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 .
Examiner’s Note
Examiner has cited particular paragraphs/columns and line numbers or figures in the references as applied to the claims below for the convenience of the applicant. Although the specified citations are representative of the teachings in the art and are applied to the specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant, in preparing the responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner. Applicant is reminded that the Examiner is entitled to give the broadest reasonable interpretation to the language of the claims. Furthermore, the Examiner is not limited to Applicants’ definition which is not specifically set forth in the claims.
Response to Amendment
The amendment filed 12/15/2025 has been entered. Claims 1-5, 7, 9-14, 15, 16, 18, and 19 remain pending in the application.
Response to Arguments
Applicant’s arguments, see pages 9 & 10, filed 12/15/2025, with respect to the indefiniteness rejection have been fully considered and are persuasive. The rejections under U.S.C. 112(b) of the claims have been withdrawn.
Applicant's arguments regarding the rejections under U.S.C. 101 and 103, filed 12/15/2025 have been fully considered but they are not persuasive.
Regarding the rejection under U.S.C 101, applicant asserts that the steps of "obtaining...,""simulating...,""detecting...," and "determining..." cannot be rejected under U.S.C 101 as they allegedly cannot be performed in the human mind, claiming that they are not “observations, evaluations, judgments, or opinions”. However, that is precisely what these limitations represent- the allegation that “the human mind is not equipped to detect a topological structure of a road where the vehicle is located at the current moment or detect road features of the road and entity features of the environmental entity in the environment.” is false, in view of the applicant’s own specification’s meaning of topology and topological structures, stating in [0076] “the topological relationship of the environmental entity may include single-lane topology, merged topology, lane- changing topology, crossing topology, etc.”. It is plainly unreasonable to claim a human cannot identify the surrounding lane environment or type of roadway in this way, and observe the relationship of itself and others within it- this is a basic part of driving. A competent driver must detect the topology of the roadway (as the term is understood in view of the specification), where they fit inside it, where others fit into it as well, and how this will affect the surrounding actors movement. This, then, is an observation as described in MPEP 2106.04(a). Similarly, it is incorrect to say a human mind is unable to “detect road features of the road and entity features of the environmental entity in the environment” as detecting the road and surrounding entities is basic awareness and art of driving- there is no specific type pf feature being detected and as such nothing of this cannot be considered simple human observation. The examiner also disagrees that “further, the human mind is not equipped to determine a driving trajectory of the vehicle based on the optimal interaction intention” as this is a mental process evaluation. The applicant simply states that this cannot be performed in the human mind as fact, however the as-written claim does not represent something which cannot be performed in a human mind as a person is capable of determining a riving trajectory, determining it based on the optimal decision to make aka the optimal intention. Therefore, these are not additional elements but rather further mental processes.
The applicant further asserts that the claim overcomes the rejection under U.S.C. 101 because the above-cited additional elements integrate the abstract ideas into something more than an abstract idea; however this is not possible as they represent mental processes and not additional elements. As an abstract idea limitation cannot serve to integrate the abstract idea into a practical application, these cannot be considered additional elements which are an improvement to the technical field as they are not more than abstract ideas.
Regarding the rejection under U.S.C. 103, applicant paraphrases much of the Zhao system to contrast with the applicant’s characterization of the limitation “obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention,” which the applicant recites and then goes on to paraphrase in such a way that the examiner does not consider the Zhao reference to fail to read on as no specific difference between the reference and claim are described- just a paraphrase of each. While the claims are read in view of the specification, the actual claim as written is examined and interpreted based on what has been claimed. As such, based on the actual claim as written, the examiner maintains that the Zhao reference [0061] “The leaf node with the highest score value may be determined as the target leaf node," [0062] "After determining the target leaf node, we can trace back from the target leaf node to the root node to obtain the nodes arranged along the path from the root node to the target leaf node” reads on the limitation “obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention” with the exception of the “at each moment”, as the examiner does recognize that the Zhao reference appears to evaluate the chain of moments as a whole rather than merely basing on the maximum at each moment. However, the newly-used Narayanan (US 20240174256) reference does disclose this as it discloses a system in which each single node of the decision tree is evaluated, and each lowest-cost action node is followed rather than seeking a complete path and evaluating the total. See full rejection below
Applicant further states that the limitation "determining a driving trajectory of the vehicle based on the optimal interaction intention," is not read on by the Zhao reference as the amended independent claims now “provides that the driving trajectory of the vehicle is determined based on a combination of the optimal interaction intentions corresponding to respective moments of the plurality of future moments.”. See above regarding the new reference which reads on the amended claims, and the full rejection below.
