DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Status of Claims
Claims 1-5, 7-13, and 15-18 are pending in this application.
No claims are presented as currently amended claims.
No claims are newly presented.
No claims are newly cancelled.
Claim Rejections - 35 USC § 103
The text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 1-3, 5, 8-11, 13, and 16-18 are rejected under 35 U.S.C. 103 as being unpatentable over Cui (US 20210107476 A1) in view of Ichikawa et al. (US 20160282879 A1) (the combination thereof referred to as combination Cui hereinafter). As regards the individual claims:
Regarding claim 1, Cui teaches a vehicle behavior prediction method, comprising:
acquiring a path that a target vehicle will travel at a current intersection; (Cui: ¶ 071; processor such as the a processor such as the detecting engine 125 and/or the determining engine 126 may detect that the [Examiner’s note: vehicle-mounted turn signal] turn light 1028 is illuminated or flashing and determine that the second vehicle 1020 will be making a 90-degree left turn. In response to determining that the second vehicle 1020 will be making a 90-degree left turn, the determining engine 126 may determine that it is safe for the vehicle 1010 to make a 90-degree left turn and the responding engine 1028 may cause the vehicle 1010 to, or initiate the vehicle 1010 to, make a left turn.) determining a target traffic light corresponding to the path; acquiring an indication status of the target traffic light; (Cui: ¶ 071; vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099)) determining a neighboring traffic light corresponding to the target traffic light and the indication status of the neighboring traffic light according to the target traffic light, (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction) . . . wherein the neighboring traffic light is a traffic light at the current intersection controlling traffic in a direction different from that of the target traffic light; (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction) acquiring a position of an obstacle vehicle; predicting each possible travel path of the obstacle vehicle at the current intersection according to the position of the obstacle vehicle, (Cui: ¶ 071; processor such as the a processor such as the detecting engine 125 and/or the determining engine 126 may detect that the [Examiner’s note: vehicle-mounted turn signal] turn light 1028 is illuminated or flashing and determine that the second vehicle 1020 will be making a 90-degree left turn. In response to determining that the second vehicle 1020 will be making a 90-degree left turn, the determining engine 126 may determine that it is safe for the vehicle 1010 to make a 90-degree left turn and the responding engine 1028 may cause the vehicle 1010 to, or initiate the vehicle 1010 to, make a left turn.) and determining a traffic light corresponding to each possible travel path, wherein the neighboring traffic light comprises a traffic light corresponding to each possible travel path; (Cui: ¶ 071; vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099) and determining a final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path, (Cui: ¶ 073: vehicle 1110 may determine or predict whether the vehicle 1110 would get stuck in one or more red lights as a result of waiting for the predicted waiting time. In some embodiments, the vehicle 1110 may predict the waiting time based on predicted trajectories or paths of one or more of the second vehicle 1120, the third vehicle) wherein the determining the final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path comprises: for each possible travel path, if the indication status of the traffic light corresponding to the possible travel path is a red light or a yellow light, updating the possible travel path to a lane before the traffic light; (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction, . . .)(Cui: ¶ 071; vehicle 1010 may detect and recognize one or more traffic lights 1096, 1097, 1098, and 1099, via one or more processors such as detecting engine)and determining a set including each possible travel path of the obstacle vehicle as the final possible travel path of the obstacle vehicle. (Cui: ¶ 073: vehicle 1110 may determine or predict whether the vehicle 1110 would get stuck in one or more red lights as a result of waiting for the predicted waiting time. In some embodiments, the vehicle 1110 may predict the waiting time based on predicted trajectories or paths of one or more of the second vehicle 1120, the third vehicle)
Cui does not explicitly teach: the indication status of the target traffic light and a traffic light status mapping relationship table; however, Ichikawa does teach:
the indication status of the target traffic light and a traffic light status mapping relationship table, (Ichikawa: ¶ 036; light 376 is “green” leads to an inference of the interlock rule “stop” associated with the lane link 366 and the traffic light 374 based on the interlocked state of the traffic light 374 as “red.”)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Ichikawa with the teachings of Cui because doing so would result in the predicable benefit of “improv[ing] the performance of the autonomous driving system.” (Ichikawa: ¶ 003).
