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 .
This is a Final Office Action on the merits. Claims 1-11, 13-19, and 21-22 are currently pending and are addressed below.
Response to Amendment
1. The amendment filed 12/15/2025 has been entered. Claims 1-11, 13-19, and 21-22 remain pending in the application. Applicant’s amendments to the claims have overcome each objection and 35 USC § 101 rejection previously set forth in the Non-Final Office Action mailed September 16, 2025.
Response to Arguments
2. Applicant’s arguments filed 12/15/2025 have been fully considered but they are not persuasive.
Regarding the rejection made under 35 USC 103, the Applicant’s arguments have been fully considered but are not persuasive. Applicant argues on page 12 that Takabayashi describes a plurality of trajectories; however, Takabayashi fails to describe a graph, much less projecting a state of the trajectory onto the graph. Applicant further argue that even if Takabayashi did describe projecting the state onto the graph, Takabayashi fails to describe “connecting…the ending states to a node in the graph.” The examiner respectfully disagrees. Fig. 10 of Takabayashi illustrates a graph with a node at the end of a trajectory that is closest to intermediate destination 300 (ending state of a trajectory) projected on the graph. The ending state of the trajectory is connected to a node based on projecting the ending state on the graph (see at least Fig. 10 and [0173-0176]). Specifically, Takabayashi states “FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.” ([0173]). Additionally, Takabayashi states “[t]he second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.” ([0176]). The Applicant fails to provide a clear distinction between the claim language and the prior art and therefore, the prior art meets the claim limitations. Thus, Takabayashi teaches projecting an ending state of a trajectory onto the graph and connecting, based at least in part on projecting the ending state onto the graph, the ending state of the trajectory to a node in the graph.
Therefore, the prior art meets the claim limitations, and the Applicant’s arguments are not persuasive.
Claim Rejections - 35 USC § 112
3. The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
4. Claims 21-22 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement. The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for applications subject to pre-AIA 35 U.S.C. 112, the inventor(s), at the time the application was filed, had possession of the claimed invention. Specification is utilized for the description citations below.
Regarding claim 21 (and similarly 22), the limitation “wherein the graph excludes the trajectory" is not expressly, implicitly, or inherently described in the Specification as filed. The specification does not provide the terminologies “wherein the graph excludes the trajectory”. The claim as stated includes “wherein the graph excludes the trajectory” and the specification does not have support for these limitations.
In the art rejection above, the claims have been treated as best understood by the examiner.
5. The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
6. Claims 21-22 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Regarding claim 21 (and similarly 22), the limitation “wherein the graph excludes the trajectory" is indefinite because the applicant’s intended scope for the limitation is unclear. It is unclear how the graph can exclude the trajectory if the trajectory was already included and projected onto the graph in the previous claim. As discussed above, the specification does not provide the terminologies “wherein the graph excludes the trajectory”.
In the art rejection above, the claims have been treated as best understood by the examiner. Any claim not explicitly rejected under this heading is rejected as being dependent on an indefinite claim.
Claim Rejections - 35 USC § 103
7. 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 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.
8. Claims 1-11 and 13-19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Takabayashi et al. (US 20210163010, hereinafter Takabayashi) in view of Nister et al. (US 20230341234, hereinafter Nister).
Regarding claim 1, Takabayashi teaches a system comprising:
one or more processors (see at least Fig. 1 and [0055]: “The processor 2a is a calculation processing circuit that performs various types of calculation processing in the control ECU 2, and is hardware called a processor, a calculation processing circuit, an electric circuit, a controller, and the like. The processor 2a includes a set of one or more calculation processing circuits. The processor 2a is capable of reading a program from the ROM 2b and deploying the program on the RAM 2c to execute calculation processing.”); and
one or more non-transitory computer-readable media storing computer-executable instructions that, when executed, cause the system to perform operations (see at least Fig. 1 and [0056]: “The ROM 2b is a non-volatile storage device for storing one or more programs.”; [0057]: “The RAM 2c is a volatile storage device that the processor 2a uses as a deployment area for programs and various types of information.”) comprising:
receiving a destination associated with an environment (see at least [0101]: “The determination unit 38 determines an intermediate destination, which is the position of the vehicle at estimation time, for each estimation time. For example, the determination unit 38 determines the position information of an intermediate destination for each estimation time which is sequentially set from the current time, assuming that the vehicle travels at a constant velocity up to the estimation time, on the basis of the position and the speed of the vehicle acquired by the second information acquiring unit 31 and the map information.”; Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”);
receiving, from a sensor associated with a vehicle, sensor data associated with the environment (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle. The group of sensors 1 includes a speed sensor 1a, a steering angle sensor 1b, an accelerator sensor 1c, a brake sensor 1d, an acceleration sensor 1e, an angular velocity sensor 1f, a global positioning system (GPS) device 1g, an external camera 1h, and an external sensor 1i.”);
determining, based at least in part on the destination and the sensor data, a plurality of lane segments associated with a region of the environment between a position of the vehicle and the destination (see at least Fig. 9 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; [0171]: “As a result, the cost of the adjacent lane 201 drops relatively to the lane 200 as illustrated in FIG. 9, a candidate estimated path 301 along which the vehicle 100 travels on the adjacent lane 201 becomes more likely to be selected.”; [0172]: “Alternatively, the second calculation unit 37 may calculate the cost for an estimated position of the vehicle 100 at each time step estimated by the estimated path setting unit 39.”; Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”);
