimization problem such that a path can be found in real time (less than ms… While a full search method will search for a solution in a multi-dimensional space (e.g., including two space dimension, time, and other dimensions taking vehicle-related aspects such as orientation into account), blocks 3-5 in FIG. 1 may advantageously reduce this to three dimensions only… which reduces the problem size and, therefore, the optimization duration…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Dangel teaches a motion planning system for an autonomous vehicle that reduces the dimensions of vehicle state spaces by enforcing constraints on the number of dimensions that define the vehicle state spaces to generate optimized trajectories for the vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of a processor configured to collect a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space as taught by Dangel, with a reasonable expectation of success, in order to solve a coarse optimization problem in a very short time and control the vehicle using optimized trajectories as specified in at least [0098] and [0110]-[0111] of Dangel.
Furthermore, Jing also fails to specifically disclose wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer.
However, Laine, in the same field of endeavor teaches wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer (See at least [0032]-[0037] of Laine – “… A vehicle state observer is used for estimating the position of the equivalent axle position 11 (Xp,Yp) of the last towed vehicle of the vehicle combination… The state space equations describing the state of a vehicle combination with two trailers could be expressed as in the following equations… using the equivalent axle position (XP,YP) and the effective wheelbase (L.sub.eq,1) for each towed vehicle and the heading θ.sub.n of the last n.sup.th towed vehicle… the swept area of the articulated vehicle can be calculated from the vehicle dimensions… The modified swept area is used to control the steering of the vehicle combination when reversing the vehicle combination along the specified path, such that the vehicle combination does not extend outwards of the modified swept area during the reversal…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Laine teaches an automatic reversing assistance system for a towing vehicle that simplifies state space equations for a vehicle combination with two trailers by taking into account the heading angle of a last towed vehicle to obtain a swept area of the vehicle combination to then control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the algebraic constraint defining a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer as taught by Laine, with a reasonable expectation of success, in order to simplify calculations using a linear vehicle model that represents a towing vehicle with towed vehicles combination as specified in at least [0030] of Laine and to further obtain a swept area to be used to control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing as specified in at least [0037] of Laine.
Additionally, Jing fails to specifically disclose wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized.
However, Hafner, in the same field of endeavor teaches wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized (See at least [0148]-[0149] – “… Referring to FIG. 5… it is desirable to limit the potential for the vehicle 302 and the trailer 304 to attain a jackknife angle … for limiting the potential for a vehicle/trailer system attaining a jackknife angle, it is preferable to control the yaw angle of the trailer while keeping the hitch angle of the vehicle/trailer system relatively small… Referring to FIGS. 5 and 7, a steering angle limit for the steered front wheels 306 requires that the hitch angle .gamma. cannot exceed the jackknife angle … the jackknife angle .gamma.(j) is the hitch angle .gamma. that maintains a circular motion for the vehicle/trailer system when the steered wheels 306 are at a maximum steering angle…”, [0272]-[0275] – “… when the yaw rate of the vehicle 100 and the trailer 110 become equal, the actual hitch angle .gamma.(a) will likely be constant, such that the desired hitch angle provided by the trail backup steering input apparatus … is also constant and substantially achieved … the measured hitch angle .gamma.(m) and the steering angle .delta. are substantially constant during the reversing motion for at least a threshold period of time or over a threshold distance of motion…”, [0359] – “… Referring now to FIG. 59, a method for operating the trailer backup assist system 105 is illustrated… a desired hitch angle .gamma.(d) is determined based on the desired curvature .kappa..sub.2 and the steering angle .delta.. In one embodiment, at step 1542, a jackknife angle .gamma.(j) may be determined… as previously explained with reference to FIGS. 5 and 7, and thereby used to prevent the desired hitch angle .gamma.(d) from exceeding the jackknife angle … This controller implementing step 1544 is configured to generate the steering angle command consistent with the desired curvature .kappa..sub.2 …. thereby move the trailer 110 in compliance with the desired curvature .kappa..sub.2…” and Fig. 7 of Hafner – vehicle-trailer controlled to maintain a circular motion that prevents a jackknife condition). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Hafner teaches a trailer backup assist system that generates steering commands for a vehicle-trailer to maintain a constant circular motion, a desired hitch angle, and prevent a jackknife condition.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponding to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized as taught by Hafner, with a reasonable expectation of success, in order to prevent a jackknife condition and steer the vehicle and move the trailer in compliance with a desired curvature as specified in at least [0359] of Hafner.
Moreover, Jing also fails to specifically disclose perform an off-grid search of motion primitives.
However, Botros, in the same field of endeavor teaches perform an off-grid search of motion primitives (See at least page 90 of Botros – “… We present an A*-based algorithm to compute feasible motions for difficult maneuvers in both parking lot and highway settings. The algorithm… accommodates off-lattice start and goal configurations up to a specified tolerance…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Botros teaches a motion planning system for autonomous vehicles that uses an algorithm to determine off-lattice start and goal configurations when determining feasible motions for the autonomous vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an off-grid search of motion primitives as taught by Botros, with a reasonable expectation of success, in order to accommodate off-lattice start and goal configurations up to a specified tolerance as specified in at least page 90 of Botros.
Lastly, Jing also fails to specifically disclose perform an online search of motion primitives.
However, Yano, in the same field of endeavor teaches perform an online search of motion primitives (See at least [0047]-[0049] of Yano – “… the control server 3 generates, as the target moving route TGT for one movable body 1, the route that allows the one movable body 1 to move… determines the position of the movable body …”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Yano teaches an autonomous vehicle control system that determines routes and positions for moving the movable body using an online server.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an online search of motion primitives as taught by Yano, with a reasonable expectation of success, in order to allow the movable body to move as specified in at least [0047] of Yano.
For claim 2, Jing discloses wherein the set of motion primitives includes multiple motion primitives pre-calculated for each pseudo-trailer-configuration induced state with an initial state of the tractor configuration being (0,0,0), wherein the starting value of the quantized pseudo-trailer configuration belongs to the finite set of pseudo-trailer configurations (See at least [0044] – “At 120, an arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle after (x.sub.0, y.sub.0)… which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0.” and [0051] – “… The method of finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle…”).
For claim 3, Jing discloses wherein motion primitives for the starting value or motion primitives for the ending value include multiple motion primitives with a same pseudo-trailer configuration but moving the trailer-based vehicle into different locations (See at least [0011] – “FIG. 2A depicts an example of offline searching for a family of arc paths from a target ending location and orientation to all possible starting locations and orientations in the mapped area with a discrete resolution…”, [0012] – “Fig. 2B depicts an example of position grid nodes connected with path arcs through various heading angle grid bins…”, and [0055] – “… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node…”).