Further regarding U.S.C. 103, the applicant asserts that the Zhao reference fails to disclose “detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment,", "detecting road features of the road and entity features of the environmental entity in the environment,", "obtaining a probability of the interaction intention of each environmental entity based on road features of the road and entity features of the environmental entity in the environment by using an interaction intention recognition model," and "obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity and the probability thereof," and then asserts that neither the Pronovost, Caldwell, nor Jafari fail to disclose or suggest the limitations of Clam 1 as they fail to disclose “obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention; and determining a driving trajectory of the vehicle based on the optimal interaction intention,". This point is moot, as the Pronovost, Caldwell, and Jafari are not used to read on the section which the applicant states they do not read on. Further, regarding the other limitations the applicant makes no more than a mere allegation of patentability and states that the references do not rad on the limitations, which the rejections below demonstrate that the references do. As such, the examiner maintains and updates the rejections below.
Claim Rejections - 35 USC § 101
Claims 1-5, 7, 9-14, 15, 16, 18, and 19 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
Claim 1 is rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more.
The determination of whether a claim recites patent ineligible subject matter is a 2 step inquiry.
STEP 1: the claim does not fall within one of the four statutory categories of invention (process, machine, manufacture or composition of matter), see MPEP 2106.03, or
STEP 2: the claim recites a judicial exception, e.g. an abstract idea, without reciting additional elements that amount to significantly more than the judicial exception, as determined using the following analysis: see MPEP 2106.04
STEP 2A (PRONG 1): Does the claim recite an abstract idea, law of nature, or natural phenomenon? see MPEP 2106.04(II)(A)(1)
STEP 2A (PRONG 2): Does the claim recite additional elements that integrate the judicial exception into a practical application? see MPEP 2106.04(II)(A)(2)
STEP 2B: Does the claim recite additional elements that amount to significantly more than the judicial exception? see MPEP 2106.05
101 Analysis – Step 1
Claim 1 is directed to a method (i.e., a process). Therefore, claim 1 is within at least one of the four statutory categories.
101 Analysis – Step 2A, Prong I
Regarding Prong I of the Step 2A analysis, the claims are to be analyzed to determine whether they recite subject matter that falls within one of the follow groups of abstract ideas: a) mathematical concepts, b) certain methods of organizing human activity, and/or c) mental processes. see MPEP 2106(A)(II)(1) and MPEP 2106.04(a)-(c)
Independent claim 1 includes limitations that recite an abstract idea (emphasized below [with the category of abstract idea in brackets]) and will be used as a representative claim for the remainder of the 101 rejection.