determining, based at least in part on the plurality of lane segments and the sensor data, a graph comprising a plurality of nodes and a plurality of edges between the plurality of nodes, the graph including an action for the vehicle to transition from a first node of the plurality of nodes to a second node of the plurality of nodes (see at least Figs. 9-10 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining, based at least in part on the sensor data, a transition associated with the action (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle.”; [0205]: “The estimated path setting unit 39 may calculate the likelihood of the nodes 302 on the basis of the costs set to the nodes 302 according to the following equation (6). With this, the estimated path setting unit 39 may identify anode 302 having a high likelihood L.sub.i(k) from among the N nodes 302 at the previous time step t.sub.p, k-1 and generate a node 302 at the following time steps t.sub.p, k from the identified node 302.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”);
determining a cost associated with the first node, the cost representing a cost of navigating from the first node to a boundary of the graph (see at least Figs. 7-9 and [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0167]: “FIG. 8 is a graph illustrating the relationship between the area in the road width direction and the cost when the highest cost is set to the adjacent lane 201. In FIG. 8, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; Fig. 9 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”);
projecting an ending state of a trajectory onto the graph (see at least Fig. 10, [0173], and [0176]: Fig. 10 illustrates a graph with a node at the end of a trajectory that is closest to intermediate destination 300 (ending state of a trajectory) projected on the graph.);
connecting, based at least in part on projecting the ending state onto the graph, the ending state of the trajectory to a node in the graph (see at least Fig. 10 and [0173-0176]: the ending state of the trajectory is connected to a node based on projecting the ending state on the graph.);
determining, based at least in part on connecting the ending state of the trajectory to the node in the graph, to follow the trajectory (see at least Fig. 10 and [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”); and
controlling the vehicle based at least in part on the trajectory (see at least [0054]: “The control ECU 2 has a function of controlling the entire vehicle.”; [0188]: “In step ST9, the estimated path setting unit 39 generates a plurality of candidate estimated paths 301 on which the vehicle 100 travels toward the intermediate destination 300 while avoiding the moving objects present by the estimation time, depending on the cost information of the lanes. The estimated path setting unit 39 sets an estimated path selected from the plurality of candidate estimated paths 301 as the path of the vehicle 100 for each estimation time.”; [0189]: “For example, the estimated path setting unit 39 sets, in the control ECU 2, estimated path information selected for each estimation time. The control ECU 2 controls the operation of the vehicle 100 in accordance with the estimated path information set from the estimated path setting unit 39 and thereby causes the vehicle 100 to travel along the estimated path.”).
Takabayashi fails to explicitly teach determining a probability of the transition associated with the action and determining, based at least in part on the probability, a cost associated with the first node, the cost representing a cost of navigating from the first node to a connection node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability of a transition associated with an action (see at least [0064]: “The large lane graph 130 is processed at the lane planner 110 to generate lane planner output data that includes equivalent times 114 at a plurality of nodes of the large lane graph. With the equivalent times 114, the value of an action can be calculated as an expected value over the probabilistic outcomes of that action into the next node. Lane planner output data can further include a probability associated with an action that indicates a best action from each node. It is further contemplated that a single nominal plan can be generated—for example as a visualization or for cueing the motion planner—by assuming that the actions will succeed.”) and determines, based at least in part on the probability, a cost associated with the first node, the cost representing a cost of navigating from the first node to a connection node (see at least [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; [0071]: “The expected time reward 114 may refer to the optimal expected value, and each large lane graph node can be assigned an expected equivalent time reward (e.g., expected equivalent time rewards 114 of FIG. 1A). The expected equivalent time reward of a node measures, in terms of time, how good it is to arrive at the target starting from this node. An expected equivalent time reward 114 may refer to, for a driving route, a time a driver is willing to spend minus an expected equivalent time cost.”; [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determine a probability of the transition associated with the action and determine, based at least in part on the probability, a cost associated with a first node, the cost representing a cost of navigating from the first node to a connection node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 2, modified Takabayashi teaches the limitations of claim 1. Takabayashi further teaches wherein the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), wherein determining the trajectory for the vehicle comprises:
associating the ending state of the trajectory with the graph (see at least Figs. 9-10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”);
associating a second action to the graph, the second action located between the ending state and the first node (see at least [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
associating an edge with the ending state of the trajectory, the second action, and the first node (see at least Figs. 9-10 and [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0175]: “Moreover, information of the state of the vehicle 100 for each estimated position is set in a node 302. Hereinafter, an estimated position of the vehicle 100 is referred to as a node 302 for the sake of convenience.”); and
determining, based at least in part on the second action and the edge, a second cost associated with the ending state of the trajectory (see at least Figs. 9-10 and [0184]: “For example, the second calculation unit 37 sets a low cost to a node 302 closer to the center line of a lane among a plurality of nodes 302 included in a candidate estimated path 301, sets a low cost to a node 302 at which an estimated speed of the vehicle 100 is close to a recommended speed, and sets a high cost to a node 302 close to an estimated position of the moving object.”).