For claim 4, Jing discloses wherein the pseudo-trailer-configuration is represented by a steering angle value (See at least [0045] – “… kinematic solver solves for the tractor-trailer kinematic states along the arc path… includes the continuous traces of tractor heading angle, tractor rear axle center location, tractor steering angle, trailer heading angle, trailer rear axle center location, and trailer articulation angle…”), and relative angles between headings of the at least one trailer attached to the tractor are functions of steering angles (See at least [0047] – “… one or more cost or performance metrics are applied to the arc path… the articulation metric may generate a higher (or lower) value indicating a more desirable path for an arc path that where a maximum angle between the tractor and the trailer is smaller (closer to straight line alignment between the tractor and the trailer) compared to an arc path where a maximum angle between the tractor and the trailer is larger, especially when the angle is close to an angle that may cause a jackknife…”).
For claim 5, Jing discloses wherein the pseudo-trailer-configuration is represented by a relative angle between a heading of the tractor and an heading of an adjacent trailer, and headings of the trailers are functions of the pseudo-trailer-configuration (See at least [0045] – “… kinematic solver solves for the tractor-trailer kinematic states along the arc path… includes the continuous traces of tractor heading angle, tractor rear axle center location, tractor steering angle, trailer heading angle, trailer rear axle center location, and trailer articulation angle…”, [0047] – “… one or more cost or performance metrics are applied to the arc path… the articulation metric may generate a higher (or lower) value indicating a more desirable path for an arc path that where a maximum angle between the tractor and the trailer is smaller (closer to straight line alignment between the tractor and the trailer) compared to an arc path where a maximum angle between the tractor and the trailer is larger, especially when the angle is close to an angle that may cause a jackknife…”, [0050] – “… If a metric lies outside the range, the arc may be avoided or not selected…”, and [0051] – “… finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… the generated optimal path library finds the global optimal path and actions for any given vehicle location and orientation state within the map and maintains finite computation memory and time usage in the offline search process”).
For claim 16, Jing discloses a method for controlling a motion of a trailer-based vehicle (See at least [0039] of Jing – “The disclosed techniques may be used by an autonomous driving system on a tractor-trailer truck to generate an optimal driving path through a pre-mapped space using a pre-generated offline optimal path library. The space may include areas that are challenging for turning a tractor-trailer, such as areas with tight turns…”) from an initial state till a target state, wherein each state includes at least a location and a heading of the trailer-based vehicle (See at least [0032]-[0034] – “…the method uses the vehicle's current x and y coordinates reported from a localization method to find the nearest grid node on the discretized state space of the optimal path library, and then uses the vehicle's current heading angle value reported from a yaw angle measurement device to find the nearest orientation grid bin of the nearest location grid node… the entire optimal driving trajectory expands consecutively and autonomously starting from the initial pair indicating the vehicle's current location and orientation, leading to the desired terminal driving state on the map of the turning area represented by end pair of grid node and grid bin...”), wherein the trailer-based vehicle includes a tractor and at least one trailer attached to the tractor such that a motion of the tractor controls a motion of the trailer (See at least [0037] – “… the compact library may include optimal paths through a parking lot for an autonomous tractor-trailer vehicle that takes into account the wide turns taken by a tractor-trailer… avoidance of collision with fixed objects… prevent jackknifing of the tractor-trailer…”), the method comprising:
collecting a set of motion primitives parameterized on a quantized pseudo-trailer-configuration from a finite set of quantized pseudo-trailer-configurations, each motion primitive configured to move the trailer-based vehicle from a pseudo-trailer-configuration induced initial state relating to the finite set of quantized pseudo-trailer-configurations to another pseudo-trailer-configuration induced target state having a same or different pseudo-trailer-configuration relating to the finite set of quantized pseudo-trailer-configurations (See at least [0051]-[0053] – “The method of finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer… From a search starting location… a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… the generated optimal path library finds the global optimal path and actions for any given vehicle location and orientation state within the map… The disclosed offline path library generation method may be exhaustive to any given discretized vehicle location and orientation within the mapped range, and all of the paths originating from a vehicle starting state converge into one optimal path for the mapped area. This property robustly handles all potential autonomous driving states in the defined map region… develops a dynamic resolution technique that dynamically generates the heading angle resolution grid values based on optimal solution local progressing at each position state instance… the optimal paths are stored… Each arc piece corresponds to an arc from one path state to another path state… The optimal path to an endpoint given the starting position and orientation can be extracted…”);
repetitively selecting a node based on a corresponding cost, and applying motion primitives at the selected node based on a corresponding pseudo-trailer-configuration to add new nodes having pseudo-trailer-configurations belonging to a set of all possible values (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle… the path arc reaches to the lower layer position grid node…”, [0047] – “…one or more cost or performance metrics are applied to the arc path..”, [0051] – “… finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… Each state space node of the map region links the decisions of preceding choices to get to that node including accumulated historical action metric values and costs…”, [0054]-[0055] – “FIG. 2A depicts an illustration at 210 of a family of arc paths… Each arc segment begins at a node and ends at another node… The arc segments shown at 210 are all the possible arc segments origination at 212 before the optimal path is chosen from a starting location... FIG. 2B depicts an illustration at 250 of locations or points in a grid map with bins and nodes… Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations… evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256…” and [0077] – “… the offline server may perform the evaluating operation … assigning costs for all of the trajectory connections to a layer of grid nodes, and saving optimal trajectory connections to every reachable grid node and grid bin pair, and deactivating grid node and grid bin pairs for the next layer's search evaluation when at least one criteria is violated.… that relate to motion control … the linkage information for optimal trajectory connections is saved to the optimal path library”), wherein a tractor configuration, x,y,00, is arbitrary (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature … cause the tractor-trailer to move from (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t), which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”);
performing an offline search of motion primitives for the quantized pseudo-trailer configuration (See at least [0005] of Jing – “performing, by the offline server, an exhaustive search for an optimal vehicle driving trajectory for the discretized position space… includes evaluating driving trajectory connections between every two pairs of state space and grid nodes on two layers along a reference driving direction in the driving space to determine a best driving action leading to global optimal complete trajectories…”) and connecting a sequence of multiple motion primitives into a motion path connecting the initial state with the target state, wherein a starting value of a quantized pseudo-trailer-configuration of a subsequent motion primitive in the sequence equals an ending value of a quantized pseudo-trailer-configuration of a previous motion primitive in the sequence (See at least [0006] – “generating a library of optimal paths for an autonomous driving vehicle is disclosed… determining, at the offline server, path arcs between an evaluated state space node and reachable state space nodes … a path arc curvature… a tractor vehicle steering angle and coordinates for one or more body locations of the autonomous driving vehicle along the path arc… the steering controller steering angle…”, [0037] – “The paths are optimal in that the paths provide avoidance of collision with fixed objects, the paths minimize steering changes…” and [0044] – “arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle after (x.sub.0, y.sub.0).… which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”); and
controlling the motion of the tractor-trailer according to the motion path (See at least [0056] – “… At 330, the bin with the closest heading angle to the vehicle heading is selected. At 340, the optimal parent layer node, bin, arc curvature, and arc length are read based on the matched grid node and the selected vehicle heading… At 350, the parent node location, arc curvature, and arc length are converted to a steering command to send to the autonomous steering controller…”).
