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 Action on the Merits. Claims 1, 3-13, 15-18, and 20-23 are currently pending and are addressed below.
Response to Amendments
The amendment filed on June 13th, 2025 has been considered and entered. Accordingly, claims 1, 3, 7, 13, 15, and 18 have been amended. Claims 2, 14, and 19 have been cancelled. Claims 21-23 have been newly added
Response to Arguments
The applicant states (Amend. 7-9) that Lee (US 20160090087 A1) (“Lee”) in view of Singh (US 20240001926 A1) (“Singh”) fail to teach the limitations of amended independent claims 1, 13 and 18. The examiner respectfully disagrees. Singh teaches an S-V map used to determine lane change trajectories using points which indicate at which point a lane-change is made (See at least Singh FIG. 5 and Paragraph 59 “FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”), such that Singh discloses the amended limitations. Furthermore, the rejection of cancelled claim 2, which has been incorporated into claim 1 as the amended limitation, is rejected on the combination of the teachings of Lee in view of Singh.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 3-4, 7-8, 13, 15-16, 18, and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Lee (US 20160090087 A1) (“Lee”) in view of Singh (US 20240001926 A1) (“Singh”).
With respect to claim 1, Lee teaches a computer-implemented method for operating an autonomous driving vehicle (ADV), the method comprising:
perceiving a driving environment based on sensor data obtained from a plurality of sensors mounted on the ADV, including obtaining information of one or more obstacles on an adjacent lane (See at least Lee FIG. 7 and Paragraph 46 “The information collector 100 may obtain road information and driving information by receiving a sensing signal from a sensor 20 connected thereto. The road information may include geometric information about a road, e.g., lanes of the road, a width of the lanes, a form (curvature) of the road, etc. The driving information may include information about movement of the vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof.” | Paragraph 111 “Referring to FIG. 9, the cruise control system may obtain road information and driving information by receiving a sensing signal from a sensor (operation S11). The road information may include geometric information about a road, such as lanes of the road, a width of the lanes, a form (curvature, etc.) of the road, etc. The driving information may include information about movement of a vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof”); and
controlling the ADV to drive autonomously according to the trajectory to make the lane change to the adjacent lane and avoid the one or more obstacles (See at least Lee Paragraph 44 “Referring to FIG. 1, the cruise control system 10 a according to an exemplary embodiment may be a system that controls movement of a driving device or an automatic driving device (e.g., a vehicle, a robot, etc.), and may be installed in the driving device. The cruise control system 10 a may generate a lane change path for the driving device to move from a current lane to a target lane on a road along which the driving device is driven, in response to a lane change request or automatically.” | Paragraphs 118-121 “The cruise control system may determine degrees of risk of the second change paths, and select, as a lane change path, a second change path, the degree of risk of which is minimum among the second change paths (operation S27). A degree of risk is a value representing a probability that the driving device will collide with a moving object near the driving device when the driving device changes lanes while moving along the second change path … As described above, according to the above exemplary embodiments, a cruise control system and method are capable of providing a safe lane change path in which lane changing can be performed without invading lanes other than a current lane and a lane to be moved to on a road”).
Lee fails to explicitly disclose receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map.