Regarding claim 3, modified Takabayashi teaches the limitations of claim 1. Takabayashi further teaches wherein the cost is a first cost and the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), and wherein determining the first cost comprises:
identifying a second action within the graph (see at least [0172]: “Alternatively, the second calculation unit 37 may calculate the cost for an estimated position of the vehicle 100 at each time step estimated by the estimated path setting unit 39.”);
determining, based at least in part on the first action, a second cost (see at least [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining, based at least in part on the second action, a third cost (see at least [0177]: “In addition, the second calculation unit 37 may set a lower cost as a node 302 in the plurality of candidate estimated paths 301 approaches the center line of a lane.”; [0181]: “In addition, the second calculation unit 37 may set a higher cost as a node 302 approaches an estimated position of a moving object.”); and
determining, based at least in part on the second cost being less than the third cost, that the second cost is the first cost (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”).
Regarding claim 4, modified Takabayashi teaches the limitations of claim 1. Takabayashi further teaches wherein determining the cost is based at least in part on a transition cost associated with navigating from the first node to the second node (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”) , determining the transition cost is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0161]: “The cost of the lane 200 is obtained by adding up the cost corresponding to a Euclidean distance between a node 302 and the center line a of the lane 200 with respect to the standard cost set to the center line a of the lane 200.”; [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”).
Regarding claim 5, modified Takabayashi teaches the limitations of claim 1.
Takabayashi fails to explicitly teach wherein determining the probability of the transition is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability of a transition based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0066]: “As such, the lane planner 110 receives the lane planner input data 112 and generates lane planner output data (e.g., lane planner output data 114 of FIG. 1A). The lane planner output data 114 includes expected equivalent time rewards (e.g., expected equivalent time rewards 114 in FIG. 1A) as discussed herein. The state and probabilistic action space facilitates executing a value iteration (e.g., via value iteration engine 110 of FIG. 1A) to find the best action and an expected equivalent time reward of any large lane graph node. The lane planner 110 generates lane guidance data: an expected equivalent time reward for each large lane graph node. Computing the expected equivalent time reward can include determining an action having a probability score that indicates a likelihood of executing the action. As such, instead of modelling actions that lead directly and deterministically to a certain node, the actions may also, based on other probabilities, allow the vehicle to arrive at a different node.”; [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; Fig. 2D and [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards. Controlling the number of iterations for executing the modified value iteration operation is based on at least one stopping criteria.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determines a probability of a transition based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 6, Takabayashi teaches one or more non-transitory computer-readable media storing instructions executable by one or more processors, wherein the instructions, when executed, cause a system to perform operations (see at least Fig. 1 and [0056]: “The ROM 2b is a non-volatile storage device for storing one or more programs.”; [0057]: “The RAM 2c is a volatile storage device that the processor 2a uses as a deployment area for programs and various types of information.”) comprising:
receiving a destination associated with an environment (see at least [0101]: “The determination unit 38 determines an intermediate destination, which is the position of the vehicle at estimation time, for each estimation time. For example, the determination unit 38 determines the position information of an intermediate destination for each estimation time which is sequentially set from the current time, assuming that the vehicle travels at a constant velocity up to the estimation time, on the basis of the position and the speed of the vehicle acquired by the second information acquiring unit 31 and the map information.”; Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”);
determining, based at least in part on the destination, a graph comprising a plurality of nodes and a plurality of edges between the plurality of nodes (see at least Figs. 9-10 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining an action for a vehicle to perform to move between two nodes of the plurality of nodes (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0205]: “The estimated path setting unit 39 may calculate the likelihood of the nodes 302 on the basis of the costs set to the nodes 302 according to the following equation (6). With this, the estimated path setting unit 39 may identify anode 302 having a high likelihood L.sub.i(k) from among the N nodes 302 at the previous time step t.sub.p, k-1 and generate a node 302 at the following time steps t.sub.p, k from the identified node 302.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”);
determining a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a boundary of the graph (see at least Figs. 7-9 and [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0167]: “FIG. 8 is a graph illustrating the relationship between the area in the road width direction and the cost when the highest cost is set to the adjacent lane 201. In FIG. 8, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; Fig. 9 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”);
