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 .
Priority
The present application’s claim to priority over Provisional U.S. Application No. 63/236,541, filing date 08/24/2021, is acknowledged.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 01/06/2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments
Applicant’s arguments, see Pgs. 7-10, filed 02/25/2026, with respect to the 35 USC 103 rejection of independent claims 1, 13, and 21 and their respective dependent claims have been fully considered and are partially persuasive.
Applicant argues that Kim, Eagelberg, He, Seccamonte, and Oguri fail to teach or suggest “wherein the estimated spacing profile is based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent;” The Examiner is in agreement with Applicant’s arguments with respect to Oguri, though respectfully disagrees that Kim, Eagelberg, He, and Seccamonte fail to teach or suggest the above-recited features. Upon further consideration Kim, Eagelberg, He, Seccamonte, and Oguri, and in view of the modified scope of the claims, the Examiner respectfully asserts that Kim teaches “wherein the estimated spacing profile is based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent;” in at least [0110] and [0113], which disclose the prediction of occurrence of an overlap of the subject vehicle 14 and another vehicle 22 and subsequently adjusting an estimated spacing profile based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent. In particular, [0113] teaches that “the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed.” In other words, the estimated spacing profile is determined based on how well the current overlap information and the predictive overlap information match (i.e., whether predictive and actual values are different).
Accordingly, the 35 USC 103 rejection of independent claims 1, 13, and 21 and their respective dependent claims has been withdrawn. Upon further search and consideration in view of the modified scope of the claims, a new ground(s) of rejection is made over Kim, Eagelberg and He.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-9, 11-21, and 23 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
The term “how well observed behavior... has matched…” in claim 1 is a relative term which renders the claim indefinite. The term “how well” or “well… matched” is not defined by the claim, the specification does not provide a standard for ascertaining the requisite degree, and one of ordinary skill in the art would not be reasonably apprised of the scope of the invention. In particular, the term “how well” renders the claim indefinite because it is unclear at which the observed behavior and previously predicted behavior may be considered to be well matched. Referring to [0016] and [0047] of the written description, it is disclosed that “In some implementations, the spacing profile further includes a predictability score for the road agent, which may be based on how much behavior to-date has matched previously predicted behavior and/or predictability of environmental factors.” Here, “how much” differs in scope from the claimed “how well”, as “how well” could reasonably encompass quality of matching rather than quantity of matching (i.e., “how much”). Therefore, the term “how well” amounts to a subjective term and the specification fails to provide an objective standard for measuring the scope of the term.
Claims 2-9 and 11-12 are dependent upon claim 1 and therefore inherit the above-described deficiencies. Accordingly, claims 2-9 and 11-12 are rejected under similar reasoning as claim 1 above.
Independent claims 13 and 21 include language substantially similar to that discussed above with respect to claim 1, and are likewise rendered indefinite due to use of the subjective term “how well”. Accordingly, independent claims 13 and 21 are rejected under similar reasoning as claim 1 above.
Claims 14-20 are dependent upon claim 13 and therefore inherit the above-described deficiencies. Accordingly, claims 14-20 are rejected under similar reasoning as claim 13 above.
Claim 23 is dependent upon claim 21 and therefore inherits the above-described deficiencies. Accordingly, claim 23 is rejected under similar reasoning as claim 21 above.
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.
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.
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.
Claim(s) 1-3, 5-6, 11-15, 17-18, and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim (US 2020/0108825 A1) in view of Eagelberg et al. (US 2018/0120859 A1), hereinafter Eagelberg, and in further view of He et al. (US 2019/0263399 A1), hereinafter He.
Regarding claim 1, Kim teaches a system, comprising:
a perception system;
Kim teaches ([0041]): "Referring to FIG. 1, the collision avoidance apparatus 100 according to the present disclosure includes: a first detector 110 configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector 120 configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle;"
and one or more processors configured to:
Kim teaches ([0071]): "A controller may control an overall operation of the collision avoidance apparatus 100. According to an embodiment, the controller may be implemented by an ECU. The controller may receive, from a processor, a result of processing of image data. The controller may be configured to control steering avoidance of a subject vehicle at least in part based on the processing of image data. According to an embodiment, the controller may include the calculator 130 and the control unit 140."
receive sensor data from the perception system,
Kim teaches ([0072]): "The calculator 130 may receive detected information from the first detector 110 and the second detector 120. The calculator 130 may determine whether steering avoidance is executable, on the basis of the another vehicle information, subject vehicle information, and distance information."
the sensor data identifying one or more behaviors of a road agent in an environment of an autonomous vehicle;
Kim teaches ([0041]): "Referring to FIG. 1, the collision avoidance apparatus 100 according to the present disclosure includes: a first detector 110 configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector 120 configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle;" Kim further teaches ([0042]): "According to an embodiment, the first detector 110 may include: an image sensor to be disposed at a vehicle so as to have a field of view exterior of the vehicle..." Kim even further teaches ([0043]): "The image sensor may be disposed at an autonomous driving vehicle so as to have a field of view exterior of the autonomous driving vehicle."
estimate a spacing profile of the road agent…
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included below, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
PNG
media_image1.png
644
890
media_image1.png
Greyscale
the estimated spacing profile including a road agent preference for the lateral gap,
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included above, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed." Here, the estimated spacing profile includes a preference for the lateral gap with respect to the road agent (i.e., the another vehicle); therefore, the estimated spacing profile is considered to include a road agent preference for the lateral gap.