Regarding claim 2, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Ichikawa further teaches:
determining a drivable path of each intersection according to a lane topology relationship in an electronic map; wherein the drivable path comprises an initial lane and a target lane; and determining, for each drivable path, a traffic light on the travel path from the initial lane to the target lane, and establishing a mapping relationship among the initial lane, the target lane and the traffic light. (Ichikawa: ¶ 004; detailed map format can include lane segments associated with branches of a traffic intersection and lane links that indicate the transition path between the lane segments across the traffic intersection. Each of the lane links can be associated with transition rules governing the action of the autonomous vehicle based on the state of detected traffic signals.)
Regarding claim 3, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Ichikawa further teaches:
wherein establishing of the traffic light status mapping relationship table comprises: for each intersection in an electronic map, (Ichikawa: ¶ 035; map format has been improved to include interlock rules.) obtaining the indication status of a single traffic light at the intersection, (Ichikawa: ¶ 034; traffic light 376 is directly detected by the autonomous vehicle) and the indication status of other traffic light at the intersection during the indication status of the single traffic light; and establishing a mapping relation among the single traffic light, the indication status of the single traffic light, the other traffic light and the indication status of the other traffic light, to obtain the traffic light status mapping relationship table. (Ichikawa: ¶ 036; state of the traffic lights 372, 374 can then be inferred to be “red,” . . . since the traffic lights 372, 374 are interlocked traffic signals)
Regarding claim 5, as detailed above, combination Cui teaches the invention as detailed with respect to claim 2. Ichikawa further teaches:
wherein each possible travel path is formed by at least two lanes in sequence from the initial lane to the target lane; (Ichikawa: ¶ 033; a transition rule “go” is highlighted as associated with the lane links 348, 350 and can direct the autonomous vehicle 200 to either proceed straight through the intersection from the lane segment 316 to the lane segment 324 or proceed in a right turn) and the determining the traffic light corresponding to each possible travel path comprises: determining the traffic light corresponding to every two consecutive lanes in each possible travel path, (Ichikawa: ¶ 029; Each of the traffic signals can be associated with at least one of the lane links 348, 350, 352, 354, 356, 357, 358, 360, 362, 364, 366, 368 and information associated with the traffic signals can include a geographical location, a traffic signal type, and a traffic signal state.) according to the mapping relationship among the initial lane, the target lane and the traffic light; (Ichikawa: ¶ 028; Each of the lane links 348, 350, 352, 354, 356, 357, 358, 360, 362, 364, 366, 368 can be associated with two of the lane segments 308, 310, 312, 314, 316, 318, 320, 322, 324, 326 and can extend between two of the branches 300, 302, 304, 306 of the traffic intersection.) and using the determined traffic light as the traffic light corresponding to each possible travel path. (Ichikawa: ¶ 035; map format has been improved to include interlock rules.)