projecting an ending state of a trajectory onto the graph (see at least Fig. 10, [0173], and [0176]: Fig. 10 illustrates a graph with a node at the end of a trajectory that is closest to intermediate destination 300 (ending state of a trajectory) projected on the graph.);
connecting, based at least in part on projecting the ending state onto the graph, the ending state of the trajectory to the node in the graph (see at least Fig. 10 and [0173-0176]: the ending state of the trajectory is connected to a node based on projecting the ending state on the graph.);
determining, based at least in part on connecting the ending state of the trajectory to the node in the graph and the cost, to follow the trajectory (see at least Fig. 10 and [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”); and
and controlling the vehicle based at least in part on the trajectory (see at least [0054]: “The control ECU 2 has a function of controlling the entire vehicle.”; [0188]: “In step ST9, the estimated path setting unit 39 generates a plurality of candidate estimated paths 301 on which the vehicle 100 travels toward the intermediate destination 300 while avoiding the moving objects present by the estimation time, depending on the cost information of the lanes. The estimated path setting unit 39 sets an estimated path selected from the plurality of candidate estimated paths 301 as the path of the vehicle 100 for each estimation time.”; [0189]: “For example, the estimated path setting unit 39 sets, in the control ECU 2, estimated path information selected for each estimation time. The control ECU 2 controls the operation of the vehicle 100 in accordance with the estimated path information set from the estimated path setting unit 39 and thereby causes the vehicle 100 to travel along the estimated path.”).
Takabayashi fails to explicitly teach determining a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes and determining, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes (see at least [0064]: “The large lane graph 130 is processed at the lane planner 110 to generate lane planner output data that includes equivalent times 114 at a plurality of nodes of the large lane graph. With the equivalent times 114, the value of an action can be calculated as an expected value over the probabilistic outcomes of that action into the next node. Lane planner output data can further include a probability associated with an action that indicates a best action from each node. It is further contemplated that a single nominal plan can be generated—for example as a visualization or for cueing the motion planner—by assuming that the actions will succeed.”) and determines, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node (see at least [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; [0071]: “The expected time reward 114 may refer to the optimal expected value, and each large lane graph node can be assigned an expected equivalent time reward (e.g., expected equivalent time rewards 114 of FIG. 1A). The expected equivalent time reward of a node measures, in terms of time, how good it is to arrive at the target starting from this node. An expected equivalent time reward 114 may refer to, for a driving route, a time a driver is willing to spend minus an expected equivalent time cost.”; [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determine a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes and determine, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 7, modified Takabayashi teaches the limitations of claim 6. Takabayashi further teaches wherein the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), wherein determining the trajectory for the vehicle comprises:
associating a second action to the graph, the second action being located between the ending state and the node (see at least Figs. 9-10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”); and
determining, based at least in part on the second action, a second cost associated with the ending state of the trajectory (see at least Figs. 9-10 and [0184]: “For example, the second calculation unit 37 sets a low cost to a node 302 closer to the center line of a lane among a plurality of nodes 302 included in a candidate estimated path 301, sets a low cost to a node 302 at which an estimated speed of the vehicle 100 is close to a recommended speed, and sets a high cost to a node 302 close to an estimated position of the moving object.”).
Regarding claim 8, modified Takabayashi teaches the limitations of claim 6. Takabayashi further teaches wherein the cost is a first cost and the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), and wherein determining the first cost comprises:
identifying a second action associated with the graph (see at least [0172]: “Alternatively, the second calculation unit 37 may calculate the cost for an estimated position of the vehicle 100 at each time step estimated by the estimated path setting unit 39.”);
determining, based at least in part on the first action, a second cost (see at least [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining, based at least in part on the second action, a third cost (see at least [0177]: “In addition, the second calculation unit 37 may set a lower cost as a node 302 in the plurality of candidate estimated paths 301 approaches the center line of a lane.”; [0181]: “In addition, the second calculation unit 37 may set a higher cost as a node 302 approaches an estimated position of a moving object.”); and
determining, based at least in part on the second cost being less than the third cost, that the second cost is the first cost (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”).
Regarding claim 9, modified Takabayashi teaches the limitations of claim 6. Takabayashi further teaches wherein the node is a first node, wherein the first node is connected to a second node by the action (see at least Fig. 10 and [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0180]: “By setting costs to the nodes 302 and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302 in this manner, a candidate estimated path 301 having less variations in the speed of the vehicle 100 becomes more likely to be selected.”).
