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 .
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 4/16/2026 has been entered.
Response to Arguments
Applicant's arguments filed 10/28/2025 have been fully considered but are not persuasive.
Applicant asserts that Gross “is instead silent regarding an ‘estimated minimum cost’ and an ‘estimated maximum cost’” in page 11 of Applicant’s Remarks. However, Examiner respectfully disagrees. Gross discloses assigned costs for each node in the lattice solver graph where a lowest-cost path can be determined. Examiner sets forth that with the lattice solver graph, a maximum cost can also be determined. The costs of each node being computed beforehand does not mean the costs are not “estimated.” A calculation or judgement of value (cost) is still being made.
Applicant further asserts “Gross describes a compute-once-then-search framework wherein all node costs are computed prior to a graph search” in page 11 of Applicant’s Remarks. Examiner assumes this argument is being made to say that Applicant’s claims are meant to be a “on-the-go” calculation or that the calculations are done during a graph search. However, this element or limitation is not reflected in the claims as written. Gross also discloses that the lattice solver graph could be generated dynamically “on-the-fly” as the AV is operated indicating the costs may not all be computed at once as Applicant argues. As such, Gross still reads on the claims of the instant application and the rejection is therefore maintained as outlined below.
Response to Amendment
Regarding the rejections under 35 USC §112, Applicant has amended the claims to overcome the rejections. The rejections under 35 USC §112 have been withdrawn.
Regarding the rejections under 35 USC §103, amendments made to the claims fail to overcome the rejections. The rejections under 35 USC §103 are maintained as outlined below.
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 2-6, 8-12, and 15-19 are rejected under 35 U.S.C. 103 as being unpatentable over Gross et al. (U.S. Patent Application Publication No. 2018/0150081 A1; hereinafter Gross) in view of Popov et al. (U.S. Patent Application Publication No. 2021/0156963 A1; hereinafter Popov).
Regarding claim 2, Gross discloses:
A method comprising: determining a first candidate action for controlling motion of a vehicle (method for controlling a first vehicle, see at least [0005] and [0129]; first node 1501 includes an initial state and proceeds in one of three directions 1571, 1572, or 1573, wherein 1571 is for AV 10 decelerating, see at least [0105]-[0106]);
determining a first cost associated with the first candidate action (lattice of future states along with cost function for paths, see at least [0065] and [0084]; node 1511 has a cost associated therewith, see at least [0104]);
determining a lower bound cost based at least in part on the first cost and an additional cost associated with an additional candidate action (next node using one of the directions includes node 1521 when decelerating, see at least [0113]), the lower bound cost being an estimated minimum cost to move from a first state of the vehicle and being updated based at least in part on a lowest cost among the first cost and the additional cost (cost associated with node 1511 is low, see at least [0107]; cost associated with node 1521 is low, see at least [0116]; lowest-cost path is described as 1501, 1511, and 1521, see at least [0126]);
determining an upper bound cost based at least in part on performing a default action (from node 1511, node 1522 is when AV 10 is neither accelerating or decelerating, see at least [0113]; cost associated with node 1522, see at least [0116]) *Examiner sets forth that when a vehicle is not making any changes, hence not accelerating or decelerating, the vehicle is simply running in a continuing mode which reads on the “default action.”
the upper bound cost being an estimated maximum cost to move from a state associated with the first candidate action (cost associated with node 1522 may be significantly high, see at least [0116]; each node 1521-1525 includes a different respective state of AV, see at least [0116])
determining to perform the first candidate action based at least in part on the lower bound cost and the upper bound cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]); and
controlling the vehicle based at least in part on the first candidate action (selected path is implemented by AV 10, see at least [0126]).