Claim 1 recites a method for determining a vehicle driving trajectory, comprising:
obtaining an interaction scenario of a vehicle at a current moment; [abstract idea – mental process]
sequentially simulating, based on the interaction scenario of the vehicle at the current moment by using forward driving of the vehicle as a constraint condition, an interaction scenario of the vehicle at each of a plurality of future moments, to form a scenario tree consisting of the interaction scenarios at the current moment and the future moments; [abstract idea – mental process]
obtaining a scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree, the scenario value representing a matching degree between the interaction intention and a human driving intention; [abstract idea – mental process]
obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention [abstract idea – mental process]
and determining a driving trajectory of the vehicle based on the optimal interaction intention, [abstract idea – mental process]
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located, and the environmental entity comprises at least the vehicle and other traffic agents. [abstract idea – mental process]
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment; [abstract idea – mental process]
obtaining, based on a topological relationship of a road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment; [abstract idea – mental process]
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity; [abstract idea – mental process]
detecting road features of the road and entity features of the environmental entity in the environment; [abstract idea – mental process]
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment by using an interaction intention recognition model; [abstract idea – mental process]
and obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity and the probability thereof. [abstract idea – mental process]
The examiner submits that the foregoing bolded limitation(s) constitute a “mental process” because under its broadest reasonable interpretation, the claim covers limitations which may be performed in the human mind. Regarding the limitations of this claim, limitations “obtaining an interaction scenario of a vehicle at a current moment” in the context of this claim encompass a person observing the interaction scenario around their vehicle at the current time. The limitations “sequentially simulating, based on an interaction scenario of a vehicle at a current moment by using forward driving of the vehicle as a constraint condition, an interaction scenario of the vehicle at each of a plurality of future moments, to form a scenario tree consisting of the interaction scenarios at the current moment and the future moments;” in the context of this claim encompass a person mentally visualizing/simulating a series of future actions of a vehicle at a series of future moments, only considering scenarios in which the vehicle moves forward. This represents what any responsible driver must do before and during navigating an intersection with other vehicles, mentally determining what may happen if certain actions are taken by themselves and others during the interaction. The limitations “obtaining a scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree, the scenario value representing a matching degree between the interaction intention and a human driving intention” in the context of this claim encompass a person assigning a value to each potation scenario or course of action based on how closely it resembles what a person would normally do. The limitations “obtaining an optimal interaction intention of the vehicle in the interaction scenario at each moment based on the scenario value;” in the context of this claim encompass a person determining which value is highest among a set of values assigned to different scenarios, and determining it as optimal. The limitations “obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention” in the context of this claim encompass a person determining an optimal action at a point in time, for a series of points in time, then selecting the interaction intention with the maximum overall interaction intention. The limitations “and determining a driving trajectory of the vehicle based on the optimal interaction intention” in the context of this claim encompass a person determining a vehicle trajectory based on an intended set of actions. The limitations “wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located, and the environmental entity comprises at least the vehicle and other traffic agents.” in the context of this claim encompass a person considering their own and other’s intended movements and interaction actions while simulating the interaction. The limitations “wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment;” in the context of this claim encompass a person observing the topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment. Examiner notes that the “topological structure” is described in the applicant’s specification as “topological relationship of the environmental entity may include single-lane topology, merged topology, lane- changing topology, crossing topology, etc. The single-lane topology refers to a topological structure where the road on which the environmental entity is located is a single lane, and a possible traffic behavior of the environmental entity under this topological structure is single-lane driving.”, this topological structure is something clearly understandable and detectable by the human mind. The limitations “obtaining, based on a topological relationship of a road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment” in the context of this claim encompass a person observing the relative locations of objects in their surroundings withing the topological environment. The limitations “obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity;” in the context of this claim encompass a person determining what an environmental entity will do based on its lane, location, etc. The limitations “detecting road features of the road and entity features of the environmental entity in the environment” in the context of this claim encompass a person observing their surroundings. The limitations “obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment by using an interaction intention recognition model” in the context of this claim encompass a person determining how others in their surroundings are likely to act based on the road, the features of the other entity, using logic. The limitations “and obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity and the probability thereof” in the context of this claim encompass a person determining a scenario for the driving based on what the others on the road are likely to do. Accordingly, the claim recites at least one abstract idea.