wherein the estimated spacing profile is based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent;
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, while Kim does teach estimating a spacing profile including preference for a lateral gap (see at least [0110]-[0113])) and sensor data identifying detected characteristics of a road agent, road agent behavior, and one or more other road agents (see at least [0041], FIG. 5, and [0108]-[0112]), Kim does not outright teach determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Eagelberg teaches systems and methods for navigating lane merges and lane splits, comprising:
determine an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent;
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113]))
estimate a spacing profile of the road agent based on changes to the lateral gap over time,
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... If, however, target vehicle 802 is moving such that its trajectory is intersecting lane mark 1004C at an angle (e.g., a small angle less than 90 degrees), then target vehicle 802 is likely moving over quickly and will merge close to host vehicle 200. The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113])). In other words, the estimated spacing profile of the road agent includes the lateral distance monitoring of Kim and the maintenance of a safe distance from the target vehicle of Eagelberg.
send control instructions to control one or more operational systems of the autonomous vehicle based on the estimated spacing profile.
Eagelberg teaches ([0192]): "The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration." Eagelberg further teaches ([0189]): "Returning to FIG. 9, at step 914, processing unit 110 may determine a navigational action for the host vehicle based on the determined lane mark type and the determined characteristic of the target vehicle. The navigational action may include changing or maintaining one or more of steering, braking, or acceleration/deceleration of the host vehicle. In some embodiments, the navigational action may be carried out using one or more of the throttling system 220, braking system 230, steering system 240, velocity and acceleration module 406, and navigational response module 408 described above in connection with FIGS. 2F and 4."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim to incorporate the teachings of Eagelberg to provide determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Kim and Eagelberg are each directed towards similar pursuits in the field of autonomous vehicle control, with both in particular being concerned with lane cut-ins and lane changes, and the estimation of spacing profiles (see at least [0110]-[0113] of Kim). Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so advantageously improves safety by allowing for the maintenance of a safe distance between the host autonomous vehicle and another vehicle cutting in to the host vehicle's lane ahead of the host vehicle, or if appropriate, facilitating a safe merge with the another vehicle (i.e., the road agent), as recognized by Eagelberg (see at least [0191]-[0192]).
However, neither Kim nor Eagelberg outright teach that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. He teaches an intelligent vehicle safety driving envelope reconstruction method, comprising:
wherein the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent,
He teaches ([0037]): "As shown in FIG. 2, when considering only the current position of forward vehicle ②, the lateral distance Cy,j(t) between intelligent vehicle ① and forward vehicle ② is shown as in FIG. 2 (a). When considering that forward vehicle ② has left-turn driving behavior, the lateral distance C′y,j(t) between intelligent vehicle ① and forward vehicle ② is shown as FIG. 2 (b). Comparing FIG. 2 (a) and FIG. 2 (b), we can see that the lateral spacing between the intelligent vehicle ① and the forward vehicle ② gets smaller. Based on the prediction result, lateral safety distance is reconstructed to achieve new lateral secure model C′y,j(t)=ωyCy,j(t), where ωy is lateral correction factor; represents the variations in scale of lateral distance, and its value depend on the predicted maximum likelihood probability of the left-turning driving behavior of the forward vehicle driving behavior prediction model." One of ordinary skill in the art would recognize that modifying the value of the lateral correction factor would result in reducing or increasing the autonomous vehicle preference for the lateral gap (i.e., the lateral safety distance).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim and Eagelberg to incorporate the teachings of He to provide that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. Kim, Eagelberg, and He are each directed towards similar pursuits in the field of autonomous vehicle control and monitoring of road agent behavior. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of He, as doing so beneficially improves the safety and stability of the autonomous vehicle due to the adjustment of the autonomous vehicle preference for the lateral gap, as recognized by He (see at least [0034]-[0036]).
Regarding claim 2, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on when the road agent is predicted to interact with the autonomous vehicle.
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
Regarding claim 3, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent,
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a lateral gap requirement for the autonomous vehicle in relation to the road agent.
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed.
Regarding claim 5, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on an existing lateral gap between the autonomous vehicle and the road agent.
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information." FIG. 2, included above, demonstrates that the initiation of the analysis is based on an existing lateral gap (i.e., "Current Lateral distance") between the autonomous vehicle and the road agent.
Regarding claim 6, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. However, while Kim does teach determining one or more predicted behaviors of the road agent (see at least [0088]), Kim does not outright teach that the determination is initiated based on a machine learning model. Eagelberg further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent,
Eagelberg teaches ([0146]): "At step 584, processing unit 110 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make the determination based on a weighted average of the individual analyses performed at step 582... Furthermore, in some embodiments, the analysis may make use of trained system (e.g., a machine learning or deep learning system), which may, for example, estimate a future path ahead of a current location of a vehicle based on an image captured at the current location."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a machine learning model.