Gross does not explicitly recite:
default action
However, However, Popov teaches:
default action (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the cost determination and maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 3, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the default action: repeating the first candidate action after performing the first candidate action; or maintaining a speed (node 1522 if AV is neither accelerating or decelerating, see at least [0113])
Gross does not disclose:
maintaining lane positioning of the vehicle
However, Popov teaches:
maintaining a speed and lane positioning of the vehicle after performing the first candidate action (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 4, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the upper bound cost is a first upper bound cost, and wherein determining to perform the first candidate action is further based on determining that the first upper bound cost is less than a second upper bound cost that is an estimated maximum cost to move from a state associated with the additional candidate action (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]; cost associated with nodes 1522 and 1523 may be significantly high, see at least [0116])
Regarding claim 5, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the lower bound cost is defined to be the first cost based at least in part on determining that the first cost is less than the additional cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]), and
wherein controlling the vehicle comprises determining a trajectory, the trajectory associated with a cost that is within a range defined by the lower bound cost and the upper bound cost (sequence of path segments are selected using the various nodes of the lattice solver graph that accomplishes the goal of AV to travel along its intended path while minimizing sum of the costs, see at least [0125]; the lattice solver graph having low and high costs, see at least [0126], [0116], and Fig. 15)
Regarding claim 6, The combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051]);
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a reactive object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054])
determining, based at least in part on executing a first simulation using the determination that the object is the reactive object, a first prediction (determine a set of predicted paths of one or more objects likely to intersect the region of interest, see at least [0062])
executing the first simulation using the determination that the object is the reactive object comprises determining a motion of a representation of the object based at least in part on the first candidate action (predicted paths of objects likely to intersect the region of interest are determined within a predetermined time interval or planning horizon, see at least [0098])
at least one of the lower bound cost or the upper bound cost is based at least in part on the first simulation (cost of nodes 1511-1548 are associated with whether another vehicle or other object is likely to contact the AV 10 or intersect with a path of the AV or whether the object is likely to come sufficiently close to contacting the AV, see at least [0104])
Regarding claim 8, Gross discloses:
A system comprising: one or more processors (at least one processor 44, see at least [0038]); and
a non-transitory memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising (computer-readable storage device or media 46 to store executable instructions used by the controller, see at least [0038]):
determining a first candidate action for controlling motion of a vehicle, the first candidate action being included in a trajectory (method for controlling a first vehicle, see at least [0005] and [0129]; first node 1501 includes an initial state and proceeds in one of three directions 1571, 1572, or 1573, wherein 1571 is for AV 10 decelerating, see at least [0105]-[0106]);
determining a first cost associated with the first candidate action (lattice of future states along with cost function for paths, see at least [0065] and [0084]; node 1511 has a cost associated therewith, see at least [0104]);
determining a lower bound cost based at least in part on the first cost and an additional cost associated with an additional candidate action (next node using one of the directions includes node 1521 when decelerating, see at least [0113]), the lower bound cost being an estimated minimum cost to move from a first state of the vehicle (cost associated with node 1511 is low, see at least [0107]; cost associated with node 1521 is low, see at least [0116]; lowest-cost path is described as 1501, 1511, and 1521, see at least [0126]);
determining an upper bound cost based at least in part on performing a default action (from node 1511, node 1522 is when AV 10 is neither accelerating or decelerating, see at least [0113]; cost associated with node 1522, see at least [0116]); *Examiner sets forth that when a vehicle is not making any changes, hence not accelerating or decelerating, the vehicle is simply running in a continuing mode which reads on the “default action.”
the upper bound cost being an estimated cost to move from a state associated with the first candidate action (cost associated with node 1522 may be significantly high, see at least [0116]; each node 1521-1525 includes a different respective state of AV, see at least [0116]);
determining whether to perform the first candidate action based at least in part on the lower bound cost and the upper bound cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]); and
controlling the vehicle based at least in part on the first candidate action (selected path is implemented by AV 10, see at least [0126]).
Gross does not explicitly recite:
default action associated with a default control instruction
However, However, Popov teaches:
default action associated with a default control instruction (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the cost determination and maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 9, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the default action: repeating the first candidate action after performing the first candidate action; or maintaining a speed of the vehicle after performing the first candidate action (node 1522 if AV is neither accelerating or decelerating, see at least [0113])
Gross does not disclose:
maintaining lane positioning of the vehicle
However, Popov teaches:
maintaining a speed and lane positioning of the vehicle after performing the first candidate action (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 10, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the upper bound cost associated with the first candidate action is a first upper bound cost, and wherein determining to perform the first candidate action is further based on determining that the first upper bound cost is less than a second upper bound cost that is an estimated cost to move from a state associated with the additional candidate action (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]; each node includes s different respective state and cost associated with nodes 1522 and 1523 may be significantly high, see at least [0116])
Regarding claim 11, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the lower bound cost is defined to be the first cost based at least in part on determining that the first cost is less than the additional cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125])
Regarding claim 12, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the operations further comprise: receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051]);
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a reactive object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054]); and
determining, based at least in part on executing a first simulation using the determination that the object is the reactive object, a first prediction (determine a set of predicted paths of one or more objects likely to intersect the region of interest, see at least [0062]),
wherein: executing the first simulation using the determination that the object is the reactive object comprises determining a motion of a representation of the object based at least in part on the first candidate action (predicted paths of objects likely to intersect the region of interest are determined within a predetermined time interval or planning horizon, see at least [0098]); and
at least one of the lower bound cost or the upper bound cost is based at least in part on the first simulation (cost of nodes 1511-1548 are associated with whether another vehicle or other object is likely to contact the AV 10 or intersect with a path of the AV or whether the object is likely to come sufficiently close to contacting the AV, see at least [0104]).