Singh, however teaches receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV and generating a trajectory of the ADV using dynamic programming based on the S-V map (See at least Singh FIGS. 4-6 and Paragraphs 43-45 “The lane-change control system 400 can be activated or triggered by a lane-change request, e.g., user input such as activating a vehicle 150 turn signal, or a decision by a vehicle computer 302 to change lanes. As explained further below with respect to FIG. 11 , the L2C2 lane-change control system 400 typically remains active from the time the trigger is provided to a time at which the ego vehicle 150 process from a current lane 104 to a target lane 105, e.g., a time at which a center point of the vehicle 150 crosses a lane boundary … Perception block 415 represents vehicle sensors 304 provided via the vehicle network 312 to one or more vehicle computers 302 for vehicle 150 state data, data about target vehicles 151, etc., described further below. It will be understood that the perception block 415 can use various techniques to identify objects outside a vehicle 150 (e.g., target vehicles 151) and their locations. Accordingly, the perception block 415 provides localization data used by various ADAS features, including lane-centering provided by lateral control block 420, adaptive cruise control (ACC) provided via the longitudinal control block 425, as well as the lane-change control system 400.” | Paragraphs 58-59 “The L2C2 block 405 generates a set of longitudinal trajectories (i.e., specifying speeds and/or accelerations over the time specified for the lane-change) for the ego vehicle 150 with respect to each of the target vehicles in the target_vehicles list. Thus, when reference is made herein to a trajectory or trajectories generated by the black 405, reference is made to such longitudinal trajectories, i.e., to a specification of speeds and/or accelerations over time, and not to other elements that may be typically thought of as included in a directory, such as a heading or position on a path. FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”)and
determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change (See at least Singh FIG. 5 and Paragraph 59 “FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee to include receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map, as taught by Singh as disclosed above, in order to efficiently and accurately generate lane change trajectories (Singh Paragraph 16 “The lane-change control system may be referred to as a “longitudinal lateral coordinated control” (L2C2) system because it advantageously coordinates control of longitudinal velocities with lateral movement to improve trajectories of vehicles' automated lane-changes.”).
With respect to claim 3, and similarly claims 15 and 21, Lee in view of Singh teaches that the lane change includes a preparation phase in which the ADV drives straight within the current lane in a preparation operating mode and a lane change phase in which the ADV maneuvers towards the adjacent lane in a lane change operating mode (See at least Lee FIG. 2 and Paragraphs 62-68 “The first path generator 200 may calculate the moving distance D in the x-axis direction for changing lanes on the straight road R1, based on the driving speed of the vehicle. The first path generator 200 may determine the first lane changing end point IEP with an x-axis value corresponding to the moving distance D and the y-axis value corresponding to the lane width W as coordinates thereof, based on the first lane changing start point ISP as a reference point (a starting point) … ‘f(0)’ may denote a y-axis value of the vehicle 1 when lane changing starts. ‘f′(0)’ may denote a degree to which the vehicle 1 is inclined with respect to the x-axis when lane changing starts. ‘f″(0)’ may denote a variation in the degree to which the vehicle 1 is inclined with respect to the x-axis when lane changing starts. ‘f(k)’ may denote a y-axis value of the vehicle 1 when an x-axis value of the vehicle 1 on the first change path IC is ‘k’. That is, ‘f(k)’ denotes a lateral offset of the vehicle 1 from the current lane to the target lane. ‘f′(k)’ may denote a degree to which the vehicle 1 is inclined with respect to the x-axis when the x-axis value of the vehicle 1 on the first change path IC is ‘k’ … When coefficients calculated by Equations 4 to 7 are substituted in Equation 2, (x, f(x)) may be calculated in all sections in which ‘x’ is a value between 0 and D. As a result, the first change path IC may be calculated”).
With respect to claim 4, and similarly claim 22, Lee in view of Singh teaches that the trajectory includes a first portion in which the ADV drives straight on the current lane in the preparation phase and a second portion in which the ADV makes a lane change towards the adjacent lane in the lane change phase (See at least Lee FIG. 2 and Paragraphs 62-68 “The first path generator 200 may calculate the moving distance D in the x-axis direction for changing lanes on the straight road R1, based on the driving speed of the vehicle. The first path generator 200 may determine the first lane changing end point IEP with an x-axis value corresponding to the moving distance D and the y-axis value corresponding to the lane width W as coordinates thereof, based on the first lane changing start point ISP as a reference point (a starting point) … ‘f(0)’ may denote a y-axis value of the vehicle 1 when lane changing starts. ‘f′(0)’ may denote a degree to which the vehicle 1 is inclined with respect to the x-axis when lane changing starts. ‘f″(0)’ may denote a variation in the degree to which the vehicle 1 is inclined with respect to the x-axis when lane changing starts. ‘f(k)’ may denote a y-axis value of the vehicle 1 when an x-axis value of the vehicle 1 on the first change path IC is ‘k’. That is, ‘f(k)’ denotes a lateral offset of the vehicle 1 from the current lane to the target lane. ‘f′(k)’ may denote a degree to which the vehicle 1 is inclined with respect to the x-axis when the x-axis value of the vehicle 1 on the first change path IC is ‘k’ … When coefficients calculated by Equations 4 to 7 are substituted in Equation 2, (x, f(x)) may be calculated in all sections in which ‘x’ is a value between 0 and D. As a result, the first change path IC may be calculated”).