Regarding claim 8, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Ichikawa further teaches:
wherein after updating the possible travel path to the lane before the traffic light, the method further comprises: predicting that a speed and an acceleration of the obstacle vehicle are both zero when the obstacle vehicle reaches a stop line corresponding to the traffic light. (Ichikawa: ¶ 043; stop line 466 can be linked to the end of the lanes associated with the lane segments 434, 436 and information associated with the stop line 466 can include a geographical location of a position where the vehicle 200 must stop)
Regarding claim 9, Ichikawa teaches a vehicle behavior prediction apparatus, comprising:
acquire a path that a target vehicle will travel at a current intersection (Cui: ¶ 071; processor such as the a processor such as the detecting engine 125 and/or the determining engine 126 may detect that the [Examiner’s note: vehicle-mounted turn signal] turn light 1028 is illuminated or flashing and determine that the second vehicle 1020 will be making a 90-degree left turn. In response to determining that the second vehicle 1020 will be making a 90-degree left turn, the determining engine 126 may determine that it is safe for the vehicle 1010 to make a 90-degree left turn and the responding engine 1028 may cause the vehicle 1010 to, or initiate the vehicle 1010 to, make a left turn.)and determine a target traffic light corresponding to the path;(Cui: ¶ 071; vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099)) acquire an indication status of the target traffic light, and determine a neighboring traffic light corresponding to the target traffic light and the indication status of the neighboring traffic light (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction) . . . wherein the neighboring traffic light is a traffic light at the current intersection controlling traffic in a direction different from that of the target traffic light;; (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction) acquire a position of an obstacle vehicle, predict each possible travel path of the obstacle vehicle at the current intersection according to the position of the obstacle vehicle (Cui: ¶ 071; processor such as the a processor such as the detecting engine 125 and/or the determining engine 126 may detect that the [Examiner’s note: vehicle-mounted turn signal] turn light 1028 is illuminated or flashing and determine that the second vehicle 1020 will be making a 90-degree left turn. In response to determining that the second vehicle 1020 will be making a 90-degree left turn, the determining engine 126 may determine that it is safe for the vehicle 1010 to make a 90-degree left turn and the responding engine 1028 may cause the vehicle 1010 to, or initiate the vehicle 1010 to, make a left turn.)and determine a traffic light corresponding to each possible travel path, wherein the neighboring traffic light comprises the traffic light corresponding to each possible travel path; and (Cui: ¶ 071; vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099) determine a final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path, (Cui: ¶ 073: vehicle 1110 may determine or predict whether the vehicle 1110 would get stuck in one or more red lights as a result of waiting for the predicted waiting time. In some embodiments, the vehicle 1110 may predict the waiting time based on predicted trajectories or paths of one or more of the second vehicle 1120, the third vehicle) wherein the vehicle behavior prediction apparatus is further caused to: for each possible travel path, if the indication status of the traffic light corresponding to the possible travel path is a red light or a yellow light, update the possible travel path to a lane before the traffic light; (Cui ; ¶ 071; When the vehicle 1010 approaches an intersection 1089, the vehicle 1010 may detect and recognize one or more traffic lights . . . vehicle 1010 may determine whether or not, and/or when, to make a 90-degree turn at an intersection 1089 at least based on a signal of the one or more traffic lights 1096, 1097, 1098, and 1099, for example, whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction, . . .)(Cui: ¶ 071; vehicle 1010 may detect and recognize one or more traffic lights 1096, 1097, 1098, and 1099, via one or more processors such as detecting engine)and determine a set including each possible travel path of the obstacle vehicle as the final possible travel path of the obstacle vehicle. (Cui: ¶ 073: vehicle 1110 may determine or predict whether the vehicle 1110 would get stuck in one or more red lights as a result of waiting for the predicted waiting time. In some embodiments, the vehicle 1110 may predict the waiting time based on predicted trajectories or paths of one or more of the second vehicle 1120, the third vehicle)
Cui does not explicitly teach: according to the target traffic light, the indication status of the target traffic light and a traffic light status mapping relationship table; however, Ichikawa does teach:
according to the target traffic light, the indication status of the target traffic light and a traffic light status mapping relationship table, (Ichikawa: ¶ 036; light 376 is “green” leads to an inference of the interlock rule “stop” associated with the lane link 366 and the traffic light 374 based on the interlocked state of the traffic light 374 as “red.”"
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Ichikawa with the teachings of Cui because doing so would result in the predicable benefit of “improv[ing] the performance of the autonomous driving system.” (Ichikawa: ¶ 003).
Regarding claim 10, as detailed above, combination Cui teaches the invention as detailed with respect to claim 9. Ichikawa further teaches:
determine a drivable path of each intersection according to a lane topology relationship in an electronic map; wherein the drivable path comprises an initial lane and a target lane; and determine, for each drivable path, a traffic light on the travel path from the initial lane to the target lane, and establish a mapping relationship among the initial lane, the target lane and the traffic light. (Ichikawa: ¶ 004; detailed map format can include lane segments associated with branches of a traffic intersection and lane links that indicate the transition path between the lane segments across the traffic intersection. Each of the lane links can be associated with transition rules governing the action of the autonomous vehicle based on the state of detected traffic signals.)