Jing fails to specifically disclose collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space.
However, Dangel, in the same field of endeavor teaches collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space (See at least [0053] – “… at high velocities … resulting model involves eight states (longitudinal force/acceleration, steering angle, v.sub.x, v.sub.y, yaw-rate, s, w, relative heading)… At low velocities, the vehicle model used may for example be a simpler kinematic model with four states only (x and y coordinates, velocity and heading…” and [0098] of Dangel – “…It is advantageous to simplify the mathematical optimization problem such that a path can be found in real time (less than ms… While a full search method will search for a solution in a multi-dimensional space (e.g., including two space dimension, time, and other dimensions taking vehicle-related aspects such as orientation into account), blocks 3-5 in FIG. 1 may advantageously reduce this to three dimensions only… which reduces the problem size and, therefore, the optimization duration…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Dangel teaches a motion planning system for an autonomous vehicle that reduces the dimensions of vehicle state spaces by enforcing constraints on the number of dimensions that define the vehicle state spaces to generate optimized trajectories for the vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space as taught by Dangel, with a reasonable expectation of success, in order to solve a coarse optimization problem in a very short time and control the vehicle using optimized trajectories as specified in at least [0098] and [0110]-[0111] of Dangel.
Furthermore, Jing also fails to specifically disclose wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer.
However, Laine, in the same field of endeavor teaches wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer (See at least [0032]-[0037] of Laine – “… A vehicle state observer is used for estimating the position of the equivalent axle position 11 (Xp,Yp) of the last towed vehicle of the vehicle combination… The state space equations describing the state of a vehicle combination with two trailers could be expressed as in the following equations… using the equivalent axle position (XP,YP) and the effective wheelbase (L.sub.eq,1) for each towed vehicle and the heading θ.sub.n of the last n.sup.th towed vehicle… the swept area of the articulated vehicle can be calculated from the vehicle dimensions… The modified swept area is used to control the steering of the vehicle combination when reversing the vehicle combination along the specified path, such that the vehicle combination does not extend outwards of the modified swept area during the reversal…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Laine teaches an automatic reversing assistance system for a towing vehicle that simplifies state space equations for a vehicle combination with two trailers by taking into account the heading angle of a last towed vehicle to obtain a swept area of the vehicle combination to then control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the algebraic constraint defining a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer as taught by Laine, with a reasonable expectation of success, in order to simplify calculations using a linear vehicle model that represents a towing vehicle with towed vehicles combination as specified in at least [0030] of Laine and to further obtain a swept area to be used to control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing as specified in at least [0037] of Laine.
Additionally, Jing fails to specifically disclose wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized.
However, Hafner, in the same field of endeavor teaches wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized (See at least [0148]-[0149] – “… Referring to FIG. 5… it is desirable to limit the potential for the vehicle 302 and the trailer 304 to attain a jackknife angle … for limiting the potential for a vehicle/trailer system attaining a jackknife angle, it is preferable to control the yaw angle of the trailer while keeping the hitch angle of the vehicle/trailer system relatively small… Referring to FIGS. 5 and 7, a steering angle limit for the steered front wheels 306 requires that the hitch angle .gamma. cannot exceed the jackknife angle … the jackknife angle .gamma.(j) is the hitch angle .gamma. that maintains a circular motion for the vehicle/trailer system when the steered wheels 306 are at a maximum steering angle…”, [0272]-[0275] – “… when the yaw rate of the vehicle 100 and the trailer 110 become equal, the actual hitch angle .gamma.(a) will likely be constant, such that the desired hitch angle provided by the trail backup steering input apparatus … is also constant and substantially achieved … the measured hitch angle .gamma.(m) and the steering angle .delta. are substantially constant during the reversing motion for at least a threshold period of time or over a threshold distance of motion…”, [0359] – “… Referring now to FIG. 59, a method for operating the trailer backup assist system 105 is illustrated… a desired hitch angle .gamma.(d) is determined based on the desired curvature .kappa..sub.2 and the steering angle .delta.. In one embodiment, at step 1542, a jackknife angle .gamma.(j) may be determined… as previously explained with reference to FIGS. 5 and 7, and thereby used to prevent the desired hitch angle .gamma.(d) from exceeding the jackknife angle … This controller implementing step 1544 is configured to generate the steering angle command consistent with the desired curvature .kappa..sub.2 …. thereby move the trailer 110 in compliance with the desired curvature .kappa..sub.2…” and Fig. 7 of Hafner – vehicle-trailer controlled to maintain a circular motion that prevents a jackknife condition). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Hafner teaches a trailer backup assist system that generates steering commands for a vehicle-trailer to maintain a constant circular motion, a desired hitch angle, and prevent a jackknife condition.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponding to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized as taught by Hafner, with a reasonable expectation of success, in order to prevent a jackknife condition and steer the vehicle and move the trailer in compliance with a desired curvature as specified in at least [0359] of Hafner.
Moreover, Jing also fails to specifically disclose performing an off-grid search of motion primitives.
However, Botros, in the same field of endeavor teaches performing an off-grid search of motion primitives (See at least page 90 of Botros – “… We present an A*-based algorithm to compute feasible motions for difficult maneuvers in both parking lot and highway settings. The algorithm… accommodates off-lattice start and goal configurations up to a specified tolerance…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Botros teaches a motion planning system for autonomous vehicles that uses an algorithm to determine off-lattice start and goal configurations when determining feasible motions for the autonomous vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an off-grid search of motion primitives as taught by Botros, with a reasonable expectation of success, in order to accommodate off-lattice start and goal configurations up to a specified tolerance as specified in at least page 90 of Botros.
Lastly, Jing also fails to specifically disclose performing an online search of motion primitives.
However, Yano, in the same field of endeavor teaches performing an online search of motion primitives (See at least [0047]-[0049] of Yano – “… the control server 3 generates, as the target moving route TGT for one movable body 1, the route that allows the one movable body 1 to move… determines the position of the movable body …”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Yano teaches an autonomous vehicle control system that determines routes and positions for moving the movable body using an online server.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an online search of motion primitives as taught by Yano, with a reasonable expectation of success, in order to allow the movable body to move as specified in at least [0047] of Yano.
For claim 17, Jing discloses wherein the set of motion primitives includes multiple motion primitives pre-calculated for each pseudo-trailer-configuration induced state with an initial state of the tractor configuration being (0,0,0), wherein the starting value of the quantized pseudo-trailer configuration relates to the finite set of quantized pseudo-trailer configurations (See at least [0044] – “At 120, an arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle after (x.sub.0, y.sub.0)… which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0.” and [0051] – “… The method of finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle…”).