Regarding claim 15, Gross discloses:
One or more non-transitory computer-readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising (computer-readable storage device or media 46 to store executable instructions used by the controller, see at least [0038]; controller 34 includes at least one processor 44, see at least [0038]):
determining a first candidate action for controlling motion of a vehicle, the first candidate action being included in a trajectory (first node 1501 includes an initial state and proceeds in one of three directions 1571, 1572, or 1573, wherein 1571 is for AV 10 decelerating, see at least [0105]-[0106]; segments in a path, see at least [0125]);
determining a first cost associated with the first candidate action (lattice of future states along with cost function for paths, see at least [0065] and [0084]; node 1511 has a cost associated therewith, see at least [0104]);
determining a lower bound cost based at least in part on the first cost and an additional cost associated with an additional candidate action (next node using one of the directions includes node 1521 when decelerating, see at least [0113]), the lower bound cost being an estimated minimum cost to move from a first state of the vehicle (cost associated with node 1511 is low, see at least [0107]; cost associated with node 1521 is low, see at least [0116]; lowest-cost path is described as 1501, 1511, and 1521, see at least [0126]);
determining an upper bound cost based at least in part on performing a default action (from node 1511, node 1522 is when AV 10 is neither accelerating or decelerating, see at least [0113]; cost associated with node 1522, see at least [0116]); *Examiner sets forth that when a vehicle is not making any changes, hence not accelerating or decelerating, the vehicle is simply running in a continuing mode which reads on the “default action.”
the upper bound cost being an estimated cost to move from a state associated with the first candidate action (cost associated with node 1522 may be significantly high, see at least [0116]; each node 1521-1525 includes a different respective state of AV, see at least [0116]);
determining whether to perform the first candidate action based at least in part on the lower bound cost and the upper bound cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]); and
controlling the vehicle based at least in part on the first candidate action (selected path is implemented by AV 10, see at least [0126]).
Gross does not explicitly recite:
default action associated with a default control instruction
However, However, Popov teaches:
default action associated with a default control instruction (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the cost determination and maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 16, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the default action: repeating the first candidate action after performing the first candidate action; or maintaining a speed (node 1522 if AV is neither accelerating or decelerating, see at least [0113])
Gross does not disclose:
maintaining lane positioning of the vehicle
However, Popov teaches:
maintaining a speed and lane positioning of the vehicle after performing the first candidate action (default behavior may be to stay in lane, see at least [0070])
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the maintaining speed disclosed by Gross by adding the default behavior to stay in lane taught by Popov with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification “so that the feasible behaviors may be matched up with the most desired behaviors output from the lane planner” (see [0070]). Furthermore, not changing a speed and direction is a default for a cruise setting.
Regarding claim 17, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the upper bound cost associated with the first candidate action is a first upper bound cost, and wherein determining to perform the first candidate action is further based on determining that the first upper bound cost is less than a second upper bound cost that is an estimated cost to move from a state associated with the additional candidate action (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125]; each node includes s different respective state and cost associated with nodes 1522 and 1523 may be significantly high, see at least [0116]).
Regarding claim 18, The combination of Gross and Popov teaches the elements above and Gross further discloses:
the lower bound cost is defined to be the first cost based at least in part on determining that the first cost is less than the additional cost (system determines lowest-cost path is described by nodes 1501, 1511, 1521, see at least [0126]; select a lowest total cost path for AV 10 to travel, see at least [0125])
Regarding claim 19, The combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051]);
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a reactive object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054]); and
determining, based at least in part on executing a first simulation using the determination that the object is the reactive object, a first prediction (determine a set of predicted paths of one or more objects likely to intersect the region of interest, see at least [0062]), wherein:
executing the first simulation using the determination that the object is the reactive object comprises determining a motion of a representation of the object based at least in part on the first candidate action (predicted paths of objects likely to intersect the region of interest are determined within a predetermined time interval or planning horizon, see at least [0098]); and
at least one of the lower bound cost or the upper bound cost is based at least in part on the first simulation (cost of nodes 1511-1548 are associated with whether another vehicle or other object is likely to contact the AV 10 or intersect with a path of the AV or whether the object is likely to come sufficiently close to contacting the AV, see at least [0104])
Claims 7, 13-14, and 20-21 are rejected under 35 U.S.C. 103 as being unpatentable over Gross and Popov as applied to claims 2, 8, and 15 above and further in view of Floyd-Jones et al. (U.S. Patent Application Publication No. 2020/0377085 A1; hereinafter Floyd-Jones).