Eagelberg teaches ([0146]): "At step 584, processing unit 110 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make the determination based on a weighted average of the individual analyses performed at step 582... Furthermore, in some embodiments, the analysis may make use of trained system (e.g., a machine learning or deep learning system), which may, for example, estimate a future path ahead of a current location of a vehicle based on an image captured at the current location."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to further incorporate the teachings of Eagelberg to provide determining one or more predicted behaviors of the road agent, wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a machine learning model. Kim and Eagelberg are each directed towards similar pursuits in the field of autonomous vehicle control, with both in particular being concerned with lane cut-ins and lane changes. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so advantageously allows for the prediction of a future path of the road agent using the trained machine learning system, as recognized by Eagelberg ([0146]), which is particularly beneficial for collision-avoidance purposes. The use of machine learning in Eagelberg provides the additional benefit of improving lane mark identification, as recognized by Eagelberg ([0241]).
Regarding claim 11, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more operational systems include at least one of a deceleration system or an acceleration system.
Kim teaches ([0074]): "The control unit 140 may control an overall operation of the collision avoidance apparatus 100. According to an embodiment, the control unit 140 may be implemented by an ECU. The control unit 140 may receive steering avoidance information calculated by the calculator 130. The control unit 140 may control a steering device, a braking device, and the like, which are disposed in the subject vehicle, so that the subject vehicle travels according to the steering avoidance information."
Regarding claim 12, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more operational systems further include a steering system.
Kim teaches ([0074]): "The control unit 140 may control an overall operation of the collision avoidance apparatus 100. According to an embodiment, the control unit 140 may be implemented by an ECU. The control unit 140 may receive steering avoidance information calculated by the calculator 130. The control unit 140 may control a steering device, a braking device, and the like, which are disposed in the subject vehicle, so that the subject vehicle travels according to the steering avoidance information."
Regarding claim 13, Kim teaches a method, comprising:
receiving, by one or more computing devices from a perception system, sensor data identifying one or more behaviors of a road agent in an environment of an autonomous vehicle;
Kim teaches ([0041]): "Referring to FIG. 1, the collision avoidance apparatus 100 according to the present disclosure includes: a first detector 110 configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector 120 configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle;" Kim further teaches ([0042]): "According to an embodiment, the first detector 110 may include: an image sensor to be disposed at a vehicle so as to have a field of view exterior of the vehicle..." Kim even further teaches ([0043]): "The image sensor may be disposed at an autonomous driving vehicle so as to have a field of view exterior of the autonomous driving vehicle."
estimating, by the one or more computing devices, a spacing profile of the road agent…
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included above, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
the estimated spacing profile including a road agent preference for the lateral gap...
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included above, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed." Here, the estimated spacing profile includes a preference for the lateral gap with respect to the road agent (i.e., the another vehicle); therefore, the estimated spacing profile is considered to include a road agent preference for the lateral gap.
wherein the estimated spacing profile is based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent;
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, while Kim does teach estimating a spacing profile including preference for a lateral gap (see at least [0110]-[0113])) and sensor data identifying detected characteristics of a road agent, road agent behavior, and one or more other road agents (see at least [0041], FIG. 5, and [0108]-[0112]), Kim does not outright teach determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Eagelberg teaches systems and methods for navigating lane merges and lane splits, comprising:
determining, by the one or more computing devices, an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent;
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113]))
estimating, by the one or more computing devices, a spacing profile of the road agent based on changes to the lateral gap over time,
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... If, however, target vehicle 802 is moving such that its trajectory is intersecting lane mark 1004C at an angle (e.g., a small angle less than 90 degrees), then target vehicle 802 is likely moving over quickly and will merge close to host vehicle 200. The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113])). In other words, the estimated spacing profile of the road agent includes the lateral distance monitoring of Kim and the maintenance of a safe distance from the target vehicle of Eagelberg.
and sending, by the one or more computing devices, control instructions to control one or more operational systems of the autonomous vehicle based on the estimated spacing profile.
Eagelberg teaches ([0192]): "The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration." Eagelberg further teaches ([0189]): "Returning to FIG. 9, at step 914, processing unit 110 may determine a navigational action for the host vehicle based on the determined lane mark type and the determined characteristic of the target vehicle. The navigational action may include changing or maintaining one or more of steering, braking, or acceleration/deceleration of the host vehicle. In some embodiments, the navigational action may be carried out using one or more of the throttling system 220, braking system 230, steering system 240, velocity and acceleration module 406, and navigational response module 408 described above in connection with FIGS. 2F and 4."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim to incorporate the teachings of Eagelberg to provide determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Kim and Eagelberg are each directed towards similar pursuits in the field of autonomous vehicle control, with both in particular being concerned with lane cut-ins and lane changes, and the estimation of spacing profiles (see at least [0110]-[0113] of Kim). Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so advantageously improves safety by allowing for the maintenance of a safe distance between the host autonomous vehicle and another vehicle cutting in to the host vehicle's lane ahead of the host vehicle, or if appropriate, facilitating a safe merge with the another vehicle (i.e., the road agent), as recognized by Eagelberg (see at least [0191]-[0192]).