For claim 18, Jing discloses wherein motion primitives for the starting value or motion primitives for the ending value include multiple motion primitives with a same pseudo-trailer configuration but moving the trailer-based vehicle into different locations (See at least [0011] – “FIG. 2A depicts an example of offline searching for a family of arc paths from a target ending location and orientation to all possible starting locations and orientations in the mapped area with a discrete resolution…”, [0012] – “Fig. 2B depicts an example of position grid nodes connected with path arcs through various heading angle grid bins…”, and [0055] – “… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node…”).
For claim 20, Jing discloses a non-transitory computer readable storage medium embodied thereon a program executable by a processor for performing a method (See at least [0120] – “…Implementations of aspects of the subject matter described in this specification can be implemented as one or more computer program products, e.g., one or more modules of computer program instructions encoded on a tangible and non-transitory computer readable medium for execution by, or to control the operation of, data processing apparatus...”), the method comprising:
collecting a set of motion primitives parameterized on a quantized pseudo-trailer-configuration from a finite set of quantized pseudo-trailer-configurations, each motion primitive configured to move a trailer-based vehicle from a pseudo-trailer-configuration induced initial state relating to the finite set of quantized pseudo-trailer-configurations to another pseudo-trailer-configuration induced target state having a same or different pseudo-trailer-configuration relating to the finite set of quantized pseudo-trailer-configurations (See at least [0051]-[0053] – “The method of finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer… From a search starting location… a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… the generated optimal path library finds the global optimal path and actions for any given vehicle location and orientation state within the map… The disclosed offline path library generation method may be exhaustive to any given discretized vehicle location and orientation within the mapped range, and all of the paths originating from a vehicle starting state converge into one optimal path for the mapped area. This property robustly handles all potential autonomous driving states in the defined map region… develops a dynamic resolution technique that dynamically generates the heading angle resolution grid values based on optimal solution local progressing at each position state instance… the optimal paths are stored… Each arc piece corresponds to an arc from one path state to another path state… The optimal path to an endpoint given the starting position and orientation can be extracted…”);
repetitively selecting a node based on a corresponding cost, and applying motion primitives at the selected node based on a corresponding pseudo-trailer-configuration to add new nodes which have pseudo-trailer-configurations belonging to a set of all possible values (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle… the path arc reaches to the lower layer position grid node…”, [0047] – “…one or more cost or performance metrics are applied to the arc path..”, [0051] – “… finding the optimal path includes searching all possible actions that can be taken by the tractor-trailer and evaluating the performance/cost metrics, starting from the desired terminal state point. From a search starting location, which is also a terminal state location, a family of paths exist where sections of each path may be represented by nodes. Each node corresponds to a family of parameter values including an x coordinate, a y coordinate and a heading angle… Each state space node of the map region links the decisions of preceding choices to get to that node including accumulated historical action metric values and costs…”, [0054]-[0055] – “FIG. 2A depicts an illustration at 210 of a family of arc paths… Each arc segment begins at a node and ends at another node… The arc segments shown at 210 are all the possible arc segments origination at 212 before the optimal path is chosen from a starting location... FIG. 2B depicts an illustration at 250 of locations or points in a grid map with bins and nodes… Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations… evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256…” and [0077] – “… the offline server may perform the evaluating operation … assigning costs for all of the trajectory connections to a layer of grid nodes, and saving optimal trajectory connections to every reachable grid node and grid bin pair, and deactivating grid node and grid bin pairs for the next layer's search evaluation when at least one criteria is violated.… that relate to motion control … the linkage information for optimal trajectory connections is saved to the optimal path library”), wherein a tractor configuration, x,y,00, is arbitrary (See at least [0044] – “an arc solver determines a continuous arc path of constant curvature … cause the tractor-trailer to move from (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t), which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”);
performing an offline search of motion primitives for the quantized pseudo-trailer configuration (See at least [0005] of Jing – “performing, by the offline server, an exhaustive search for an optimal vehicle driving trajectory for the discretized position space… includes evaluating driving trajectory connections between every two pairs of state space and grid nodes on two layers along a reference driving direction in the driving space to determine a best driving action leading to global optimal complete trajectories…”) and connecting a sequence of multiple motion primitives into a motion path connecting the initial state with the target state, wherein a starting value of a quantized pseudo-trailer-configuration of a subsequent motion primitive in the sequence equals an ending value of a quantized pseudo-trailer-configuration of a previous motion primitive in the sequence (See at least [0006] – “generating a library of optimal paths for an autonomous driving vehicle is disclosed… determining, at the offline server, path arcs between an evaluated state space node and reachable state space nodes … a path arc curvature… a tractor vehicle steering angle and coordinates for one or more body locations of the autonomous driving vehicle along the path arc… the steering controller steering angle…”, [0037] – “The paths are optimal in that the paths provide avoidance of collision with fixed objects, the paths minimize steering changes…” and [0044] – “arc solver determines a continuous arc path of constant curvature from location (x.sub.0, y.sub.0) to a point (x.sub.t, y.sub.t, θ.sub.t) that will be travelled by the vehicle after (x.sub.0, y.sub.0).… which includes the arc curvature κ, arc length L.sub.Arc, and the tractor vehicle's initial heading angle θ.sub.0…”); and
controlling the motion of the tractor-trailer according to the motion path (See at least [0056] – “… At 330, the bin with the closest heading angle to the vehicle heading is selected. At 340, the optimal parent layer node, bin, arc curvature, and arc length are read based on the matched grid node and the selected vehicle heading… At 350, the parent node location, arc curvature, and arc length are converted to a steering command to send to the autonomous steering controller…”).
Jing fails to specifically disclose collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space.
However, Dangel, in the same field of endeavor teaches collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space (See at least [0053] – “… at high velocities … resulting model involves eight states (longitudinal force/acceleration, steering angle, v.sub.x, v.sub.y, yaw-rate, s, w, relative heading)… At low velocities, the vehicle model used may for example be a simpler kinematic model with four states only (x and y coordinates, velocity and heading…” and [0098] of Dangel – “…It is advantageous to simplify the mathematical optimization problem such that a path can be found in real time (less than ms… While a full search method will search for a solution in a multi-dimensional space (e.g., including two space dimension, time, and other dimensions taking vehicle-related aspects such as orientation into account), blocks 3-5 in FIG. 1 may advantageously reduce this to three dimensions only… which reduces the problem size and, therefore, the optimization duration…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Dangel teaches a motion planning system for an autonomous vehicle that reduces the dimensions of vehicle state spaces by enforcing constraints on the number of dimensions that define the vehicle state spaces to generate optimized trajectories for the vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of collecting a set of motion primitives parameterized on a quantized pseudo-trailer- configuration from a finite set of quantized pseudo-trailer-configurations defined in a reduced state space resulting by enforcing an algebraic constraint on a configuration of the trailer-based vehicle in an original state space as taught by Dangel, with a reasonable expectation of success, in order to solve a coarse optimization problem in a very short time and control the vehicle using optimized trajectories as specified in at least [0098] and [0110]-[0111] of Dangel.
Furthermore, Jing also fails to specifically disclose wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer.