Regarding claim 11, as detailed above, combination Cui teaches the invention as detailed with respect to claim 9. Ichikawa further teaches:
wherein the vehicle behavior prediction apparatus is further caused to: for each intersection in an electronic map, (Ichikawa: ¶ 035; map format has been improved to include interlock rules.) obtain the indication status of a single traffic light at the intersection, (Ichikawa: ¶ 034; traffic light 376 is directly detected by the autonomous vehicle) and the indication status of other traffic light at the intersection during the indication status of the single traffic light; and establish a mapping relation among the single traffic light, the indication status of the single traffic light, the other traffic light and the indication status of the other traffic light, to obtain the traffic light status mapping relationship table. (Ichikawa: ¶ 036; state of the traffic lights 372, 374 can then be inferred to be “red,” . . . since the traffic lights 372, 374 are interlocked traffic signals)
Regarding claim 13, as detailed above, combination Cui teaches the invention as detailed with respect to claim 10. Ichikawa further teaches:
wherein each possible travel path is formed by at least two lanes in sequence from the initial lane to the target lane; (Ichikawa: ¶ 033; a transition rule “go” is highlighted as associated with the lane links 348, 350 and can direct the autonomous vehicle 200 to either proceed straight through the intersection from the lane segment 316 to the lane segment 324 or proceed in a right turn) and wherein the vehicle behavior prediction apparatus is further caused to determine the traffic light corresponding to each possible travel path by: determining the traffic light corresponding to every two consecutive lanes in each possible travel path, (Ichikawa: ¶ 029; Each of the traffic signals can be associated with at least one of the lane links 348, 350, 352, 354, 356, 357, 358, 360, 362, 364, 366, 368 and information associated with the traffic signals can include a geographical location, a traffic signal type, and a traffic signal state.) according to the mapping relationship among the initial lane, the target lane and the traffic light; (Ichikawa: ¶ 028; Each of the lane links 348, 350, 352, 354, 356, 357, 358, 360, 362, 364, 366, 368 can be associated with two of the lane segments 308, 310, 312, 314, 316, 318, 320, 322, 324, 326 and can extend between two of the branches 300, 302, 304, 306 of the traffic intersection.) and using the determined traffic light as the traffic light corresponding to each possible travel path. (Ichikawa: ¶ 035; map format has been improved to include interlock rules.)
Regarding claim 16, as detailed above, combination Cui teaches the invention as detailed with respect to claim 9. Ichikawa further teaches:
wherein the vehicle behavior prediction apparatus is further caused to: predict that a speed and an acceleration of the obstacle vehicle are both zero when the obstacle vehicle reaches a stop line corresponding to the traffic light. (Ichikawa: ¶ 043; stop line 466 can be linked to the end of the lanes associated with the lane segments 434, 436 and information associated with the stop line 466 can include a geographical location of a position where the vehicle 200 must stop)
Regarding claim 17, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Ichikawa further teaches:
a processor; and a memory, configured to store instructions executable by the processor, wherein the processor is configured to implement the method according to claim1 by executing the instructions. (Ichikawa: ¶ 019; memory 104 can also include an operating system 110 and installed applications 112, the installed applications 112 including programs that permit the CPU 102 to perform automated driving methods)
Regarding claim 18, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Ichikawa further teaches:
a non-transitory storage medium having a computer program stored thereon, which when being executed by a processor, implements the method according to claim1. (Ichikawa: ¶ 019; memory 104 can also include an operating system 110 and installed applications 112, the installed applications 112 including programs that permit the CPU 102 to perform automated driving methods)
Claims 4 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over combination Cui as applied to claims 2 and 10 respectively above, and further in view of Ota (US 20140046581 A1).