Takabayashi fails to explicitly teach determining the probability is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0066]: “As such, the lane planner 110 receives the lane planner input data 112 and generates lane planner output data (e.g., lane planner output data 114 of FIG. 1A). The lane planner output data 114 includes expected equivalent time rewards (e.g., expected equivalent time rewards 114 in FIG. 1A) as discussed herein. The state and probabilistic action space facilitates executing a value iteration (e.g., via value iteration engine 110 of FIG. 1A) to find the best action and an expected equivalent time reward of any large lane graph node. The lane planner 110 generates lane guidance data: an expected equivalent time reward for each large lane graph node. Computing the expected equivalent time reward can include determining an action having a probability score that indicates a likelihood of executing the action. As such, instead of modelling actions that lead directly and deterministically to a certain node, the actions may also, based on other probabilities, allow the vehicle to arrive at a different node.”; [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; Fig. 2D and [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards. Controlling the number of iterations for executing the modified value iteration operation is based on at least one stopping criteria.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determines a probability of a transition based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 10, modified Takabayashi teaches the limitations of claim 6. Takabayashi further teaches wherein determining the cost is based at least in part on a transition cost associated with navigating from a first node of the plurality of nodes to a second node of the plurality of nodes (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”), determining the transition cost is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0161]: “The cost of the lane 200 is obtained by adding up the cost corresponding to a Euclidean distance between a node 302 and the center line a of the lane 200 with respect to the standard cost set to the center line a of the lane 200.”; [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”).
Regarding claim 11, modified Takabayashi teaches the limitations of claim 10. Takabayashi further teaches wherein determining the graph is based at least in part on at least one of:
determining, based at least in part on sensor data associated with the environment, the transition cost representing a value of transitioning from between the two nodes (see at least [0161]: “The cost of the lane 200 is obtained by adding up the cost corresponding to a Euclidean distance between a node 302 and the center line a of the lane 200 with respect to the standard cost set to the center line a of the lane 200.”; [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”),
detecting, based at least in part on the sensor data, the object blocking a driving lane associated with a portion of the graph (see at least Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”), or
associating, based at least in part on the sensor data, an additional action with the graph, the additional action instructing the vehicle to return to a previous state or to reduce velocity (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle. The group of sensors 1 includes a speed sensor 1a, a steering angle sensor 1b, an accelerator sensor 1c, a brake sensor 1d, an acceleration sensor 1e, an angular velocity sensor 1f, a global positioning system (GPS) device 1g, an external camera 1h, and an external sensor 1i.”; [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”; [0246]: “When having recognized that the vehicle 100 cannot overtake the preceding vehicle 101 from the value of the no-overtaking flag, the determination unit 38 sets an intermediate destination 300 at a position which is on the lane 200 that the vehicle 100 is traveling on and which allows the vehicle 100 to follow the preceding vehicle 101 without overtaking.”).
Regarding claim 13, modified Takabayashi teaches the limitations of claim 6. Takabayashi further teaches wherein the boundary includes the destination (see at least Figs. 6-10 and [0164]: “Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”).
Regarding claim 14, Takabayashi teaches a method (see at least Fig. 3) comprising:
receiving a destination associated with an environment (see at least [0101]: “The determination unit 38 determines an intermediate destination, which is the position of the vehicle at estimation time, for each estimation time. For example, the determination unit 38 determines the position information of an intermediate destination for each estimation time which is sequentially set from the current time, assuming that the vehicle travels at a constant velocity up to the estimation time, on the basis of the position and the speed of the vehicle acquired by the second information acquiring unit 31 and the map information.”; Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”);
determining, based at least in part on the destination, a graph comprising a plurality of nodes and a plurality of edges between the plurality of nodes (see at least Figs. 9-10 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining an action for a vehicle to perform to move between two nodes of the plurality of nodes (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0205]: “The estimated path setting unit 39 may calculate the likelihood of the nodes 302 on the basis of the costs set to the nodes 302 according to the following equation (6). With this, the estimated path setting unit 39 may identify anode 302 having a high likelihood L.sub.i(k) from among the N nodes 302 at the previous time step t.sub.p, k-1 and generate a node 302 at the following time steps t.sub.p, k from the identified node 302.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”);
determining a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a boundary of the graph (see at least Figs. 7-9 and [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0167]: “FIG. 8 is a graph illustrating the relationship between the area in the road width direction and the cost when the highest cost is set to the adjacent lane 201. In FIG. 8, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”; Fig. 9 and [0169]: “FIG. 9 is a graph illustrating the relationship between the area in the road width direction and the cost when a lower cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 9, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201 like in FIG. 7.”);
projecting an ending state of a trajectory onto the graph (see at least Fig. 10, [0173], and [0176]: Fig. 10 illustrates a graph with a node at the end of a trajectory that is closest to intermediate destination 300 (ending state of a trajectory) projected on the graph.);