However, Laine, in the same field of endeavor teaches wherein the algebraic constraint defines a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer (See at least [0032]-[0037] of Laine – “… A vehicle state observer is used for estimating the position of the equivalent axle position 11 (Xp,Yp) of the last towed vehicle of the vehicle combination… The state space equations describing the state of a vehicle combination with two trailers could be expressed as in the following equations… using the equivalent axle position (XP,YP) and the effective wheelbase (L.sub.eq,1) for each towed vehicle and the heading θ.sub.n of the last n.sup.th towed vehicle… the swept area of the articulated vehicle can be calculated from the vehicle dimensions… The modified swept area is used to control the steering of the vehicle combination when reversing the vehicle combination along the specified path, such that the vehicle combination does not extend outwards of the modified swept area during the reversal…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Laine teaches an automatic reversing assistance system for a towing vehicle that simplifies state space equations for a vehicle combination with two trailers by taking into account the heading angle of a last towed vehicle to obtain a swept area of the vehicle combination to then control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the algebraic constraint defining a relationship between a steering input of the tractor and a resultant spatial configuration of the at least one trailer as taught by Laine, with a reasonable expectation of success, in order to simplify calculations using a linear vehicle model that represents a towing vehicle with towed vehicles combination as specified in at least [0030] of Laine and to further obtain a swept area to be used to control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing as specified in at least [0037] of Laine.
Additionally, Jing fails to specifically disclose wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized.
However, Hafner, in the same field of endeavor teaches wherein the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponds to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized (See at least [0148]-[0149] – “… Referring to FIG. 5… it is desirable to limit the potential for the vehicle 302 and the trailer 304 to attain a jackknife angle … for limiting the potential for a vehicle/trailer system attaining a jackknife angle, it is preferable to control the yaw angle of the trailer while keeping the hitch angle of the vehicle/trailer system relatively small… Referring to FIGS. 5 and 7, a steering angle limit for the steered front wheels 306 requires that the hitch angle .gamma. cannot exceed the jackknife angle … the jackknife angle .gamma.(j) is the hitch angle .gamma. that maintains a circular motion for the vehicle/trailer system when the steered wheels 306 are at a maximum steering angle…”, [0272]-[0275] – “… when the yaw rate of the vehicle 100 and the trailer 110 become equal, the actual hitch angle .gamma.(a) will likely be constant, such that the desired hitch angle provided by the trail backup steering input apparatus … is also constant and substantially achieved … the measured hitch angle .gamma.(m) and the steering angle .delta. are substantially constant during the reversing motion for at least a threshold period of time or over a threshold distance of motion…”, [0359] – “… Referring now to FIG. 59, a method for operating the trailer backup assist system 105 is illustrated… a desired hitch angle .gamma.(d) is determined based on the desired curvature .kappa..sub.2 and the steering angle .delta.. In one embodiment, at step 1542, a jackknife angle .gamma.(j) may be determined… as previously explained with reference to FIGS. 5 and 7, and thereby used to prevent the desired hitch angle .gamma.(d) from exceeding the jackknife angle … This controller implementing step 1544 is configured to generate the steering angle command consistent with the desired curvature .kappa..sub.2 …. thereby move the trailer 110 in compliance with the desired curvature .kappa..sub.2…” and Fig. 7 of Hafner – vehicle-trailer controlled to maintain a circular motion that prevents a jackknife condition). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time, while Hafner teaches a trailer backup assist system that generates steering commands for a vehicle-trailer to maintain a constant circular motion, a desired hitch angle, and prevent a jackknife condition.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the configuration of the trailer-based vehicle with the algebraic constraint enforced thereon corresponding to a stable circular configuration associated with driving the trailer-based vehicle with a fixed steering angle for a time period such that a relative angle between the at least one trailer and the tractor is stabilized as taught by Hafner, with a reasonable expectation of success, in order to prevent a jackknife condition and steer the vehicle and move the trailer in compliance with a desired curvature as specified in at least [0359] of Hafner.
Moreover, Jing also fails to specifically disclose performing an off-grid search of motion primitives.
However, Botros, in the same field of endeavor teaches performing an off-grid search of motion primitives (See at least page 90 of Botros – “… We present an A*-based algorithm to compute feasible motions for difficult maneuvers in both parking lot and highway settings. The algorithm… accommodates off-lattice start and goal configurations up to a specified tolerance…”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Botros teaches a motion planning system for autonomous vehicles that uses an algorithm to determine off-lattice start and goal configurations when determining feasible motions for the autonomous vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an off-grid search of motion primitives as taught by Botros, with a reasonable expectation of success, in order to accommodate off-lattice start and goal configurations up to a specified tolerance as specified in at least page 90 of Botros.
Lastly, Jing also fails to specifically disclose performing an online search of motion primitives.
However, Yano, in the same field of endeavor teaches performing an online search of motion primitives (See at least [0047]-[0049] of Yano – “… the control server 3 generates, as the target moving route TGT for one movable body 1, the route that allows the one movable body 1 to move… determines the position of the movable body …”). Thus, Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time and includes an offline search of motion primitives for the quantized pseudo-trailer configuration, while Yano teaches an autonomous vehicle control system that determines routes and positions for moving the movable body using an online server.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of performing an online search of motion primitives as taught by Yano, with a reasonable expectation of success, in order to allow the movable body to move as specified in at least [0047] of Yano.
Claims 6, 13, and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, and Yano, as applied to claim 1 above, and further in view of Floyd-Jones et al. US 20200377085 (“Floyd-Jones”).
For claim 6, Jing discloses the processor being further configured to:
construct a graph having multiple nodes defining states of the trailer-based vehicle with tractor configurations being unrestricted to pre-defined real values, wherein the nodes include at least one of a final node or a goal node defining the initial state of the trailer-based vehicle, and a root node defining the target state of the trailer-based vehicle (See at least [0011] – “FIG. 2A depicts an example of offline searching for a family of arc paths from a target ending location and orientation to all possible starting locations and orientations in the mapped area with a discrete resolution…”, [0012] – “Fig. 2B depicts an example of position grid nodes connected with path arcs through various heading angle grid bins…”, and [0055] – “… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node…”);
determine a first trajectory from at least one of the final node or the goal node to the root node of the graph (See at least [0055] – “… Each node includes grid bins such as grid bin 254… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node. Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations (and later searched locations) evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256...”); and
determine a second trajectory from the initial state to the root node of the graph (See at least [0054] – ““FIG. 2A depicts an illustration at 210 of a family of arc paths… Each arc segment begins at a node and ends at another node… The arc segments shown at 210 are all the possible arc segments origination at 212 before the optimal path is chosen from a starting location...”, [0055] – “… Each node includes grid bins such as grid bin 254… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node. Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations (and later searched locations) evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256...” and [0072] – “… iteratively generates multiple steering commands to navigate the autonomous vehicle between multiple current positions and multiple next positions based on multiple optimal paths retrieved from the pre-stored path library …”).
Jing fails to specifically disclose wherein each pair of nodes in the graph is connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives.