With respect to claim 7, and similarly claim 16, Lee in view of Singh teaches determining a lane change cost function based on the S-V map (See at least Lee FIGS. 7-8 and Paragraph 35 “FIGS. 7 and 8 are diagrams illustrating methods of determining a degree of risk by using a path selector of FIG. 4, according to exemplary embodiments” | Paragraphs 102-104 “FIG. 7 illustrates a state of an actual road at a moment a vehicle 1 passes through a point with coordinates (xr1(k), yr1(k)) to change lanes on the second change path RC2. FIG. 8 illustrates a state of an actual road at a moment a vehicle 1 passes through a point with coordinates (xr2(k), yr2(k)) to change lanes on the third change path RC3. Another moving object, e.g., a vehicle 2, may be also present on the actual road. The vehicle 2 is being driven along a lane adjacent to a current lane, and the vehicle 1 is performing lane changing from the current lane to an adjacent lane … The path selector 401 may determine a maximum value among degrees of risks ID2(k) at the moment, which are calculated between the vehicle 1 that changes lanes on the second change path RC2 and the vehicle 2 at predetermined time intervals, as a degree of risk TD2 of the second change path RC2 with respect to the vehicle 2, as shown in Equation 13 below”) (See at least Singh Paragraph 20 “The optimal trajectory can be selected from the candidate trajectories by performing a discrete search of the candidate trajectories for the candidate trajectory that optimizes a cost function” | Paragraph 29 “Trajectories having a duration larger than a predefined prediction horizon (e.g., 10-15 seconds), i.e., a predefined amount of time in a vehicle computer for which the vehicle computer is deemed capable of predicting events relevant to a lane-change, are rejected. Obtained admissible trajectories are stored. After storing admissible trajectories for all considered target vehicles, an optimal trajectory is found by minimizing a defined cost function. A first value of a longitudinal acceleration profile of the selected trajectory is then applied to the ego vehicle. When the final time of the selected optimal trajectory is equal to the required time for the vehicle to perform a lane-change, the lane-change control system commands a lane-change request”).
With respect to claim 8, Lee in view of Singh teaches that determining the lane change cost function based on the S-V map comprises determining a value of the lane change cost function based on a position of a corresponding point in the S-V map (See at least Lee FIGS. 7-8 and Paragraph 35 “FIGS. 7 and 8 are diagrams illustrating methods of determining a degree of risk by using a path selector of FIG. 4, according to exemplary embodiments” | Paragraphs 102-104 “FIG. 7 illustrates a state of an actual road at a moment a vehicle 1 passes through a point with coordinates (xr1(k), yr1(k)) to change lanes on the second change path RC2. FIG. 8 illustrates a state of an actual road at a moment a vehicle 1 passes through a point with coordinates (xr2(k), yr2(k)) to change lanes on the third change path RC3. Another moving object, e.g., a vehicle 2, may be also present on the actual road. The vehicle 2 is being driven along a lane adjacent to a current lane, and the vehicle 1 is performing lane changing from the current lane to an adjacent lane … The path selector 401 may determine a maximum value among degrees of risks ID2(k) at the moment, which are calculated between the vehicle 1 that changes lanes on the second change path RC2 and the vehicle 2 at predetermined time intervals, as a degree of risk TD2) (See at least Singh Paragraph 20 “The optimal trajectory can be selected from the candidate trajectories by performing a discrete search of the candidate trajectories for the candidate trajectory that optimizes a cost function” | Paragraph 29 “Trajectories having a duration larger than a predefined prediction horizon (e.g., 10-15 seconds), i.e., a predefined amount of time in a vehicle computer for which the vehicle computer is deemed capable of predicting events relevant to a lane-change, are rejected. Obtained admissible trajectories are stored. After storing admissible trajectories for all considered target vehicles, an optimal trajectory is found by minimizing a defined cost function. A first value of a longitudinal acceleration profile of the selected trajectory is then applied to the ego vehicle. When the final time of the selected optimal trajectory is equal to the required time for the vehicle to perform a lane-change, the lane-change control system commands a lane-change request”).