101 Analysis – Step 2A, Prong II
Regarding Prong II of the Step 2A analysis, the claims are to be analyzed to determine whether the claim, as a whole, integrates the abstract into a practical application. see MPEP 2106.04(II)(A)(2) and MPEP 2106.04(d)(2). It must be determined whether any additional elements in the claim beyond the abstract idea integrate the exception into a practical application in a manner that imposes a meaningful limit on the judicial exception. The courts have indicated that additional elements merely using a computer to implement an abstract idea, adding insignificant extra solution activity, or generally linking use of a judicial exception to a particular technological environment or field of use do not integrate a judicial exception into a “practical application.”
In the present case, the additional limitations beyond the above-noted abstract idea are as follows (where the underlined portions are the “additional limitations” [with a description of the additional limitations in brackets], while the bolded portions continue to represent the “abstract idea”.):
obtaining an interaction scenario of a vehicle at a current moment; [abstract idea – mental process]
sequentially simulating, based on the interaction scenario of the vehicle at the current moment by using forward driving of the vehicle as a constraint condition, an interaction scenario of the vehicle at each of a plurality of future moments, to form a scenario tree consisting of the interaction scenarios at the current moment and the future moments; [abstract idea – mental process]
obtaining a scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree, the scenario value representing a matching degree between the interaction intention and a human driving intention; [abstract idea – mental process]
obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario at each moment, and using the interaction intention having the maximum scenario value as an optimal interaction intention [abstract idea – mental process]
and determining a driving trajectory of the vehicle based on the optimal interaction intention, [abstract idea – mental process]
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located, and the environmental entity comprises at least the vehicle and other traffic agents. [abstract idea – mental process]
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment; [abstract idea – mental process]
obtaining, based on a topological relationship of a road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment; [abstract idea – mental process]
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity; [abstract idea – mental process]
detecting road features of the road and entity features of the environmental entity in the environment; [abstract idea – mental process]
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment by using an interaction intention recognition model; [abstract idea – mental process]
and obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity and the probability thereof. [abstract idea – mental process]
As shown above, the claim does not include an additional limitations other than those which represent an abstract idea, consisting entirely of abstract idea mental processes. As such, there can be no additional limitation to integrate the abstract ides into something to significantly more than the judicial exception.
101 Analysis – Step 2B
Regarding Step 2B of the Revised Guidance, representative independent claim 1 does not include additional elements (considered both individually and as an ordered combination) that are sufficient to amount to significantly more than the judicial exception for the same reasons to those discussed above with respect to determining that the claim does not integrate the abstract idea into a practical application. As discussed above with respect to integration of the abstract idea into a practical application, there are no additional elements to analyze and therefore no additional elements which may integrate the claim into an abstract idea. Hence, the claim is not patent eligible.
Dependent claims 2-5, 7, and 9 do not recite any further limitations that cause the claim(s) to be patent eligible. Rather, the limitations of dependent claims are directed toward additional aspects of the judicial exception and/or well-understood, routine and conventional additional elements that do not integrate the judicial exception into a practical application. Therefore, dependent claims 2-5, 7, and 9 are not patent eligible under the same rationale as provided for in the rejection of Independent Claim 1.
Claim 10 is rejected for the same reasons as the representative Claim 1 above, as the claim is
substantially identical to the examined claims with only minor changes to the limitations; being a computer which performs a method- changes which do not overcome the rejection above. The claim recites a computer device; however this is contained entirely within the preamble, and at best serves merely to perform the abstract idea using a generic computer- something which fails to integrate the abstract idea into a practical application and does not represent anything beyond what is routine and conventional in the art.
Dependent claims 11-14, 16, 18, and 19 do not recite any further limitations that cause the claim(s) to be patent eligible. Rather, the limitations of dependent claims are directed toward additional aspects of the judicial exception and/or well-understood, routine and conventional additional elements that do not integrate the judicial exception into a practical application. Therefore, dependent claims 11-14, 16, 18, and 19 are not patent eligible under the same rationale as provided for in the rejection of Independent Claim 10.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-4, 7, 10-13, 16 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao (CN 115675518), herein after referred to as Zhao, in view of Pronovost (US 20240174265), herein after referred to as Pronovost, Narayanan (US 20240174256), herein after referred to as Narayanan, and Caldwell (US 20240092398), herein after referred to as Caldwell.