However, Floyd-Jones, in the same field of endeavor teaches wherein each pair of nodes in the graph is connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives (See at least [0147] – “FIG. 4 is an example motion planning lattice 400 for the primary agent 102 of FIG. 1 in the case where the goal of the primary agent 102 is to avoid collision with the dynamic obstacle B 112 of FIG. 1 that is approaching the primary agent, and an example path 412 (including the bolded edges of lattice 400 connecting node 408a to 408i) identified in the planning lattice 400 for the primary agent 102 to avoid collision with the dynamic obstacle B 112…” and [0158] of Floyd-Jones – “…once all edge costs of the planning lattice 400 have been assigned … the motion planner 280 may perform a calculation to determine a least cost path to or toward a goal state represented by a goal node. For example, the motion planner 280 may perform a least cost path algorithm from the current state of the primary agent 102 in the planning lattice 400 to possible final states. The least cost (closest to zero) path in the planning lattice 400 is then selected by the motion planner 280…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Floyd-Jones teaches a motion planner for an autonomous vehicle that connects nodes using edges for a primary agent to avoid a collision with an obstacle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of each pair of nodes in the graph being connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives as taught by Floyd-Jones, with a reasonable expectation of success, in order to determine a least cost path toward a goal state represented by a goal node and avoid a collision as specified in at least [0158] of Floyd-Jones.
For claim 13, Jing discloses wherein, for determining the first trajectory, the processor is configured to:
obtain a path from at least one of the final node or the goal node to the root node of the graph (See at least [0042] – “FIG. 1 depicts a process 100, in accordance with some example embodiments. The process generates an optimal path for a vehicle through a mapped area by evaluating all feasible path connections. The optimal path generation process may start at the desired ending location for the vehicle and end at the starting location for the vehicle. By exhaustively searching for a path from the ending location to the starting location, the search will result in globally optimal paths for any initial states within the search space…”);
record a moving direction, a steering action, and lengths of each edge (See at least [0056] – “…At 330, the bin with the closest heading angle to the vehicle heading is selected. At 340, the optimal parent layer node, bin, arc curvature, and arc length are read based on the matched grid node and the selected vehicle heading…At 350, the parent node location, arc curvature, and arc length are converted to a steering command to send to the autonomous steering controller…”);
acquire a first segment of the path with same moving direction (See at least [0056] – “…At 330, the bin with the closest heading angle to the vehicle heading is selected. At 340, the optimal parent layer node, bin, arc curvature, and arc length are read based on the matched grid node and the selected vehicle heading…”);
plan velocity and steering profiles for the first segment, based on the moving direction (See at least [0072] – “online server iteratively generates multiple steering commands to navigate the autonomous vehicle between multiple current positions and multiple next positions based on multiple optimal paths retrieved from the pre-stored path library such that a next position of a previous iteration is used as a current position of a next iteration until and end criterion is met by the autonomous vehicle. The steering commands may include… a steering torque command to the steering actuator at a vehicle longitudinal wheel speed…”);
remove the first segment from the path; and repeat recording, acquiring, planning, and removing until the path is empty (See at least [0080] – “… the search process repeats by repeating the evaluating the driving trajectory connections, the expanding the vehicle kinematic trace, and the keeping only the optimal trajectory connections to every reachable pair of grid nodes for each unevaluated layer of grid nodes until reaching the other margin of the interested area on the map which corresponds to the margin of searchable space of the map area…”).
For claim 19, Jing discloses the method further comprising:
constructing a graph having multiple nodes defining states of the trailer-based vehicle with tractor configurations being unrestricted to pre-defined real values, wherein the nodes include at least one of a final node or a goal node defining the initial state of the trailer-based vehicle, and a root node defining the target state of the trailer-based vehicle (See at least [0011] – “FIG. 2A depicts an example of offline searching for a family of arc paths from a target ending location and orientation to all possible starting locations and orientations in the mapped area with a discrete resolution…”, [0012] – “Fig. 2B depicts an example of position grid nodes connected with path arcs through various heading angle grid bins…”, and [0055] – “… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node…”);
determining a first trajectory from at least one of the final node or the goal node to the root node of the graph (See at least [0055] – “… Each node includes grid bins such as grid bin 254… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node. Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations (and later searched locations) evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256...”); and
determining a second trajectory from the initial state to the root node of the graph (See at least [0054] – ““FIG. 2A depicts an illustration at 210 of a family of arc paths… Each arc segment begins at a node and ends at another node… The arc segments shown at 210 are all the possible arc segments origination at 212 before the optimal path is chosen from a starting location...”, [0055] – “… Each node includes grid bins such as grid bin 254… Each grid bin contains a most feasible heading angle for the vehicle to travel from the corresponding grid node. Upper layer grid bins such as grid bin 254 corresponding to earlier driven locations (and later searched locations) evaluate to determine a possible path based on the single heading angle stored in the next lower grid bin such as grid bin 256...” and [0072] – “… iteratively generates multiple steering commands to navigate the autonomous vehicle between multiple current positions and multiple next positions based on multiple optimal paths retrieved from the pre-stored path library …”).
Jing fails to specifically disclose wherein each pair of nodes in the graph is connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives.
However, Floyd-Jones, in the same field of endeavor teaches wherein each pair of nodes in the graph is connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives (See at least [0147] – “FIG. 4 is an example motion planning lattice 400 for the primary agent 102 of FIG. 1 in the case where the goal of the primary agent 102 is to avoid collision with the dynamic obstacle B 112 of FIG. 1 that is approaching the primary agent, and an example path 412 (including the bolded edges of lattice 400 connecting node 408a to 408i) identified in the planning lattice 400 for the primary agent 102 to avoid collision with the dynamic obstacle B 112…” and [0158] of Floyd-Jones – “…once all edge costs of the planning lattice 400 have been assigned … the motion planner 280 may perform a calculation to determine a least cost path to or toward a goal state represented by a goal node. For example, the motion planner 280 may perform a least cost path algorithm from the current state of the primary agent 102 in the planning lattice 400 to possible final states. The least cost (closest to zero) path in the planning lattice 400 is then selected by the motion planner 280…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Floyd-Jones teaches a motion planner for an autonomous vehicle that connects nodes using edges for a primary agent to avoid a collision with an obstacle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of each pair of nodes in the graph being connected with an edge defined by a collision-ignorant motion primitive from the set of motion primitives as taught by Floyd-Jones, with a reasonable expectation of success, in order to determine a least cost path toward a goal state represented by a goal node and avoid a collision as specified in at least [0158] of Floyd-Jones.
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, and Yano, as applied to claim 1 above, and further in view of Wang US 20200097014 (“Wang”).
For claim 7, Jing fails to specifically disclose the processor being further configured to: select nodes of the graph according to a cost of each of the selected nodes, wherein the cost of a node includes a cost of arrival and an estimated cost-to-go determined by evaluating a heuristic function.