With respect to claim 13, Lee teaches a non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising:
perceiving a driving environment based on sensor data obtained from a plurality of sensors mounted on the ADV, including obtaining information of one or more obstacles on an adjacent lane (See at least Lee FIG. 7 and Paragraph 46 “The information collector 100 may obtain road information and driving information by receiving a sensing signal from a sensor 20 connected thereto. The road information may include geometric information about a road, e.g., lanes of the road, a width of the lanes, a form (curvature) of the road, etc. The driving information may include information about movement of the vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof.” | Paragraph 111 “Referring to FIG. 9, the cruise control system may obtain road information and driving information by receiving a sensing signal from a sensor (operation S11). The road information may include geometric information about a road, such as lanes of the road, a width of the lanes, a form (curvature, etc.) of the road, etc. The driving information may include information about movement of a vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof”);
controlling the ADV to drive autonomously according to the trajectory to make the lane change to the adjacent lane and avoid the one or more obstacles (See at least Lee Paragraph 44 “Referring to FIG. 1, the cruise control system 10 a according to an exemplary embodiment may be a system that controls movement of a driving device or an automatic driving device (e.g., a vehicle, a robot, etc.), and may be installed in the driving device. The cruise control system 10 a may generate a lane change path for the driving device to move from a current lane to a target lane on a road along which the driving device is driven, in response to a lane change request or automatically.” | Paragraphs 118-121 “The cruise control system may determine degrees of risk of the second change paths, and select, as a lane change path, a second change path, the degree of risk of which is minimum among the second change paths (operation S27). A degree of risk is a value representing a probability that the driving device will collide with a moving object near the driving device when the driving device changes lanes while moving along the second change path … As described above, according to the above exemplary embodiments, a cruise control system and method are capable of providing a safe lane change path in which lane changing can be performed without invading lanes other than a current lane and a lane to be moved to on a road”).
Lee fails to explicitly disclose receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map.
Singh, however teaches receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV and generating a trajectory of the ADV using dynamic programming based on the S-V map (See at least Singh FIGS. 4-6 and Paragraphs 43-45 “The lane-change control system 400 can be activated or triggered by a lane-change request, e.g., user input such as activating a vehicle 150 turn signal, or a decision by a vehicle computer 302 to change lanes. As explained further below with respect to FIG. 11 , the L2C2 lane-change control system 400 typically remains active from the time the trigger is provided to a time at which the ego vehicle 150 process from a current lane 104 to a target lane 105, e.g., a time at which a center point of the vehicle 150 crosses a lane boundary … Perception block 415 represents vehicle sensors 304 provided via the vehicle network 312 to one or more vehicle computers 302 for vehicle 150 state data, data about target vehicles 151, etc., described further below. It will be understood that the perception block 415 can use various techniques to identify objects outside a vehicle 150 (e.g., target vehicles 151) and their locations. Accordingly, the perception block 415 provides localization data used by various ADAS features, including lane-centering provided by lateral control block 420, adaptive cruise control (ACC) provided via the longitudinal control block 425, as well as the lane-change control system 400.” | Paragraphs 58-59 “The L2C2 block 405 generates a set of longitudinal trajectories (i.e., specifying speeds and/or accelerations over the time specified for the lane-change) for the ego vehicle 150 with respect to each of the target vehicles in the target_vehicles list. Thus, when reference is made herein to a trajectory or trajectories generated by the black 405, reference is made to such longitudinal trajectories, i.e., to a specification of speeds and/or accelerations over time, and not to other elements that may be typically thought of as included in a directory, such as a heading or position on a path. FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”)and
determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change (See at least Singh FIG. 5 and Paragraph 59 “FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee to include receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map, as taught by Singh as disclosed above, in order to efficiently and accurately generate lane change trajectories (Singh Paragraph 16 “The lane-change control system may be referred to as a “longitudinal lateral coordinated control” (L2C2) system because it advantageously coordinates control of longitudinal velocities with lateral movement to improve trajectories of vehicles' automated lane-changes.”).