However, neither Kim nor Eagelberg outright teach that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. He teaches an intelligent vehicle safety driving envelope reconstruction method, comprising:
wherein the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent;
He teaches ([0037]): "As shown in FIG. 2, when considering only the current position of forward vehicle ②, the lateral distance Cy,j(t) between intelligent vehicle ① and forward vehicle ② is shown as in FIG. 2 (a). When considering that forward vehicle ② has left-turn driving behavior, the lateral distance C′y,j(t) between intelligent vehicle ① and forward vehicle ② is shown as FIG. 2 (b). Comparing FIG. 2 (a) and FIG. 2 (b), we can see that the lateral spacing between the intelligent vehicle ① and the forward vehicle ② gets smaller. Based on the prediction result, lateral safety distance is reconstructed to achieve new lateral secure model C′y,j(t)=ωyCy,j(t), where ωy is lateral correction factor; represents the variations in scale of lateral distance, and its value depend on the predicted maximum likelihood probability of the left-turning driving behavior of the forward vehicle driving behavior prediction model." One of ordinary skill in the art would recognize that modifying the value of the lateral correction factor would result in reducing or increasing the autonomous vehicle preference for the lateral gap (i.e., the lateral safety distance).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim and Eagelberg to incorporate the teachings of He to provide that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. Kim, Eagelberg, and He are each directed towards similar pursuits in the field of autonomous vehicle control and monitoring of road agent behavior. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of He, as doing so beneficially improves the safety and stability of the autonomous vehicle due to the adjustment of the autonomous vehicle preference for the lateral gap, as recognized by He (see at least [0034]-[0036]).
Regarding claim 14, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
determining one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on when the road agent is predicted to interact with the autonomous vehicle.
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
Regarding claim 15, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
determining one or more predicted behaviors of the road agent,
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a lateral gap requirement for the autonomous vehicle in relation to the road agent.
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed.
Regarding claim 17, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
determining one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on an existing lateral gap between the autonomous vehicle and the road agent.
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information." FIG. 2, included above, demonstrates that the initiation of the analysis is based on an existing lateral gap (i.e., "Current Lateral distance") between the autonomous vehicle and the road agent.
Regarding claim 18, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. However, while Kim does teach determining one or more predicted behaviors of the road agent (see at least [0088]), Kim does not outright teach that the determination is initiated based on a machine learning model. Eagelberg further teaches:
determining one or more predicted behaviors of the road agent,
Eagelberg teaches ([0146]): "At step 584, processing unit 110 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make the determination based on a weighted average of the individual analyses performed at step 582... Furthermore, in some embodiments, the analysis may make use of trained system (e.g., a machine learning or deep learning system), which may, for example, estimate a future path ahead of a current location of a vehicle based on an image captured at the current location."
wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a machine learning model.
Eagelberg teaches ([0146]): "At step 584, processing unit 110 may determine whether or not leading vehicle 200 is changing lanes based on the analysis performed at step 582. For example, processing unit 110 may make the determination based on a weighted average of the individual analyses performed at step 582... Furthermore, in some embodiments, the analysis may make use of trained system (e.g., a machine learning or deep learning system), which may, for example, estimate a future path ahead of a current location of a vehicle based on an image captured at the current location."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to further incorporate the teachings of Eagelberg to provide determining one or more predicted behaviors of the road agent, wherein the determination of the one or more predicted behaviors of the road agent is initiated based on a machine learning model. Kim and Eagelberg are each directed towards similar pursuits in the field of autonomous vehicle control, with both in particular being concerned with lane cut-ins and lane changes. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so advantageously allows for the prediction of a future path of the road agent using the trained machine learning system, as recognized by Eagelberg ([0146]), which is particularly beneficial for collision-avoidance purposes. The use of machine learning in Eagelberg provides the additional benefit of improving lane mark identification, as recognized by Eagelberg ([0241]).
Regarding claim 21, Kim teaches a non-transitory computer-readable medium storing instructions (“computer-readable codes in a medium on which a program is recorded”, “computer-readable mediums” including, e.g., a Read Only Memory, [0155]) that when executed by one or more, cause the one or more processors to perform operations comprising:
receive sensor data from a perception system,
Kim teaches ([0072]): "The calculator 130 may receive detected information from the first detector 110 and the second detector 120. The calculator 130 may determine whether steering avoidance is executable, on the basis of the another vehicle information, subject vehicle information, and distance information."
the sensor data identifying one or more behaviors of a road agent in an environment of an autonomous vehicle;
Kim teaches ([0041]): "Referring to FIG. 1, the collision avoidance apparatus 100 according to the present disclosure includes: a first detector 110 configured to detect another vehicle information including a longitudinal velocity and a lateral velocity of another vehicle, and distance information including a longitudinal distance and a lateral distance from another vehicle; a second detector 120 configured to detect subject vehicle information including a velocity and a yaw rate of the subject vehicle;" Kim further teaches ([0042]): "According to an embodiment, the first detector 110 may include: an image sensor to be disposed at a vehicle so as to have a field of view exterior of the vehicle..." Kim even further teaches ([0043]): "The image sensor may be disposed at an autonomous driving vehicle so as to have a field of view exterior of the autonomous driving vehicle."
estimate a spacing profile of the road agent…
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included above, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
the estimated spacing profile including a road agent preference for the lateral gap,
Kim teaches ([0089]): "Referring to FIG. 2, a lateral position of the another vehicle at a current time point and a lateral position of the another vehicle at a TTC are illustrated. As illustrated in FIG. 2, a consideration is given to a case in which the another vehicle 20 is detected at the position of the subject vehicle 10. A distance to a center of the subject vehicle 10 from a straight line extending in parallel with a traveling direction of the subject vehicle 10 from a center of the another vehicle 20 may be calculated as a lateral distance at the current time point (or a current lateral distance)." FIG. 2, included above, depicts the determined and predicted lateral distances. Kim further teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim even further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed." Here, the estimated spacing profile includes a preference for the lateral gap with respect to the road agent (i.e., the another vehicle); therefore, the estimated spacing profile is considered to include a road agent preference for the lateral gap.