However, Wang, in the same field of endeavor teaches the processor being further configured to: select nodes of the graph according to a cost of each of the selected nodes, wherein the cost of a node includes a cost of arrival and an estimated cost-to-go determined by evaluating a heuristic function (See at least [0119] of Wang – “… specifically node X.sub.bestg is selected for expansion since it has the lowest cost among custom-character.sub.g. Its expansion, with a control action A.sub.g, results in a child node X.sub.g. The cost of the node X.sub.g is given by the sum of its arrival cost and estimated cost-to-go…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Wang teaches a system for controlling movement of a vehicle that constructs a graph using doubletree construction to select an expandable node based on cost of the expandable node.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of selecting nodes of the graph according to a cost of each of the selected nodes, wherein the cost of a node includes a cost of arrival and an estimated cost-to-go determined by evaluating a heuristic function as taught by Wang, with a reasonable expectation of success, in order to expand nodes of minimum cost in a doubletree graph construction and make the graph extension more computationally efficient as specified in at least [0110] of Wang.
Claims 8 and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, Yano, and Wang, as applied to claim 7 above, and further in view of Huh et al. US 20220276657 (“Huh”).
For claim 8, Jing fails to specifically disclose the processor being further configured to: calculate the estimated cost-to-go of each of the selected nodes using a neural network.
However, Huh, in the same field of endeavor teaches the processor being further configured to: calculate the estimated cost-to-go of each of the selected nodes using a neural network (See at least [0061] – “… the second neural network may obtain the first configuration, through operation S104, and the second configuration through a user or operator input, and may output an estimated cost-to-go from the first configuration to the second configuration…” and [0057] of Huh – “the second neural network may be formed by assigning the weights to a plurality of nodes of the second neural network… connections between the layers and nodes may be also predetermined and pre-stored, so that the second neural network can be generated once the weights are obtained from the first neural network…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Huh teaches a system for generating a trajectory for an autonomous vehicle by using a neural network to calculate a cost-to-go value from a first configuration to a second configuration.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of calculating the estimated cost-to-go of each of the selected nodes using a neural network as taught by Huh, with a reasonable expectation of success, in order to generate a trajectory from a first configuration to a second configuration that steers the robot (i.e., autonomous vehicle) away from obstacles as specified in at least [0067] of Huh.
For claim 9, Jing fails to specifically disclose wherein the neural network has an input as two states of the trailer-based vehicle in one of the original state space or the reduced state space.
However, Huh, in the same field of endeavor teaches wherein the neural network has an input as two states of the trailer-based vehicle in one of the original state space or the reduced state space (See at least [0121]-[0123] of Huh – “… the robot or the external device may generate an optical trajectory of the robot based on a first configuration (e.g., a current position of the robot) and a second configuration (e.g., a preset destination position of the robot)… The second neural network receives, as input, the first configuration and the second configuration, and outputs an estimated cost-to-go value from the first configuration to the second configuration…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Huh teaches a system for generating a trajectory for an autonomous vehicle by using a neural network to calculate a cost-to-go value from a first configuration to a second configuration.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of a neural network having an input as two states of the trailer-based vehicle in one of the original state space or the reduced state space as taught by Huh, with a reasonable expectation of success, in order to generate a trajectory from a first configuration to a second configuration that steers the robot (i.e., autonomous vehicle) away from obstacles as specified in at least [0067] of Huh.
Claim 10 is rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, Yano, Wang, and Huh, as applied to claim 8 above, and further in view of Minsky et al. US 20210334671 (“Minsky”).
For claim 10, Jing fails to specifically disclose wherein the cost-to-go is estimated by a finite number of neural networks, each neural network having a different pseudo-trailer-configuration induced state for its target state.
However, Minsky, in the same field of endeavor teaches wherein the cost-to-go is estimated by a finite number of neural networks, each neural network having a different pseudo-trailer-configuration induced state for its target state (See at least [0197] of Minsky – “The APP node's action-controller 232 may employ the allied planners 234 to compute the least cost sequence of actions to reach the goal state 234 over the system's graph of learned APP nodes, that is, the knowledge graph 222, to find the best path from a currently accessible state to the goal, that is, the goal state 234. The action-controller 232, also referred to interchangeably herein as a planner, employs the allied planners 234 and may be referred to herein as having an allied planning network (APN) architecture. The allied planners 234 may be a hybrid of different neural networks and may be referred to interchangeably herein as Allied Planning Networks (APNs) because such networks advise each other…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Minsky teaches a system for autonomous robots that computes costs to reach state goals over the system’s graph of learned nodes using a hybrid of different neural networks.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of estimating the cost-to-go by a finite number of neural networks with each neural network having a different pseudo-trailer-configuration induced state for its target state as taught by Minsky, with a reasonable expectation of success, in order to find the best path from a currently accessible state to a goal state as specified in at least [0197] of Minsky.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, Yano, Wang, and Huh, as applied to claim 8 above, and further in view of Xu et al. US 20220134546 (“Xu”).
For claim 11, Jing fails to specifically disclose wherein the neural network is trained using reinforcement learning with a sparse reward function.
However, Xu, in the same field of endeavor teaches wherein the neural network is trained using reinforcement learning with a sparse reward function (See at least [0015]-[0016] of Xu – “…reinforcement learning episodes can be performed in simulation using scripted movements or partially trained versions of the neural network model… In some implementations of reinforcement learning, the reward function is a sparse binary reward function, optionally with a small penalty given at each time step to encourage faster execution of the pushing or other manipulation…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Xu teaches a system for manipulating a robot that utilizes a trained neural network using reinforcement learning with a sparse reward function.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of the neural network being trained using reinforcement learning with a sparse reward function as taught by Xu, with a reasonable expectation of success, in order to encourage faster execution of manipulation of the mobile robot as discussed in at least [0016] of Xu.
Claim 12 is rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, Yano, Wang, and Huh, as applied to claim 8 above, and further in view of Movert et al. US 20190176818 (“Movert”).
For claim 12, Jing fails to specifically disclose wherein the neural network is obtained by training with supervised learning.
However, Movert, in the same field of endeavor teaches wherein the neural network is obtained by training with supervised learning (See at least [0038] of Movert – “The deep neural network may be trained by supervised learning based on target values and paths recorded from human drivers in traffic or from automated drivers in traffic… During supervised training the deep neural network is trained by comparing the path taken by the vehicle based on the predicted paths with the target values… the deep neural network learns to behave as the demonstrations…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Movert teaches a system for predicting a path for autonomous vehicles using a neural network trained with supervised learning.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of a neural network obtained by training with supervised learning as taught by Movert, with a reasonable expectation of success, in order to have a neural network learn to behave as the demonstrations of preferred behavior recorded from human drivers as specified in at least [0038] of Movert.
Claim 14 is rejected under 35 U.S.C. 103 as being unpatentable over Jing in view of Dangel, Laine, Hafner, Botros, Yano, and Floyd-Jones, as applied to claim 6 above, and further in view of Zhu et al. US 20190080266 (“Zhu”).