Regarding claim 4, as detailed above, combination Cui teaches the invention as detailed with respect to claim 2. Cui does not explicitly teach:
wherein the predicting each possible travel path of the obstacle vehicle at the current intersection according to the position of the obstacle vehicle comprises: determining a lane in which the obstacle vehicle is located according to the position; and predicting each possible travel path of the obstacle vehicle at the current intersection according to the lane in which the obstacle vehicle is located and the lane topology relationship; however, Ota does teach:
wherein the predicting each possible travel path of the obstacle vehicle at the current intersection according to the position of the obstacle vehicle comprises: determining a lane in which the obstacle vehicle is located according to the position; (Ota: ¶ 089; estimated that the number of stopping vehicles on the first traffic lane is one, that the number of stopping vehicles on the second traffic lane is zero, and that the number of stopping vehicles on the third traffic lane is zero.) and predicting each possible travel path of the obstacle vehicle at the current intersection according to the lane in which the obstacle vehicle is located and the lane topology relationship. (Ota: ¶ 085; it is possible to determine whether the different vehicles are to pass by or stop at the traffic light according to the traveling direction (straight ahead, turn right, or turn left) considering the estimated driving routes of the different vehicles, right and left-turn signal)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Ota with the teachings of Cui because doing so would result in the predicable benefit of “provid[ing] a drive assistance device capable of estimating a passable time zone taking different vehicles presenting around the own vehicle into account.” (Ota: ¶ 011).
Regarding claim 12, as detailed above, combination Cui teaches the invention as detailed with respect to claim 10. Cui does not explicitly teach:
wherein the vehicle behavior prediction apparatus is further caused obtain the position of the obstacle vehicle, determine a lane in which the obstacle vehicle is located according to the position; and predict each possible travel path of the obstacle vehicle at the current intersection according to the lane in which the obstacle vehicle is located and the lane topology relationship; however, Ota does teach:
wherein the vehicle behavior prediction apparatus is further caused obtain the position of the obstacle vehicle, determine a lane in which the obstacle vehicle is located according to the position; (Ota: ¶ 089; estimated that the number of stopping vehicles on the first traffic lane is one, that the number of stopping vehicles on the second traffic lane is zero, and that the number of stopping vehicles on the third traffic lane is zero.) and predict each possible travel path of the obstacle vehicle at the current intersection according to the lane in which the obstacle vehicle is located and the lane topology relationship. (Ota: ¶ 085; it is possible to determine whether the different vehicles are to pass by or stop at the traffic light according to the traveling direction (straight ahead, turn right, or turn left) considering the estimated driving routes of the different vehicles, right and left-turn signal)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Ota with the teachings of Cui because doing so would result in the predicable benefit of “provid[ing] a drive assistance device capable of estimating a passable time zone taking different vehicles presenting around the own vehicle into account.” (Ota: ¶ 011).
Claims 7 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over combination Cui as applied to claims 1 and 9 respectively above, and further in view of Ratnasingam (US 9672734 B1).
Regarding claim 7, as detailed above, combination Cui teaches the invention as detailed with respect to claim 1. Cui does not explicitly teach:
wherein the updating the possible travel path to the lane before the traffic light comprises: obtaining a coordinate sequence comprising coordinate of each lane in the lane before the traffic light; removing coordinates located behind the obstacle vehicle in the coordinate sequence according to the position of the obstacle vehicle, to obtain a processed coordinate sequence; and determining a path formed by the processed coordinate sequence as the possible travel path of the obstacle vehicle; however, Ratnasingam does teach:
wherein the updating the possible travel path to the lane before the traffic light comprises: obtaining a coordinate sequence comprising coordinate of each lane in the lane before the traffic light; removing coordinates located behind the obstacle vehicle in the coordinate sequence according to the position of the obstacle vehicle, to obtain a processed coordinate sequence; and determining a path formed by the processed coordinate sequence as the possible travel path of the obstacle vehicle; (Ratnasingam: ¶ 191; Cols. 43, Lns. 13-15; system may store a set of coordinate points obtained at an appropriate distance interval) and determining a path formed by the processed coordinate sequence as the possible travel path of the obstacle vehicle. (Ratnasingam: ¶ 191; Cols. 43, Lns. 34-36; system may create a mathematical model such as Kalman filter, particle filter or neural network model to approximately describe the movement of a vehicle to determine the current road segment.).
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Cui with the teachings of Ratnasingam with a reasonable expectation of success because the use of a known technique to improve similar methods in the same way is obvious (KSR Int'l Co. v. Teleflex Inc., 550 U.S. at 417, 82 USPQ2d at 1396.) In the instant case, both Cui and Ratnasingam's base methods are similar methods for predicting other-vehicle behavior at an intersection; however, the combined device would further filter the path of vehicles to reduce path-prediction errors which would give the self-vehicle better information to reduce the risk of collision.