wherein the estimated spacing profile is based on how well observed behavior of the road agent has matched previously predicted behavior for the road agent;
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, while Kim does teach estimating a spacing profile including preference for a lateral gap (see at least [0110]-[0113])) and sensor data identifying detected characteristics of a road agent, road agent behavior, and one or more other road agents (see at least [0041], FIG. 5, and [0108]-[0112]), Kim does not outright teach determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Eagelberg teaches systems and methods for navigating lane merges and lane splits, comprising:
determine an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent;
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113]))
estimate a spacing profile of the road agent based on changes to the lateral gap over time,
Eagelberg teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg further teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... If, however, target vehicle 802 is moving such that its trajectory is intersecting lane mark 1004C at an angle (e.g., a small angle less than 90 degrees), then target vehicle 802 is likely moving over quickly and will merge close to host vehicle 200. The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration. " Eagelberg is modified such that the maintaining of a safe distance from the target vehicle in response to the prediction corresponds to the estimation of the spacing profile of Kim (see at least [0110]-[0113])). In other words, the estimated spacing profile of the road agent includes the lateral distance monitoring of Kim and the maintenance of a safe distance from the target vehicle of Eagelberg.
and send control instructions to control one or more operational systems of the autonomous vehicle based on the estimated spacing profile.
Eagelberg teaches ([0192]): "The navigational action may be a change in acceleration of host vehicle 200 to accommodate the lateral movement of target vehicle 802. As still another example, if the determined characteristic(s) of the target vehicle includes a velocity of the target vehicle relative to the host vehicle, the navigational action for the host vehicle may include maintaining a safe distance from the target vehicle, e.g., through acceleration or deceleration." Eagelberg further teaches ([0189]): "Returning to FIG. 9, at step 914, processing unit 110 may determine a navigational action for the host vehicle based on the determined lane mark type and the determined characteristic of the target vehicle. The navigational action may include changing or maintaining one or more of steering, braking, or acceleration/deceleration of the host vehicle. In some embodiments, the navigational action may be carried out using one or more of the throttling system 220, braking system 230, steering system 240, velocity and acceleration module 406, and navigational response module 408 described above in connection with FIGS. 2F and 4."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim to incorporate the teachings of Eagelberg to provide determining an autonomous vehicle preference for a lateral gap between the autonomous vehicle and the road agent, estimating a spacing profile of the road agent based on changes to the lateral gap over time, and sending control instructions to control one or more operational systems of the autonomous vehicle based on the estimated space profile. Kim and Eagelberg are each directed towards similar pursuits in the field of autonomous vehicle control, with both in particular being concerned with lane cut-ins and lane changes, and the estimation of spacing profiles (see at least [0110]-[0113] of Kim). Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so advantageously improves safety by allowing for the maintenance of a safe distance between the host autonomous vehicle and another vehicle cutting in to the host vehicle's lane ahead of the host vehicle, or if appropriate, facilitating a safe merge with the another vehicle (i.e., the road agent), as recognized by Eagelberg (see at least [0191]-[0192]).
However, neither Kim nor Eagelberg outright teach that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. He teaches an intelligent vehicle safety driving envelope reconstruction method, comprising:
wherein the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent;
He teaches ([0037]): "As shown in FIG. 2, when considering only the current position of forward vehicle ②, the lateral distance Cy,j(t) between intelligent vehicle ① and forward vehicle ② is shown as in FIG. 2 (a). When considering that forward vehicle ② has left-turn driving behavior, the lateral distance C′y,j(t) between intelligent vehicle ① and forward vehicle ② is shown as FIG. 2 (b). Comparing FIG. 2 (a) and FIG. 2 (b), we can see that the lateral spacing between the intelligent vehicle ① and the forward vehicle ② gets smaller. Based on the prediction result, lateral safety distance is reconstructed to achieve new lateral secure model C′y,j(t)=ωyCy,j(t), where ωy is lateral correction factor; represents the variations in scale of lateral distance, and its value depend on the predicted maximum likelihood probability of the left-turning driving behavior of the forward vehicle driving behavior prediction model." One of ordinary skill in the art would recognize that modifying the value of the lateral correction factor would result in reducing or increasing the autonomous vehicle preference for the lateral gap (i.e., the lateral safety distance).
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim and Eagelberg to incorporate the teachings of He to provide that the autonomous vehicle preference for the lateral gap is reduced or increased based on the one or more behaviors of the road agent. Kim, Eagelberg, and He are each directed towards similar pursuits in the field of autonomous vehicle control and monitoring of road agent behavior. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of He, as doing so beneficially improves the safety and stability of the autonomous vehicle due to the adjustment of the autonomous vehicle preference for the lateral gap, as recognized by He (see at least [0034]-[0036]).
Claim(s) 4, 7, 16, and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim, Eagelberg, and He in view of Kang (US 2020/0189596 A1).