Regarding Claim 1, Zhao discloses:
obtaining an interaction scenario of a vehicle at a current moment; (see at least [0006] “When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained, where the first state includes: driving states of the vehicle and the first obstacle at the first moment, respectively;”)
sequentially simulating, (see at least [0007] “Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period”)
based on the interaction scenario of the vehicle at the current moment (see at least [0006] “When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained,”)
by using forward driving of the vehicle as a constraint condition, (see at least [0094] “the initial driving trajectory is used as a constraint”)
an interaction scenario of the vehicle at each of a plurality of future moments, (see at least [0052] “As the interaction between the main vehicle and the first obstacle progresses, the above process of constructing parent-child nodes is repeated until the interaction between the main vehicle and the first obstacle ends”)
to form a scenario tree consisting of the interaction scenarios at the current moment and the future moments; (see at least [0008] “Constructing a first game tree based on the first state and the M second states, where the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node;”)
obtaining a scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree (see at least [0060] “All leaf results simulated in the first game tree can be scored, and the scoring criteria can take into account interaction safety, interaction sensation, traffic rules, etc”)
obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario ... and using the interaction intention having the maximum scenario value as an optimal interaction intention; (see at least [0061] “The leaf node with the highest score value may be determined as the target leaf node,”) [0062] "After determining the target leaf node, we can trace back from the target leaf node to the root node to obtain the nodes arranged along the path from the root node to the target leaf node
and determining a driving trajectory of the vehicle based on the optimal interaction intention, (see at least [0063] “By recording the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment in the order of the path, the target driving trajectory of the vehicle can be obtained.”)
wherein the interaction [scenarios comprise] an interaction intention of each environmental entity in an environment where the vehicle is located, (see at least [0047] “For example, at least one driving behavior that the main vehicle may decide includes driving behavior A1 and driving behavior A2, and at least one driving behavior that the first obstacle may decide includes driving behavior B1 and driving behavior B2. Then the M first behavior combinations include (A1, B1), (A1, B2), (A2, B1) and (A2, B2)." [0075] "during the simulation of the interaction between the main vehicle and the first obstacle, it is possible to detect whether there is a second obstacle around the main vehicle that interacts with it. If it is detected that the main vehicle interacts with the second obstacle, a second game tree for the interaction between the main vehicle and the second obstacle can be constructed.”)
and the environmental entity comprises at least the vehicle and other traffic agents. (see at least [0011] “the first behavior combinations include: driving behaviors of the vehicle and the first obstacle, respectively, within the first time period,”)
detecting road features of the road and entity features of the environmental entity in the environment; (see at least [0038] “In step S101, the vehicle may be an autonomous driving vehicle, which may be referred to as a master vehicle, and the first obstacle may be an obstacle around the master vehicle, which may be a motor vehicle, which may be referred to as a slave vehicle.”)
[determining environmental entity actions] by using an interaction intention recognition model; (see at least [0047] “at least one driving behavior that the first obstacle may decide includes driving behavior B1 and driving behavior B2." [0127] "computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms”)
and obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity (see at least [0032] “When interaction between a vehicle and a first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained,")
Zhao does not explicitly disclose:
the scenario value representing a matching degree between the interaction intention and a human driving intention;
[having a maximum scenario value of the vehicle in the interaction scenario] at each moment
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located,
being in one tree
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment;
obtaining, based on the topological relationship of the road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment;
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity;
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment
by using an interaction intention recognition model;
and the probability thereof.