Regarding claim 7, The combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051])
determining, by a machine-learned model and based at least in part on the sensor data, the object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054])
Gross does not disclose:
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a passive object; and determining, based at least in part on modeling motion of the passive object, a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action; and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object.
However, Floyd-Jones teaches:
determining, based at least in part on the sensor data, that the object is a passive object (sensors collect information to produce model of environment including movement of agents such as obstacle A 104, wherein object A moves away from the primary agent, see at least [0132]-[0133] and Fig. 1) *Examiner sets forth passive object is one that will not interact with the host vehicle (primary agent) ; and
determining, based at least in part on modeling motion of the passive object (generate predicted trajectory for obstacle 104, see at least [0132]), a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action (object behavior predicter generates one or more predicted trajectories of the dynamic obstacle such as indicating obstacle A 104 is currently on a trajectory heading in a particular direction, see at least [0132]-[0133]); and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object (motion planner adjusts cost values along edge in planning lattice based on the collision assessment to account for the predicted trajectories, see at least [0137]).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the object classification and path determination disclosed by Gross and the default behavior to stay in lane taught by Popov by adding the obstacle moving away taught by Floyd-Jones with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because such “functions may advantageously require less computational expense when performing collision assessment than motion equations for example by avoiding the need to evaluate trigonometric functions” (see [0005]).
Regarding claim 13, The combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051]);
determining, by a machine-learned model and based at least in part on the sensor data, the object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054])
Gross does not disclose:
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a passive object; and determining, based at least in part on modeling motion of the passive object, a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action; and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object.
However, Floyd-Jones teaches:
determining, based at least in part on the sensor data, that the object is a passive object (sensors collect information to produce model of environment including movement of agents such as obstacle A 104, wherein object A moves away from the primary agent, see at least [0132]-[0133] and Fig. 1) *Examiner sets forth passive object is one that will not interact with the host vehicle (primary agent) ; and
determining, based at least in part on modeling motion of the passive object (generate predicted trajectory for obstacle 104, see at least [0132]), a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action (object behavior predicter generates one or more predicted trajectories of the dynamic obstacle such as indicating obstacle A 104 is currently on a trajectory heading in a particular direction, see at least [0132]-[0133]); and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object (motion planner adjusts cost values along edge in planning lattice based on the collision assessment to account for the predicted trajectories, see at least [0137]).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the object classification and path determination disclosed by Gross and the default behavior to stay in lane taught by Popov by adding the obstacle moving away taught by Floyd-Jones with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because such “functions may advantageously require less computational expense when performing collision assessment than motion equations for example by avoiding the need to evaluate trigonometric functions” (see [0005]).
Regarding claim 14, the combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051])
Gross does not disclose:
determining, based at least in part on the sensor data, a likelihood that the object will modify a behavior in response to one or more of the first candidate action or the additional candidate action; and one of: determining to classify the object as a reactive object based at least in part on the likelihood meeting or exceeding a threshold; or determining to classify the object as a passive object based at least in part on the likelihood being less than or equal to the threshold.
However, Floyd-Jones teaches:
determining, based at least in part on the sensor data, a likelihood that the object will modify a behavior in response to one or more of the first candidate action or the additional candidate action (motion planner determines probability of collision, see at least [0154]) *Examiner sets forth collision requires modification of behavior from both parties
determining to classify the object as a reactive object based at least in part on the likelihood meeting or exceeding a threshold; or determining to classify the object as a passive object based at least in part on the likelihood being less than or equal to the threshold (determine collision and assign weight with value greater than zero if probability of collision is greater than a particular threshold, see at least [0154]; motion planner assigns a weight with value greater than zero for probability of collision with dynamic obstacle B, see at least [0154]). *Examiner sets forth that dynamic object A does not have edges assigned with weight because it is moving away from the primary agent and does not meet the probability of collision
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the object classification and path determination disclosed by Gross and the default behavior to stay in lane taught by Popov by adding the obstacle collision and pathing taught by Floyd-Jones with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because such “to identify a path 512 in the resulting planning lattice 500 that provides a route of travel of the primary agent 102 as specified by the path with a relatively low potential of a collision with dynamic obstacle” (see [0157]).