Regarding claim 4, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent;
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted."
and determine a maneuver for the autonomous vehicle,
Kim teaches ([0074]): "The control unit 140 may control an overall operation of the collision avoidance apparatus 100. According to an embodiment, the control unit 140 may be implemented by an ECU. The control unit 140 may receive steering avoidance information calculated by the calculator 130. The control unit 140 may control a steering device, a braking device, and the like, which are disposed in the subject vehicle, so that the subject vehicle travels according to the steering avoidance information." Kim further teaches ([0082]): "When steering avoidance is determined to be executable, the DCU may calculate steering avoidance information required to control steering avoidance of the subject vehicle. The DCU may calculate steering avoidance information, that is, information, including a driving direction in which the subject vehicle should travel in order to avoid a collision with the another vehicle, a steering avoidance time for which the subject vehicle should travel in order to avoid a collision with another vehicle, a velocity or an acceleration at which the subject vehicle should travel in order to avoid a collision with another vehicle, and the like."
However, Kim does not outright teach predicting that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent. Eagelberg further teaches:
predict that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent
Eagelberg teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... If, however, target vehicle 802 is moving such that its trajectory is intersecting lane mark 1004C at an angle (e.g., a small angle less than 90 degrees), then target vehicle 802 is likely moving over quickly and will merge close to host vehicle 200." Eagelberg further teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg even further teaches ([0159]): "Disclosed embodiments include systems and methods for navigating an autonomous vehicle to take the foregoing lane change scenarios and any potential maneuvers that other neighboring vehicles may make in view of the lane change into consideration while navigating."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to further incorporate the teachings of Eagelberg to provide predicting that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent. Kim, Eagelberg, and He are each directed towards similar pursuits in the field of autonomous vehicle control and monitoring of road agent behavior. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so beneficially improves safety by allowing for the maintenance of a safe distance between the host autonomous vehicle and another vehicle cutting in to the host vehicle's lane ahead of the host vehicle, or if appropriate, facilitating a safe merge with the another vehicle (i.e., the road agent), as recognized by Eagelberg (see at least [0191]-[0192]).
However, Kim does not outright teach that the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off. Kang teaches an apparatus and method for controlling an autonomous vehicle, comprising:
the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off maneuver.
Kang teaches ([0062]): "In the case in which a first arrival time desired for the autonomous vehicle 1 to arrive at the front boundary line A1 of the potential cut-in space A exceeds a second arrival time desired for the candidate cut-in vehicle 2 to arrive at the front boundary line A1 of the potential cut-in space A, the controller 400 may perform control to decelerate the autonomous vehicle 1, and may yield in order to allow the entry of the candidate cut-in vehicle 2." One of ordinary skill in the art would appreciate that deceleration of the autonomous vehicle 1 would result in a speed slower than the initial (i.e., current) speed of the autonomous vehicle.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Kang to provide that the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off. Kim, Eagelberg, He, and Kang are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Kang, as doing so would allow the autonomous vehicle to flexibly respond to the predicted behavior of the rear vehicle in a manner which prevents the flow of traffic being hindered due to indiscriminate deceleration or yielding, thereby reducing the discomfort of drivers and passengers, as recognized by Kang ([0070]).
Regarding claim 7, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
the one or more processors configured to: determine one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
However, Kim does not outright teach that the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle. Kang teaches an apparatus and method for controlling an autonomous vehicle, comprising:
the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle.
Kang teaches ([0008]): "The present disclosure provides a vehicle running control apparatus and method that are capable of predicting the intention of a rear vehicle to overtake an autonomous vehicle in order to perform a cut-in operation and flexibly responding to the current traveling situation."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Kang to provide that the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle. Kim, Eagelberg, He, and Kang are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Kang, as doing so would allow the autonomous vehicle to flexibly respond to the predicted behavior of the rear vehicle in a manner which prevents the flow of traffic being hindered due to indiscriminate deceleration or yielding, thereby reducing the discomfort of drivers and passengers, as recognized by Kang ([0070]).
Regarding claim 16, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
determining one or more predicted behaviors of the road agent;
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted."
and determining a maneuver for the autonomous vehicle,
Kim teaches ([0074]): "The control unit 140 may control an overall operation of the collision avoidance apparatus 100. According to an embodiment, the control unit 140 may be implemented by an ECU. The control unit 140 may receive steering avoidance information calculated by the calculator 130. The control unit 140 may control a steering device, a braking device, and the like, which are disposed in the subject vehicle, so that the subject vehicle travels according to the steering avoidance information." Kim further teaches ([0082]): "When steering avoidance is determined to be executable, the DCU may calculate steering avoidance information required to control steering avoidance of the subject vehicle. The DCU may calculate steering avoidance information, that is, information, including a driving direction in which the subject vehicle should travel in order to avoid a collision with the another vehicle, a steering avoidance time for which the subject vehicle should travel in order to avoid a collision with another vehicle, a velocity or an acceleration at which the subject vehicle should travel in order to avoid a collision with another vehicle, and the like."