Regarding claim 15, as detailed above, combination Cui teaches the invention as detailed with respect to claim 9. Cui does not explicitly teach: :
wherein the vehicle behavior prediction apparatus is further caused to update the possible travel path to the lane before the traffic light by: obtaining a coordinate sequence comprising coordinate of each lane in the lane before the traffic light; removing coordinates located behind the obstacle vehicle in the coordinate sequence according to the position of the obstacle vehicle, to obtain a processed coordinate sequence; and determining a path formed by the processed coordinate sequence as the possible travel path of the obstacle vehicle. ; however, Ratnasingam does teach:
wherein the vehicle behavior prediction apparatus is further caused to update the possible travel path to the lane before the traffic light by: obtaining a coordinate sequence of the lane before the traffic light; removing coordinates located behind the obstacle vehicle in the coordinate sequence according to the position of the obstacle vehicle, to obtain a processed coordinate sequence; (Ratnasingam: ¶ 191; Cols. 43, Lns. 13-15; system may store a set of coordinate points obtained at an appropriate distance interval) and determining a path formed by the processed coordinate sequence as the possible travel path of the obstacle vehicle. (Ratnasingam: ¶ 191; Cols. 43, Lns. 34-36; system may create a mathematical model such as Kalman filter, particle filter or neural network model to approximately describe the movement of a vehicle to determine the current road segment.)
Before the effective filling date of the claimed invention, it would have been obvious to one of ordinary skill in the art to combine the teachings of Cui with the teachings of Ratnasingam with a reasonable expectation of success because the use of a known technique to improve similar methods in the same way is obvious (KSR Int'l Co. v. Teleflex Inc., 550 U.S. at 417, 82 USPQ2d at 1396.) In the instant case, both Cui and Ratnasingam's base methods are similar methods for predicting other-vehicle behavior at an intersection; however, the combined device would further filter the path of vehicles to reduce path-prediction errors which would give the self-vehicle better information to reduce the risk of collision.
Response to Arguments
Applicant's remarks filed November 28, 2025 have been fully considered but are not persuasive. Applicant argues that:
Cui at least fails to disclose the following claimed features: "determining a neighboring traffic light corresponding to the target traffic light and the indication status of the neighboring traffic light according to the target traffic light, the indication status of the target traffic light and a traffic light status mapping relationship table, wherein the neighboring traffic light is a traffic light at the current intersection controlling traffic in a direction different from that of the target traffic light;" ---- according to Cui, it determines the status of all the traffic lights of the lights 1096-1099 using one or more sensors; "predicting each possible travel path of the obstacle vehicle at the current intersection according to the position of the obstacle vehicle, and determining a traffic light corresponding to each possible travel path, wherein the neighboring traffic light comprises a traffic light corresponding to each possible travel path; and"---- according to Cui, it discloses determining the trajectory of oncoming vehicles based on information such as the turning signal and driving status obtained through vehicle sensors, while nowhere does it teach or suggest "predicting each possible travel path of the obstacle vehicle", or determining "traffic light corresponding to each possible travel path"; "determining a final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path" (Applicant’s Arguments filed Nov. 28, 2025, pgs. 10-11).
Previously applied art Cui (US 20210107476 A1 teaches a system wherein the ego vehicle continuously considers all possible paths of the other vehicles in an ongoing loop where new information is integrated into the predictions and where traffic signal status is information to be considered.