With respect to claim 18, Lee teaches a data processing system, comprising: a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including:
perceiving a driving environment based on sensor data obtained from a plurality of sensors mounted on the ADV, including obtaining information of one or more obstacles on an adjacent lane (See at least Lee FIG. 7 and Paragraph 46 “The information collector 100 may obtain road information and driving information by receiving a sensing signal from a sensor 20 connected thereto. The road information may include geometric information about a road, e.g., lanes of the road, a width of the lanes, a form (curvature) of the road, etc. The driving information may include information about movement of the vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof.” | Paragraph 111 “Referring to FIG. 9, the cruise control system may obtain road information and driving information by receiving a sensing signal from a sensor (operation S11). The road information may include geometric information about a road, such as lanes of the road, a width of the lanes, a form (curvature, etc.) of the road, etc. The driving information may include information about movement of a vehicle, e.g., a location, a moving direction, driving speed, a steering angle, a yaw rate, and the like thereof”);
controlling the ADV to drive autonomously according to the trajectory to make the lane change to the adjacent lane and avoid the one or more obstacles (See at least Lee Paragraph 44 “Referring to FIG. 1, the cruise control system 10 a according to an exemplary embodiment may be a system that controls movement of a driving device or an automatic driving device (e.g., a vehicle, a robot, etc.), and may be installed in the driving device. The cruise control system 10 a may generate a lane change path for the driving device to move from a current lane to a target lane on a road along which the driving device is driven, in response to a lane change request or automatically.” | Paragraphs 118-121 “The cruise control system may determine degrees of risk of the second change paths, and select, as a lane change path, a second change path, the degree of risk of which is minimum among the second change paths (operation S27). A degree of risk is a value representing a probability that the driving device will collide with a moving object near the driving device when the driving device changes lanes while moving along the second change path … As described above, according to the above exemplary embodiments, a cruise control system and method are capable of providing a safe lane change path in which lane changing can be performed without invading lanes other than a current lane and a lane to be moved to on a road”).
Lee fails to explicitly disclose receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map.
Singh, however teaches receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV and generating a trajectory of the ADV using dynamic programming based on the S-V map (See at least Singh FIGS. 4-6 and Paragraphs 43-45 “The lane-change control system 400 can be activated or triggered by a lane-change request, e.g., user input such as activating a vehicle 150 turn signal, or a decision by a vehicle computer 302 to change lanes. As explained further below with respect to FIG. 11 , the L2C2 lane-change control system 400 typically remains active from the time the trigger is provided to a time at which the ego vehicle 150 process from a current lane 104 to a target lane 105, e.g., a time at which a center point of the vehicle 150 crosses a lane boundary … Perception block 415 represents vehicle sensors 304 provided via the vehicle network 312 to one or more vehicle computers 302 for vehicle 150 state data, data about target vehicles 151, etc., described further below. It will be understood that the perception block 415 can use various techniques to identify objects outside a vehicle 150 (e.g., target vehicles 151) and their locations. Accordingly, the perception block 415 provides localization data used by various ADAS features, including lane-centering provided by lateral control block 420, adaptive cruise control (ACC) provided via the longitudinal control block 425, as well as the lane-change control system 400.” | Paragraphs 58-59 “The L2C2 block 405 generates a set of longitudinal trajectories (i.e., specifying speeds and/or accelerations over the time specified for the lane-change) for the ego vehicle 150 with respect to each of the target vehicles in the target_vehicles list. Thus, when reference is made herein to a trajectory or trajectories generated by the black 405, reference is made to such longitudinal trajectories, i.e., to a specification of speeds and/or accelerations over time, and not to other elements that may be typically thought of as included in a directory, such as a heading or position on a path. FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”)and
determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change (See at least Singh FIG. 5 and Paragraph 59 “FIG. 5 illustrates a graph 500 including examples of different possible or candidate trajectories 505 that could be generated for a vehicle 150 in an s-v space (or domain) with respect to a target vehicle 151. s is the relative distance of the ego vehicle 150 to a target vehicle 151, and v is the relative speed of the ego vehicle 150 to the target vehicle 151. The considered target vehicle 151 is set at the origin of the s-v space as illustrated in FIG. 5 . To specify lane-change trajectories, initial values of s-v states (s0,v0) are known, i.e., as output from the perception block 415. Candidate lane-change trajectories are generated by specifying final values for a subset selected based on values of s, v, or time. A trajectory specification data structure can then be generated to specify these values, which can then be used to compute test trajectories as described further below. FIG. 6 illustrates an example grid in s-v space including test trajectories 505. Each of the (s,v) points 605 represents a possible vehicle 150 relative speed and distance with respect to the target vehicle 151.”),
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee to include receiving a request to make a lane change from a current lane on which the ADV is driving to the adjacent lane, generating an S-V map based on the information of the one or more obstacles, each point on the S-V map representing a state of the ADV including a distance and a speed of the ADV; determining one or more areas in the S-V map, each point in the one or more areas representing a feasible state for the ADV to make the lane change; and generating a trajectory of the ADV using dynamic programming based on the S-V map, as taught by Singh as disclosed above, in order to efficiently and accurately generate lane change trajectories (Singh Paragraph 16 “The lane-change control system may be referred to as a “longitudinal lateral coordinated control” (L2C2) system because it advantageously coordinates control of longitudinal velocities with lateral movement to improve trajectories of vehicles' automated lane-changes.”).