connecting, based at least in part on projecting the ending state onto the graph, the ending state of the trajectory to the node in the graph (see at least Fig. 10 and [0173-0176]: the ending state of the trajectory is connected to a node based on projecting the ending state on the graph.);
determining, based at least in part on connecting the ending state of the trajectory to the node in the graph and the cost, to follow the trajectory (see at least Fig. 10 and [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”); and
controlling the vehicle based at least in part on the trajectory (see at least [0054]: “The control ECU 2 has a function of controlling the entire vehicle.”; [0188]: “In step ST9, the estimated path setting unit 39 generates a plurality of candidate estimated paths 301 on which the vehicle 100 travels toward the intermediate destination 300 while avoiding the moving objects present by the estimation time, depending on the cost information of the lanes. The estimated path setting unit 39 sets an estimated path selected from the plurality of candidate estimated paths 301 as the path of the vehicle 100 for each estimation time.”; [0189]: “For example, the estimated path setting unit 39 sets, in the control ECU 2, estimated path information selected for each estimation time. The control ECU 2 controls the operation of the vehicle 100 in accordance with the estimated path information set from the estimated path setting unit 39 and thereby causes the vehicle 100 to travel along the estimated path.”).
Takabayashi fails to explicitly teach determining a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes and determining, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes (see at least [0064]: “The large lane graph 130 is processed at the lane planner 110 to generate lane planner output data that includes equivalent times 114 at a plurality of nodes of the large lane graph. With the equivalent times 114, the value of an action can be calculated as an expected value over the probabilistic outcomes of that action into the next node. Lane planner output data can further include a probability associated with an action that indicates a best action from each node. It is further contemplated that a single nominal plan can be generated—for example as a visualization or for cueing the motion planner—by assuming that the actions will succeed.”) and determines, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node (see at least [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; [0071]: “The expected time reward 114 may refer to the optimal expected value, and each large lane graph node can be assigned an expected equivalent time reward (e.g., expected equivalent time rewards 114 of FIG. 1A). The expected equivalent time reward of a node measures, in terms of time, how good it is to arrive at the target starting from this node. An expected equivalent time reward 114 may refer to, for a driving route, a time a driver is willing to spend minus an expected equivalent time cost.”; [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determine a probability associated with an action for a vehicle to perform to move between two nodes of the plurality of nodes and determine, based at least in part on the probability, a cost associated with a node of the plurality of nodes representing a cost of navigating from the node to a connection node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 15, modified Takabayashi teaches the limitations of claim 14. Takabayashi further teaches wherein the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), wherein determining the trajectory for the vehicle comprises:
associating a second action to the graph, the second action being located between the ending state and the node (see at least Figs. 9-10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”); and
determining, based at least in part on the second action, a second cost associated with the ending state of the trajectory (see at least Figs. 9-10 and [0184]: “For example, the second calculation unit 37 sets a low cost to a node 302 closer to the center line of a lane among a plurality of nodes 302 included in a candidate estimated path 301, sets a low cost to a node 302 at which an estimated speed of the vehicle 100 is close to a recommended speed, and sets a high cost to a node 302 close to an estimated position of the moving object.”).
Regarding claim 16, modified Takabayashi teaches the limitations of claim 14. Takabayashi further teaches wherein the cost is a first cost and the action is a first action (see at least [0164]: “As a result, the cost becomes the lowest at the center line of each of the lanes while the cost increases with distance away from the center line of a lane, and thus a candidate estimated path deviating from the center line of a lane becomes unlikely to be selected. Meanwhile, since the maximum value of cost is set to the outside of the road as illustrated in FIG. 6, a candidate estimated path 301 on which the vehicle 100 travels outside the road is not selected.”; [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”), and wherein determining the first cost comprises:
identifying a second action associated with the graph (see at least [0172]: “Alternatively, the second calculation unit 37 may calculate the cost for an estimated position of the vehicle 100 at each time step estimated by the estimated path setting unit 39.”);
determining, based at least in part on the first action, a second cost (see at least [0165]: “FIG. 7 is a graph illustrating the relationship between the area in the road width direction and the cost when a higher cost is set for the adjacent lane 201 than that of the lane 200 on which the vehicle 100 is traveling. In FIG. 7, a partitioning line c is a boundary between the lane 200 and the adjacent lane 201.”; [0176]: “The second calculation unit 37 may set a lower cost as a node 302 at the end of a path or a node 302 closest to the intermediate destination 300 in the plurality of candidate estimated paths 301 approaches the intermediate destination 300.”);
determining, based at least in part on the second action, a third cost (see at least [0177]: “In addition, the second calculation unit 37 may set a lower cost as a node 302 in the plurality of candidate estimated paths 301 approaches the center line of a lane.”; [0181]: “In addition, the second calculation unit 37 may set a higher cost as a node 302 approaches an estimated position of a moving object.”); and
determining, based at least in part on the second cost being less than the third cost, that the second cost is the first cost (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”).