However, Kim does not outright teach predicting that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent. Eagelberg further teaches:
predicting that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent;
Eagelberg teaches ([0192]): "As another example, if the determined characteristic(s) of the target vehicle include a detected lateral motion of the target vehicle relative to the identified lane mark(s), the navigational action for the host vehicle may be determined to facilitate a safe merge with the target vehicle. For instance, referring to FIG. 10A, processing unit 110 may use the detected lateral motion of target vehicle 802 relative to lane mark 1004C to determine whether target vehicle 802 is moving at a reasonable speed and/or maintaining a safe distance from host vehicle 200... If, however, target vehicle 802 is moving such that its trajectory is intersecting lane mark 1004C at an angle (e.g., a small angle less than 90 degrees), then target vehicle 802 is likely moving over quickly and will merge close to host vehicle 200." Eagelberg further teaches ([0130]): "At step 546, processing unit 110 may construct a set of measurements for the detected objects. Such measurements may include, for example, position, velocity, and acceleration values (relative to vehicle 200) associated with the detected objects... Thus, by performing steps 540-546, processing unit 110 may identify vehicles and pedestrians appearing within the set of captured images and derive information (e.g., position, speed, size) associated with the vehicles and pedestrians. Based on the identification and the derived information, processing unit 110 may cause one or more navigational responses in vehicle 200, as described in connection with FIG. 5A, above." Eagelberg even further teaches ([0159]): "Disclosed embodiments include systems and methods for navigating an autonomous vehicle to take the foregoing lane change scenarios and any potential maneuvers that other neighboring vehicles may make in view of the lane change into consideration while navigating."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to further incorporate the teachings of Eagelberg to provide predicting that the road agent will perform a cut-off maneuver based on the one or more predicted behaviors of the road agent. Kim, Eagelberg, and He are each directed towards similar pursuits in the field of autonomous vehicle control and monitoring of road agent behavior. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Eagelberg, as doing so beneficially improves safety by allowing for the maintenance of a safe distance between the host autonomous vehicle and another vehicle cutting in to the host vehicle's lane ahead of the host vehicle, or if appropriate, facilitating a safe merge with the another vehicle (i.e., the road agent), as recognized by Eagelberg (see at least [0191]-[0192]).
However, Kim does not outright teach that the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off. Kang teaches an apparatus and method for controlling an autonomous vehicle, comprising:
wherein the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off.
Kang teaches ([0062]): "In the case in which a first arrival time desired for the autonomous vehicle 1 to arrive at the front boundary line A1 of the potential cut-in space A exceeds a second arrival time desired for the candidate cut-in vehicle 2 to arrive at the front boundary line A1 of the potential cut-in space A, the controller 400 may perform control to decelerate the autonomous vehicle 1, and may yield in order to allow the entry of the candidate cut-in vehicle 2." One of ordinary skill in the art would appreciate that deceleration of the autonomous vehicle 1 would result in a speed slower than the initial (i.e., current) speed of the autonomous vehicle.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Kang to provide that the determined maneuver includes reducing a current speed of the autonomous vehicle to prepare to yield to the road agent when the road agent performs the cut-off. Kim, Eagelberg, He, and Kang are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Kang, as doing so would allow the autonomous vehicle to flexibly respond to the predicted behavior of the rear vehicle in a manner which prevents the flow of traffic being hindered due to indiscriminate deceleration or yielding, thereby reducing the discomfort of drivers and passengers, as recognized by Kang ([0070]).
Regarding claim 19, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
determining one or more predicted behaviors of the road agent,
Kim teaches ([0088]): "The calculator 130 of the collision avoidance apparatus 100 may calculate a Time To Collision (TTC) when a collision with the another vehicle is predicted, on the basis of the another vehicle information, the subject vehicle information, and the distance information."
However, Kim does not outright teach that the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle. Kang teaches an apparatus and method for controlling an autonomous vehicle, comprising:
the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle.
Kang teaches ([0008]): "The present disclosure provides a vehicle running control apparatus and method that are capable of predicting the intention of a rear vehicle to overtake an autonomous vehicle in order to perform a cut-in operation and flexibly responding to the current traveling situation."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Kang to provide that the one or more predicted behaviors of the road agent includes an overtake maneuver in relation to the autonomous vehicle. Kim, Eagelberg, He, and Kang are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Kang, as doing so would allow the autonomous vehicle to flexibly respond to the predicted behavior of the rear vehicle in a manner which prevents the flow of traffic being hindered due to indiscriminate deceleration or yielding, thereby reducing the discomfort of drivers and passengers, as recognized by Kang ([0070]).
Claim(s) 8, 20, and 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Kim, Eagelberg, and He in view of Seccamonte et al. (US 2020/0133280 A1), hereinafter Seccamonte.
Regarding claim 8, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. Kim further teaches:
...based on how well the observed behavior of the road agent has matched the previously predicted behavior for the road agent.
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, Kim does not outright teach that the spacing profile includes a predictability score for the road agent. Seccamonte teaches adjusting lateral clearance for a vehicle, comprising:
the estimated spacing profile includes a predictability score for the road agent…
Seccamonte teaches ([0181]): "In one embodiment, the planning module 1328 uses an extended Kalman filter to track the vehicle 1536 and determine a time for a potential collision... The planning module 1328 determines potential behaviors for the vehicle 1536 (e.g., change of lanes, left turn, etc.) and assigns probabilities to each potential behavior."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Seccamonte to provide that the spacing profile includes a predictability score for the road agent. Kim, Eagelberg, He, and Seccamonte are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Seccamonte, as doing so would beneficially allow for the determination of a time of a potential collision based on assigned probabilities of the road agent, as recognized by Seccamonte ([0181]).