Regarding claim 20, the combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051])
determining, by a machine-learned model and based at least in part on the sensor data, the object (predict classification and path of objects and features of the environment of the vehicle, see at least [0051]; avoiding moving objects; modules may be implemented as machine learning models and perform classification, see at least [0066] and [0054])
Gross does not disclose:
determining, by a machine-learned model and based at least in part on the sensor data, that the object is a passive object; and determining, based at least in part on modeling motion of the passive object, a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action; and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object.
However, Floyd-Jones teaches:
determining, based at least in part on the sensor data, that the object is a passive object (sensors collect information to produce model of environment including movement of agents such as obstacle A 104, wherein object A moves away from the primary agent, see at least [0132]-[0133] and Fig. 1) *Examiner sets forth passive object is one that will not interact with the host vehicle (primary agent) ; and
determining, based at least in part on modeling motion of the passive object (generate predicted trajectory for obstacle 104, see at least [0132]), a first prediction, wherein: modeling the motion of the passive object comprises determining motion of the passive object based at least in part on a state of the object and exclusive of the first candidate action (object behavior predicter generates one or more predicted trajectories of the dynamic obstacle such as indicating obstacle A 104 is currently on a trajectory heading in a particular direction, see at least [0132]-[0133]); and at least one of the lower bound cost or the upper bound cost is based at least in part on modeling the motion of the passive object (motion planner adjusts cost values along edge in planning lattice based on the collision assessment to account for the predicted trajectories, see at least [0137]).
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the object classification and path determination disclosed by Gross and the default behavior to stay in lane taught by Popov by adding the obstacle moving away taught by Floyd-Jones with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because such “functions may advantageously require less computational expense when performing collision assessment than motion equations for example by avoiding the need to evaluate trigonometric functions” (see [0005]).
Regarding claim 21, the combination of Gross and Popov teaches the elements above and Gross further discloses:
receiving sensor data indicating an object (receive and process signals from sensor system 28 to predict presence of objects, see at least [0039] and [0051])
Gross does not disclose:
determining, based at least in part on the sensor data, a likelihood that the object will modify a behavior in response to one or more of the first candidate action or the additional candidate action; and one of: determining to classify the object as a reactive object based at least in part on the likelihood meeting or exceeding a threshold; or determining to classify the object as a passive object based at least in part on the likelihood being less than or equal to the threshold.
However, Floyd-Jones teaches:
determining, based at least in part on the sensor data, a likelihood that the object will modify a behavior in response to one or more of the first candidate action or the additional candidate action (motion planner determines probability of collision, see at least [0154]) *Examiner sets forth collision requires modification of behavior from both parties
determining to classify the object as a reactive object based at least in part on the likelihood meeting or exceeding a threshold; or determining to classify the object as a passive object based at least in part on the likelihood being less than or equal to the threshold (determine collision and assign weight with value greater than zero if probability of collision is greater than a particular threshold, see at least [0154]; motion planner assigns a weight with value greater than zero for probability of collision with dynamic obstacle B, see at least [0154]). *Examiner sets forth that dynamic object A does not have edges assigned with weight because it is moving away from the primary agent and does not meet the probability of collision
It would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the object classification and path determination disclosed by Gross and the default behavior to stay in lane taught by Popov by adding the obstacle collision and pathing taught by Floyd-Jones with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because such “to identify a path 512 in the resulting planning lattice 500 that provides a route of travel of the primary agent 102 as specified by the path with a relatively low potential of a collision with dynamic obstacle” (see [0157]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Lin et al. (U.S. Patent Application Publication No. 2022/0097736 A1) teaches a vehicle control method using real-time road conditions and a current travelling state in a prediction model to obtain the next control. A pre-built search tree is used for the target path using node rewards and a predicted collision outcome based on the path of the current node.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HANA LEE whose telephone number is (571)272-5277. The examiner can normally be reached Monday-Friday: 7:30AM-4:30PM 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, Jelani Smith can be reached at (571) 270-3969. 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.
/H.L./Examiner, Art Unit 3662
/DALE W HILGENDORF/Primary Examiner, Art Unit 3662
Prosecution Insights