While not explicitly disclosing, Zhao makes obvious:
the scenario value representing a matching degree between the interaction intention and a human driving intention; (see at least [0060] “the higher the scoring value of the leaf node, the better the safety of the main vehicle and the first obstacle at the end of the interaction or during the interaction, the better the interaction sensation, and both comply with traffic rules;”)
As a sensation is felt by a person, and safety and traffic-rule compliance are both considerations taken into account by a human driver, the examiner considers it obvious to a person having ordinary skill in the art at the time of the applicant’s claimed invention to consider these as representing human driving intention. Therefore, as the Zhao reference discloses using these to determine a value of a scenario intention, the examiner understand it to be obvious that Zhao discloses “the scenario value representing a matching degree between the interaction intention and a human driving intention”
In the same field of endeavor, Pronovost discloses:
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located, (see at least [0052] “The decision tree can represent one or more objects (e.g., the vehicle 108) in the environment 100 (e.g., a simulated environment or a real-world environment).”)
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment; (see at least [Fig. 1] [0089] “the localization component 620 may include functionality to receive data from the sensor system(s) 606 to determine a position and/or orientation of the vehicle 602 (e.g., one or more of an x-, y-, z-position, roll, pitch, or yaw). For example, the localization component 620 may include and/or request/receive a map of an environment, such as from map(s) 628 and/or map component 628, and may continuously determine a location and/or orientation of the autonomous vehicle within the map." [0095] " a map may be any number of data structures modeled in two dimensions, three dimensions, or N-dimensions that are capable of providing information about an environment, such as, but not limited to, topologies”)
obtaining, based on the topological relationship of the road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment; (see at least [Fig. 1]) (*See the vehicles identified as being in certain lanes within the environment)
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity; (see at least [Fig. 1, items 118 and 120] [0066] “The object intent 306 can include, for example, one or more of: a) a reactive intent in which an object changes lanes," (*See Fig 1, in which potential intents of the vehicle are limited to those permitted by its relationship to the street direction and its travel lane) [0039] “ The object trajectories predicted by the model component 110 (e.g., the object trajectories 118 and 120) described herein may be based on passive prediction (e.g., independent of an action the vehicle and/or another object takes in the environment, substantially no reaction to the action of the vehicle and/or other objects, etc.), active prediction (e.g., based on a reaction to an action of the vehicle and/or another object in the environment), or a combination thereof”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to generate an interaction scenario which comprises an interaction intention of each environmental entity in an environment where the vehicle is located, rather than a plurality of decision trees for each object, as taught by Pronovost to represent one or more objects in a single scenario decision tree [0052] as well as obtain, based on a topological relationship of a road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment and obtain an interaction intention of each environmental entity based on the topological relationship of the environmental entity, as taught by Pronovost to determine what action a vehicle may take [0066]..
In the same field of endeavor, Caldwell discloses:
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment (see at least [Fig. 1] [0028] “the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).") (*See the vehicles identified as being in certain lanes within the environment, and the potential intents being constrained by their topological relationship to road features)
and the probability thereof. (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the probabilities of vehicle intents, and obtain a probability of the interaction intention of each environmental entity based on road features of the road and entity features of the environmental entity in the environment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
In the same field of endeavor, Narayanan discloses:
[having a maximum scenario value of the vehicle in the interaction scenario] at each moment (see at least [0036] “the planning component may iteratively, at each node in the search, determine a set of candidate actions (e.g., including inertial-based, route-based, and/or perturbed candidate actions), evaluate the associated candidate action nodes using one or more costs functions, and traverse the tree based on determining the one (or more) lowest-cost action nodes.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the max scenario value at each moment and use this to determine the optimal interaction intention, as taught by Narayanan to iteratively determine a set of candidate actions [0036].
Regarding Claim 2, modified Zhao discloses the limitations of Claim 1, and Zhao further discloses:
sequentially simulating, by using the interaction intention in the interaction scenario at the current moment as a starting point of deduction, an interaction intention of the vehicle (see at least [0006] “the first behavior combinations include: driving behaviors of the vehicle" [0007] "Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations" [0042] "The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are”)
simulating an interaction intention of another environmental entity (see at least [0006] “the first behavior combinations include: driving behaviors of... the first obstacle within the first time period" [0007] "Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations" [0042] "The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are”)
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle ...and the interaction intention of the another environmental entity ... at each of the future moments. (see at least [0042] “a first game tree for the interaction between the host vehicle and the first obstacle may be constructed, and the initial state may be used as the node state of the root node of the first game tree. The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are.”)