Regarding claim 17, modified Takabayashi teaches the limitations of claim 14. Takabayashi further teaches wherein the node is a first node, wherein the first node is connected to a second node by the action (see at least Fig. 10 and [0174]: “As illustrated in FIG. 10, a candidate estimated path 301 is formed by connecting, by a link, each node 302 set at an estimated position of the vehicle 100 at each time step.”; [0180]: “By setting costs to the nodes 302 and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302 in this manner, a candidate estimated path 301 having less variations in the speed of the vehicle 100 becomes more likely to be selected.”).
Takabayashi fails to explicitly teach determining the probability is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node.
However, Nister teaches a system and method for generating lane planner data for autonomous vehicles that determines a probability is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0066]: “As such, the lane planner 110 receives the lane planner input data 112 and generates lane planner output data (e.g., lane planner output data 114 of FIG. 1A). The lane planner output data 114 includes expected equivalent time rewards (e.g., expected equivalent time rewards 114 in FIG. 1A) as discussed herein. The state and probabilistic action space facilitates executing a value iteration (e.g., via value iteration engine 110 of FIG. 1A) to find the best action and an expected equivalent time reward of any large lane graph node. The lane planner 110 generates lane guidance data: an expected equivalent time reward for each large lane graph node. Computing the expected equivalent time reward can include determining an action having a probability score that indicates a likelihood of executing the action. As such, instead of modelling actions that lead directly and deterministically to a certain node, the actions may also, based on other probabilities, allow the vehicle to arrive at a different node.”; [0068]: “With reference to FIGS. 2B-2F, FIGS. 2B-2F illustrate features of a large lane graph 130. The large lane graph 130 includes positions of driving lanes (e.g., lane 202B, lane 204B, and lane 206B of FIG. 2B). The large lane graph 130 can be a directed graph having nodes (e.g., node 202C, node 204C, and node 206C of FIG. 2C) that are positions of driving lanes. The positions can be sampled from lane representations in the map associated with the drive plan. The directed graph can further include edges (e.g., edge 202D and action 208D, edge 204D and action 210D, and edge 206D and action 212D) that connect two nodes and describe actions. Actions can include any of the following: straight, left lane turn, right lane change, etc. (e.g., action 208D, action 210D, and action 212D, respectively).”; Fig. 2D and [0108]: “The method 500, at block B504, includes computing, for each, edge of the plurality of edges corresponding to a vehicle action, a cost function based at least in part on a time cost for traversing between the starting node and a connection node of the starting node and a probability of a vehicle action associated with the node succeeding. In one or more embodiments, such computation can be performed for each of the plurality of edges. The method 500, at block 506, includes computing the expected time reward for each node in the plurality of nodes is based at least in part on executing a modified value iteration that controls the number of iterations for executing the modified value iteration operation that computes the expected equivalent time rewards. Controlling the number of iterations for executing the modified value iteration operation is based on at least one stopping criteria.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Nister and provide a means to determines a probability of a transition based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node, with a reasonable expectation of success, in order to provide a likelihood for the best action from each node [0064].
Regarding claim 18, modified Takabayashi teaches the limitations of claim 14. Takabayashi further teaches wherein determining the cost is based at least in part on a transition cost associated with navigating from a first node of the plurality of nodes to a second node of the plurality of nodes (see at least [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”), determining the transition cost is based at least in part on at least one of: a distance between the first node and the second node, a time to navigate from the first node to the second node, a number of lane changes associated with navigating from the first node to the second node, or an object located at least partially between the first node and the second node (see at least [0161]: “The cost of the lane 200 is obtained by adding up the cost corresponding to a Euclidean distance between a node 302 and the center line a of the lane 200 with respect to the standard cost set to the center line a of the lane 200.”; [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”).