For claim 14, Jing fails to specifically disclose wherein, to determine the second trajectory, the processor is configured to:
pass the first trajectory to an iterative linear quadratic regulator (ILQR) to produce a second trajectory candidate;
check collision of the second trajectory candidate; and
output the second trajectory candidate as the second trajectory if it is collision-ignorant, else, solve an optimization problem for the second trajectory.
However, Zhu, in the same field of endeavor teaches wherein, to determine the second trajectory, the processor is configured to:
pass the first trajectory to an iterative linear quadratic regulator (ILQR) to produce a second trajectory candidate (See at least [0078] – “… Referring to FIG. 8, at block 801, processing logic calculates a first trajectory based on a map and a route information. At block 802, processing logic generates a path profile based on the first trajectory, traffic rules, and an obstacle information describing one or more obstacles perceived by the ADV… Quadratic programming optimization can be performed using respective path, speed, and/or obstacle cost functions to determine the most optimal route with the minimum total cost. At block 805, processing logic generates a second trajectory based on the optimal path and optimal speeds to control the ADV autonomously according to the second trajectory....”);
check collision of the second trajectory candidate (See at least [0086] – “… Obstacle planning module 1101 plans how an ADV is controlled in view of an obstacle. Obstacle cost calculator 1103 can calculate obstacle costs for each obstacle perceived by the ADV. The obstacle cost can represent a cost to avoid a collision between an obstacle and the particular trajectory being calculated. For example, a cost to avoid a collision between an obstacle and the trajectory can includes a cost based on a distance (“distance cost”) between the nearest point of the trajectory and the obstacle and a cost for a passing speed (“cost for passing speed”) estimated to pass the obstacle…”); and
output the second trajectory candidate as the second trajectory if it is collision-ignorant, else, solve an optimization problem for the second trajectory (See at least [0082] – “… At block 1002, processing logic generates a path profile based on the first trajectory, traffic rules, and an obstacle information describing one or more obstacles perceived by the ADV, where for each of the obstacles, the path profile includes a decision to nudge or yield to left or right of the obstacle… Quadratic programming optimization can be performed using respective path, speed, and/or obstacle cost functions to determine the most optimal route with the minimum total cost. At block 1005, processing logic controls the ADV according to the second trajectory…”). Thus, Jing discloses a system for an autonomous vehicle that is able to access information from a library of optimal paths based on a current position and navigate the autonomous vehicle, while Zhu teaches a system for generating a second trajectory from a first trajectory that prevents an autonomous vehicle from colliding with an obstacle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filing date of the claimed invention, to modify the system, method, and non-transitory computer readable storage medium for controlling a motion of a trailer-based vehicle from an initial state till a target state as disclosed in Jing to include the feature of outputting a second trajectory candidate as the second trajectory if it is collision-ignorant as taught by Zhu, with a reasonable expectation of success, in order to have the second trajectory optimized and avoid a collision with an obstacle as discussed in at least [0082] of Zhu.
Allowable Subject Matter
Claim 21 is objected to for containing allowable subject matter, but would be allowable if the claim rejections from previous sections of this office action were resolved.
The following is an Examiner’s statement of reasons for allowance:
The closest prior art of record is Jing et al. US 20210294333 (“Jing”), Dangel et al. US 20240300541 (“Dangel”), Laine US 20160114831 (“Laine”), Hafner et al. US 20140303849 A1 (“Hafner”), Botros “Lattice-Based Motion Planning with Optimal Motion Primitives” December 23, 2021 (“Botros”), Yano US 20230050172 A1 (“Yano”), Floyd-Jones et al. US 20200377085 (“Floyd-Jones”), Wang US 20200097014 (“Wang”), Huh et al. US 20220276657 (“Huh”), Minsky et al. US 20210334671 (“Minsky”), Xu et al. US 20220134546 (“Xu”), Movert et al. US 20190176818 (“Movert”), and Zhu et al. US 20190080266 (“Zhu”).
Jing discloses an autonomous driving system for a tractor-trailer that includes path planning to generate trajectories specific for vehicle locations and orientations that are updated in real time.
Dangel teaches a motion planning system for an autonomous vehicle that reduces the dimensions of vehicle state spaces by enforcing constraints on the number of dimensions that define the vehicle state spaces to generate optimized trajectories for the vehicle.
Laine teaches an automatic reversing assistance system for a towing vehicle that simplifies state space equations for a vehicle combination with two trailers by taking into account the heading angle of a last towed vehicle to obtain a swept area of the vehicle combination to then control the steering of the vehicle combination such that the vehicle combination does not extend outwards of the swept area when reversing.
Hafner teaches a trailer backup assist system that generates steering commands for a vehicle-trailer to maintain a constant circular motion, a desired hitch angle, and prevent a jackknife condition.
Botros teaches a motion planning system for autonomous vehicles that uses an algorithm to determine off-lattice start and goal configurations when determining feasible motions for the autonomous vehicle.
Yano teaches an autonomous vehicle control system that determines routes and positions for moving the movable body using an online server.
Floyd-Jones teaches a motion planner for an autonomous vehicle that connects nodes using edges for a primary agent to avoid a collision with an obstacle.
Wang teaches a system for controlling movement of a vehicle that constructs a graph using doubletree construction to select an expandable node based on cost of the expandable node.
Huh teaches a system for generating a trajectory for an autonomous vehicle by using a neural network to calculate a cost-to-go value from a first configuration to a second configuration.
Minsky teaches a system for autonomous robots that computes costs to reach state goals over the system’s graph of learned nodes using a hybrid of different neural networks.
Xu teaches a system for manipulating a robot that utilizes a trained neural network using reinforcement learning with a sparse reward function.
Movert teaches a system for predicting a path for autonomous vehicles using a neural network trained with supervised learning.
Zhu teaches a system for generating a second trajectory from a first trajectory that prevents an autonomous vehicle from colliding with an obstacle.
As to claim 21, the prior art of record, taken individually or in combination, fails to teach or suggest the following claimed subject matter:
“wherein the processor is further configured to, for each selected node, determine whether the selected node is being selected for a first time, and responsive to determining that the selected node is being selected for the first time:
categorize motion primitives associated with the selected node into a plurality of modes including forward-left, forward-right, backward-left, and backward-right;
compute, for each mode of the plurality of modes, a mode cost as an average of costs of motion primitives belonging to the mode, each motion primitive cost is based on (i) a cost of the motion primitive and (ii) a heuristic cost of a child node generated by applying the motion primitive;
select a mode having a minimum mode cost; and
apply motion primitives associated with the selected mode”
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MICHAEL J HERRERA whose telephone number is (571)270-5271. The examiner can normally be reached M-F 10:00 AM to 6:00 PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, FADEY JABR can be reached at (571)272-1516. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/M.J.H./Examiner, Art Unit 3668
/Fadey S. Jabr/Supervisory Patent Examiner, Art Unit 3668