Regarding claim 9, Kim, Eagelberg, and He teach the aforementioned limitations of claim 1. However, Kim does not outright teach that the spacing profile includes a predictability score for the autonomous vehicle. Seccamonte teaches adjusting lateral clearance for a vehicle, comprising:
the estimated spacing profile includes a predictability score for the autonomous vehicle.
Seccamonte teaches ([0186]): "In some embodiments, the generating of the multi-dimensional envelope 1308 includes determining, using the lateral error tolerance E_L, the width 1424 of the multi-dimensional envelope 1308 to avoid a collision of the AV 1304 with an identified object. In some embodiments, using a speed constraint for the AV 1304, a probability of collision for the AV 1304 with the identified object 1320 is determined."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Seccamonte to provide that the spacing profile includes a predictability score for the autonomous vehicle. Kim, Eagelberg, He and Seccamonte are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Seccamonte, as doing so would beneficially allow for the avoidance of a collision between the autonomous vehicle and the road agent based on a predictability score for the autonomous vehicle, as recognized by Seccamonte ([0186]).
Regarding claim 20, Kim, Eagelberg, and He teach the aforementioned limitations of claim 13. Kim further teaches:
...based on how well the observed behavior of the road agent matches the previously predicted behavior for the road agent.
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, Kim does not outright teach that the spacing profile includes a predictability score for the road agent or the autonomous vehicle. Seccamonte teaches adjusting lateral clearance for a vehicle, comprising:
the estimated spacing profile includes a predictability score for the road agent or the autonomous vehicle,
Seccamonte teaches ([0181]): "In one embodiment, the planning module 1328 uses an extended Kalman filter to track the vehicle 1536 and determine a time for a potential collision... The planning module 1328 determines potential behaviors for the vehicle 1536 (e.g., change of lanes, left turn, etc.) and assigns probabilities to each potential behavior."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Seccamonte to provide that the spacing profile includes a predictability score for the road agent or the autonomous vehicle. Kim, Eagelberg, He, and Seccamonte are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Seccamonte, as doing so would beneficially allow for the determination of a time of a potential collision based on assigned probabilities of the road agent, as recognized by Seccamonte ([0181]).
Regarding claim 23, Kim, Eagelberg, and He teach the aforementioned limitations of claim 21. Kim further teaches:
...based on how well the observed behavior of the road agent matches the previously predicted behavior for the road agent.
Kim teaches ([0110]): "In the present example, as illustrated in FIG. 5, at the TTC, the occurrence of a predictive overlap of the subject vehicle 14 and another vehicle 22 is predicted." Kim further teaches ([0113]): "According to an embodiment, the calculator 130 may calculate a target lateral movement distance on the basis of a larger overlap value among current overlap information and predictive overlap information. This configuration is prepared for a case in which a lateral distance to the another vehicle just before a collision according to actual driving and a predictive lateral distance are different, and thus safer steering avoidance may be performed."
However, Kim does not outright teach that the spacing profile includes a predictability score. Seccamonte teaches adjusting lateral clearance for a vehicle, comprising:
the estimated spacing profile includes a predictability score…
Seccamonte teaches ([0181]): "In one embodiment, the planning module 1328 uses an extended Kalman filter to track the vehicle 1536 and determine a time for a potential collision... The planning module 1328 determines potential behaviors for the vehicle 1536 (e.g., change of lanes, left turn, etc.) and assigns probabilities to each potential behavior."
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Kim, Eagelberg, and He to incorporate the teachings of Seccamonte to provide that the spacing profile includes a predictability score. Kim, Eagelberg, He, and Seccamonte are each directed towards similar pursuits in the field of autonomous vehicle control. Accordingly, one of ordinary skill in the art would find it advantageous to incorporate the teachings of Seccamonte, as doing so would beneficially allow for the determination of a time of a potential collision based on assigned probabilities of the road agent, as recognized by Seccamonte ([0181]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Shalev-Shwartz et al. (US 2019/0291728 A1) teaches systems and methods for navigating an autonomous vehicle, including the implementation of hard constraints such as an intervehicular lateral distance (see at least [0271]). Norwood (US 2018/0154894 A1) teaches initiating an analysis of road agent behavior based on whether the road agent is performing an overtake maneuver past the autonomous vehicle (see at least [0049]). Chow (US 2020/0130690 A1) teaches lateral adaptive cruise control, including determining a speed of an autonomous vehicle maneuver based on an estimated spacing profile (see at least [0007], [0057], [0066], and FIGs. 2A-B). Dolgov et al. (US 2014/0297094 A1) teaches controlling vehicle lateral lane positioning, including determining a route or a path of an autonomous vehicle maneuver based on an estimated spacing profile (see at least [0004], [0019], and [0044]). Nilsson (US 2018/0059670 A1) teaches a method of road vehicle trajectory planning including determining possible lateral and longitudinal trajectories and safety critical zones (see at least [0089]-[0090]), wherein the safety critical zones are associated with other vehicles and can be rectangular (i.e., are defined by a particular lateral distance; see at least FIG. 1).
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 FRANK T GLENN III whose telephone number is (571)272-5078. The examiner can normally be reached M-F 7:30AM - 4:30PM EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jelani Smith can be reached at 571-270-3969. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/F.T.G./Examiner, Art Unit 3662
/DALE W HILGENDORF/Primary Examiner, Art Unit 3662
Prosecution Insights