Regarding claim 19, modified Takabayashi teaches the limitations of claim 18. Takabayashi further teaches wherein determining the graph is based at least in part on at least one of:
determining, based at least in part on sensor data associated with the environment, the transition cost representing a value of transitioning from between the two nodes (see at least [0161]: “The cost of the lane 200 is obtained by adding up the cost corresponding to a Euclidean distance between a node 302 and the center line a of the lane 200 with respect to the standard cost set to the center line a of the lane 200.”; [0178]: “By setting a cost to a node 302 in this manner and preferentially selecting a candidate estimated path 301 having a low total sum of costs of all the nodes 302, a candidate estimated path 301 that does not deviate from the lane becomes more likely to be selected.”; [0209]: “For example, let us assume a cost corresponding to the distance between the node 302 and the center line of a lane, a cost corresponding to the distance between the node 302 and a moving object present around the vehicle, and a cost corresponding to a differential value between the speed of the vehicle 100 and a recommended speed set to the node 302.”),
detecting, based at least in part on the sensor data, the object blocking a driving lane associated with a portion of the graph (see at least Fig. 10 and [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”), or
associating, based at least in part on the sensor data, an additional action with the graph, the additional action instructing the vehicle to return to a previous state or to reduce velocity (see at least [0038]: “The group of sensors 1 includes a sensor that detects information related to the state of a moving object such as a vehicle or a pedestrian present around the vehicle, and a sensor that detects information related to the state of the vehicle. The group of sensors 1 includes a speed sensor 1a, a steering angle sensor 1b, an accelerator sensor 1c, a brake sensor 1d, an acceleration sensor 1e, an angular velocity sensor 1f, a global positioning system (GPS) device 1g, an external camera 1h, and an external sensor 1i.”; [0173]: “FIG. 10 is a diagram illustrating candidate estimated paths of the vehicle 100 and illustrating a plurality of candidate estimated paths generated from the current position of the vehicle 100 to an intermediate destination 300 by the estimated path setting unit 39. FIG. 10 illustrates, as candidate estimated paths 301, candidate estimated paths that follow a preceding vehicle 101 and candidate estimated paths 301 that lead to the intermediate destination 300 while avoiding vehicles 103 and 104 traveling on an adjacent lane 201.”; [0246]: “When having recognized that the vehicle 100 cannot overtake the preceding vehicle 101 from the value of the no-overtaking flag, the determination unit 38 sets an intermediate destination 300 at a position which is on the lane 200 that the vehicle 100 is traveling on and which allows the vehicle 100 to follow the preceding vehicle 101 without overtaking.”).
Claim Rejections - 35 USC § 103
9. Claims 21-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over Takabayashi et al. (US 20210163010, hereinafter Takabayashi) and Nister et al. (US 20230341234, hereinafter Nister) in view of Broadway et al. (US 20230358546, hereinafter Broadway).
Regarding claim 21, modified Takabayashi teaches the limitations of claim 1. Takabayashi fails to explicitly teach wherein the graph excludes the trajectory.
However, Broadway teaches a method and system for locating a plurality of mobile devices such as vehicle wherein a graph excludes a trajectory (see at least [0229]: “Removing (or reducing the confidence/weighting of) the original location, odometry or loop closure constraints in a part of the pose graph 313 is similar to removing the trajectories or parts of the trajectories linked to these constraints. Removing (or down-weighing) the new constraints after map matching is similar to ignoring or not attributing enough importance to the respective map features that led to these new constraints.”; [0235]: “Optionally, a trajectory in the pose graph 313 may be cut, and segments of it may be removed between iterations, if new and old constraints consistently contradict each other in a particular section of a trajectory. This may, for example, remove parts of trajectories 310 preventing the method 400 reaching convergence.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Broadway and provide a means to excludes a trajectory on a graph, with a reasonable expectation of success, in order to remove and cut a trajectory that does not attribute enough importance [0229].
Regarding claim 22, modified Takabayashi teaches the limitations of claim 14. Takabayashi fails to explicitly teach wherein the graph excludes the trajectory.
However, Broadway teaches a method and system for locating a plurality of mobile devices such as vehicle wherein a graph excludes a trajectory (see at least [0229]: “Removing (or reducing the confidence/weighting of) the original location, odometry or loop closure constraints in a part of the pose graph 313 is similar to removing the trajectories or parts of the trajectories linked to these constraints. Removing (or down-weighing) the new constraints after map matching is similar to ignoring or not attributing enough importance to the respective map features that led to these new constraints.”; [0235]: “Optionally, a trajectory in the pose graph 313 may be cut, and segments of it may be removed between iterations, if new and old constraints consistently contradict each other in a particular section of a trajectory. This may, for example, remove parts of trajectories 310 preventing the method 400 reaching convergence.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Takabayashi to incorporate the teachings of Broadway and provide a means to excludes a trajectory on a graph, with a reasonable expectation of success, in order to remove and cut a trajectory that does not attribute enough importance [0229].
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to TIEN MINH LE whose telephone number is (571)272-3903. The examiner can normally be reached Monday to Friday (8:30am-5:30pm eastern time).
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, Khoi Tran can be reached on (571)272-6919. 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.
/T.M.L./Examiner, Art Unit 3656
/KHOI H TRAN/Supervisory Patent Examiner, Art Unit 3656