First, Cui teaches predicting the paths of all other vehicles for straight, turning, and stopping. In particular Cui’s paragraphs ¶ 071-073 (emphasis added), teach that “processors of the vehicle 1010 may further predict trajectories or paths of one or more of the second vehicle 1020 and the third vehicle,” indicating considering the paths of other vehicles. These predictions are informed by the physical actions of the other vehicles are considered such a “turning angle or radius.” Cui also teaches considering “whether the one or more traffic lights 1096, 1097, 1098, and 1099 are green, a distance from the intersection 1089 of one or more of the vehicles 1020, 1040, 1050, and 1060 travelling in an opposite direction . . ..” Figure 10(A) shows that the traffic lights being considered are not just the traffic light that applies to the ego vehicle, but other lights that apply to the other vehicles. In other words, Cui teaches a system where the ego vehicle is constantly evaluating the predicted path of each of the second, third, and other vehicles because Cui teaches updating a prediction based on new information that a left turn did not occur (Cui: ¶ 071; if the second vehicle 1020 and/or the third vehicle 1040 does not actually make a left turn [despite previous ego predictions] the second vehicle 1020 and/or the third vehicle 1040 may change intended paths from a left turn to going straight” thus updating its predictions in real time. Finally, in addition to predicting and considering left turn and straight ahead, Cui “predict[s] the waiting time based on predicted trajectories or paths of one or more of the second vehicle.” Consequently, Cui does teach considering all (straight, stopped, turning) paths of all other vehicles in real time based on a physical observations and traffic signals in a continuously updated manner and therefore Cui does teach does or suggest "predicting each possible travel path of the obstacle vehicle.”
PNG
media_image1.png
448
574
media_image1.png
Greyscale
Second, Cui teaches considering lane-specific traffic signal information. Cui teaches at ¶ 067 (emphasis added) “vehicle 910 may determine whether to allow the second vehicle 920 to merge into the lane 980 based on another source such as a traffic light signal 992[; f]or example, if allowing the second vehicle 920 to merge into the lane 980 would be predicted to result in the vehicle 910 being caught or stuck at a red light.” Here, Cui is predicting the future path of the other vehicle based upon the traffic signal conditions, e.g. a red light would cause the vehicle to be caught at the light. This requires considering both the path of another vehicle and its interaction with the signal deemed appropriate for the lane. Cui further teaches in ¶ 073 “vehicle 1110 may determine whether or not to change lanes in order to pass a stationary vehicle such as the second vehicle 1120 based on a status of one or more upcoming traffic lights such as traffic lights 1196-1199, such as, whether the traffic lights 1196-1199 are currently green, and how much longer they will remain green or red for.” Here again, the ego vehicle [1110] is determining if the stopped vehicle [1120] is stopped because (1) the appropriate lane-matching traffic light [1196] is red and thus requires it to stop or (2) if vehicle [1120] is stopped waiting for traffic to clear. The ego vehicle [1110] will pass the other vehicle [1120] in a case where the signal [1196] is green because it reduces travel time (case 2) but does not pass when the signal [1196] is red (case 1) because that would result in an ‘extra’ lane change that does not reduce travel time. Therefore, Cui does teach does or suggest determining "traffic light corresponding to each possible travel path.”
PNG
media_image2.png
452
574
media_image2.png
Greyscale
Because the ego vehicle [1110] is predicting the path of the other vehicle [1120] (final possible travel path of three possible paths: waiting for the light, turning left, or going straight) based upon the state of the traffic light [1196] (stopped for red or waiting for clear travel under green) as part of a determining if the self-vehicle should take a path (change lanes to clear the intersection), Cui does teach does or suggest "determining a final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path.”
Consequently, Cui alone, or in combination with applied prior art Ichikawa et al. (US 20160282879 A1), teaches or suggests "predicting each possible travel path of the obstacle vehicle", or determining "traffic light corresponding to each possible travel path"; "determining a final possible travel path of the obstacle vehicle according to each possible travel path and the indication status of the traffic light corresponding to each possible travel path"
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure Ji et al (US 20190259282 A1) which discloses a method of predicting acceleration or deceleration of another vehicle based on the state of a traffic light, and determines the risk of collision based on the predicted acceleration or deceleration of the another vehicle.
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 nonprovisional extension fee (37 CFR 1.17(a)) 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 CHARLES PALL whose telephone number is (571)272-5280. The examiner can normally be reached M-F 9:30 - 18:30.
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, Angela Ortiz can be reached at 571-272-1206. 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.
/C.P./Examiner, Art Unit 3663
/ANGELA Y ORTIZ/Supervisory Patent Examiner, Art Unit 3663