Claims 5-6, 9-12, 17, 20, and 23are rejected under 35 U.S.C. 103 as being unpatentable over Lee (US 20160090087 A1) (“Lee”) in view of Singh (US 20240001926 A1) (“Singh”) in view of Lee II (US 20150353082 A1) (“Lee II”).
With respect to claim 5, and similarly claim 23 Lee in view of Singh fails to explicitly disclose determining a transition point in the one or more areas in the S-V map for the ADV to switch from the preparation operating mode to the lane change operating mode based on a cost function.
Lee II teaches determining a transition point in the one or more areas in the S-V map for the ADV to switch from the preparation operating mode to the lane change operating mode based on a plurality of cost functions (See at least Lee II Paragraph 68 “If the vehicle 42 is traveling along the center line 48 and a lane change is commanded, that lane change is performed in the same manner as in the '789 patent. FIG. 4 is an illustration 72 of the roadway 44 similar to the illustration 60, where like elements are identified by the same reference number, and showing a lane change path 74 that is determined by the algorithm so that the vehicle 42 leaves the center line 48 in the lane 46 and travels into the adjacent lane 50, where it will then be centered in the lane 50 on lane path 76. According to the invention, the algorithm first determines how many segments are needed to complete the requested lane change maneuver, i.e., how far beyond the range of the camera 14 the lane change will be completed from the vehicle's current position. For example, depending on the speed of the vehicle 42, the curvature of the roadway 44, steering aggressiveness profiles, etc., the algorithm will determine how much time is required to make the lane change request, and how far from the current vehicle's position the lane change will be completed”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee in view of Singh to include determining a transition point in the one or more areas in the S-V map for the ADV to switch from the preparation operating mode to the lane change operating mode based on a plurality of cost functions, as taught by Lee II as disclosed above, in order to ensure that the vehicle travels on an optimal trajectory (Lee II Paragraph 2 “This invention relates generally to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle and, more particularly, to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle that uses roadway points from a map data base to determine a reference vehicle path and then inputs from various vehicle sensors to alter the reference path based on road curvature and detected obstacles.”).
With respect to claim 6, Lee in view of Singh fails to explicitly disclose keeping a state of the ADV within the one or more areas in the S-V map during the lane change phase.
Lee II, however, teaches keeping a state of the AVD within the one or more areas in the S-V map during the lane change phase (See at least Lee II FIG. 4 and Paragraph 84 “The algorithm generates multiple paths 174 around the object 172, where each candidate path ni* is evaluated to determine if it is the optimal path to avoid the object 172 while allowing the vehicle 134 to stay comfortably within the lane 124 and as close to reference path 136 as possible”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee in view of Singh to include keeping a state of the AVD within the one or more areas in the S-V map during the lane change phase, as taught by Lee II as disclosed above, in order to ensure that the vehicle travels on an optimal trajectory (Lee II Paragraph 2 “This invention relates generally to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle and, more particularly, to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle that uses roadway points from a map data base to determine a reference vehicle path and then inputs from various vehicle sensors to alter the reference path based on road curvature and detected obstacles.”).
With respect to claim 9, Lee in view of Singh teaches a cost function for points in one or more areas in the S-V map (See at least Lee Paragraphs 102-104) (See at least Singh Paragraph 20 “The optimal trajectory can be selected from the candidate trajectories by performing a discrete search of the candidate trajectories for the candidate trajectory that optimizes a cost function” | Paragraph 29 “Trajectories having a duration larger than a predefined prediction horizon (e.g., 10-15 seconds), i.e., a predefined amount of time in a vehicle computer for which the vehicle computer is deemed capable of predicting events relevant to a lane-change, are rejected. Obtained admissible trajectories are stored. After storing admissible trajectories for all considered target vehicles, an optimal trajectory is found by minimizing a defined cost function. A first value of a longitudinal acceleration profile of the selected trajectory is then applied to the ego vehicle. When the final time of the selected optimal trajectory is equal to the required time for the vehicle to perform a lane-change, the lane-change control system commands a lane-change request”)
Lee in view of Singh, however, fails to explicitly disclose that a value of the lane change cost function is infinite for a corresponding point outside the one or more areas in the S-V map.
Lee II teaches determining a lane change with points in the one or more areas in the S-V map (See at least Lee II FIG. 4 and Paragraph 84 “The algorithm generates multiple paths 174 around the object 172, where each candidate path ni* is evaluated to determine if it is the optimal path to avoid the object 172 while allowing the vehicle 134 to stay comfortably within the lane 124 and as close to reference path 136 as possible”).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the method of Lee in view of Singh to include determining a lane change with points in the one or more areas in the S-V map, as taught by Lee II as disclosed above, such that the cost function value would be infinite for corresponding points outside the one or more areas in the S-V map, in order to ensure that the vehicle travels on an optimal trajectory (Lee II Paragraph 2 “This invention relates generally to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle and, more particularly, to a system and method for providing vehicle path planning and generation for lane centering and/or lane changing in a semi-autonomous or autonomously driven vehicle that uses roadway points from a map data base to determine a reference vehicle path and then inputs from various vehicle sensors to alter the reference path based on road curvature and detected obstacles.”).
With respect to claim 10, and similarly claim 17, Lee in view of Singh teaches generating a plurality of trajectories of the ADV and selecting a trajectory from the plurality of trajectories using dynamic programming (See at least Lee Paragraphs 11-14 “The first path generator may calculate a plurality of moving distances that are proportional to the speed of the driving device, and determine, as a plurality of first lane changing end points, points spaced from the first lane changing start point by one of the plurality of moving distances in a first axis parallel to the straight road and spaced from the first lane changing start point by a distance proportional to the width of the lane in a second axis perpendicular to the first axis … The cruise control system may further include a path selector for determining a degree of risk of each of the plurality of second change paths … The degree of risk may be a value representing a probability that the driving device will collide with a moving object near the driving device while the driving device moves along the second change path”);
Lee in view of Singh, however fails to explicitly disclose using a plurality of cost functions including the lane change cost function.
Lee II teaches discloses selecting a trajectory from the plurality of trajectories using dynamic programming using a plurality of cost functions including the lane change cost function (See at least Lee II Paragraph 86 “As above, a cost function is employed to determine the optimal speed for the vehicle 134 for that maneuver as follows. In this process, the algorithm generates multiple candidate speed profiles ni* that avoid the object 176, and evaluates each candidate speed profile riT using the cost function in equation (72). More particularly, the algorithm reduces the speed of the vehicle 134 to be less than the calculated reference speed, whether it be from the extreme speed profile or the comfort speed profile as determined above, some predetermined amount, such as 1 mph, to determine the optimal speed that matches the desired speed profile and safely avoids the object 176. The algorithm finds the optimal speed profile that minimizes the cost function … and where ni* is the optimal node at station layer N, E(ni*,ni+1*) is the cost associated with the speed change connecting the optimal nodes ni* and ni+1*, N(ni*) is cost associated with the speed visited at the node ni*, Cacc and ωacc are the cost and weight, respectively, fo