Zhao does not explicitly disclose:
and a probability thereof when the vehicle drives forward to each of the future moments;
and a probability thereof at each of the future moments based on the interaction intention of the vehicle and the probability thereof at each of the future moments
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle and the probability thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments.
In the same field of endeavor, Caldwell disclose:
and a probability thereof when the vehicle drives forward to each of the future moments; (see at least [0023] “an object intent may comprise a set (e.g., zero, one, or more than one) potential responses of the object to an environmental condition (which may include the action of the autonomous vehicle)" [0028] "the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence)." [0030] "The vehicle 102 can prepare for the pedestrian 110 to enter the roadway by determining a vehicle trajectory that takes into consideration multiple object trajectories, or intents, as part of a decision tree”) (*Examiner considers a system capable of determining the probability of intent of an agent as capable of doing the same to the self vehicle. Further, as the system bases the vehicle trajectory, and therefore it's intents in the probabilities of an object such as a pedestrian, it discloses the probability of its own intent)
and a probability thereof at each of the future moments based on the interaction intention of the vehicle and the probability thereof at each of the future moments (see at least [0020] “object trajectories and object intents affecting how the object “reacts” to the vehicle (e.g., different reaction thresholds for different object intents which can be independently tested) to identify less likely actions by an object which, if taken by the object, may not otherwise be considered (e.g., in systems that only consider a most likely action by the object)." [0028] "the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).”)
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle and the probability thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments. (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the probabilities of the vehicle and surrounding object intentions, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 3, modified Zhao discloses the limitations of Claim 2, and Zhao further discloses:
simulating all interaction intentions of the vehicle ... when the vehicle drives forward to each of the plurality of future moments; (see at least [0042] “a first game tree for the interaction between the host vehicle and the first obstacle may be constructed, and the initial state may be used as the node state of the root node of the first game tree. The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are.”)
Zhao does not explicitly disclose:
simulating all interaction intentions of the vehicle and probabilities thereof when the vehicle drives forward to each of the plurality of future moments;
and searching for a plurality of interaction intentions and probabilities thereof from all the interaction intentions by a predetermined first search algorithm,
as preferred interaction intentions of the vehicle and probabilities thereof at the future moment.
In the same field of endeavor, Caldwell discloses:
simulating all interaction intentions of the vehicle and probabilities thereof when the vehicle drives forward to each of the plurality of future moments; (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
and searching for a plurality of interaction intentions and probabilities thereof from all the interaction intentions by a predetermined first search algorithm, (see at least [0062] “the decision tree component 304 can apply a tree search algorithm to perform a tree search 406 based at least in part on the search setup 404. The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents" [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period"”)
as preferred interaction intentions of the vehicle and probabilities thereof at the future moment. (see at least [0033] “he decision tree component 304 can apply a tree search algorithm to perform a tree search 406 based at least in part on the search setup 404. The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents" [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period")
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the probabilities of all intentions when the vehicle drives forward to each of the plurality of future moments, and search the intentions and their probabilities by a search algorithm toas preferred interactions intentions and probabilities thereof at the future moment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 4, modified Zhao discloses the limitations of Claim 3, but Zhao does not explicitly disclose:
simulating the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments;
and the obtaining the interaction scenario at each of the future moments comprises: obtaining the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments.
In the same field of endeavor, Caldwell discloses:
simulating the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments; (see at least [Fig. 1] [0009] “ A computing device can generate a decision tree having nodes to represent different object intents and/or nodes to represent vehicle actions at a future time. ”)
and the obtaining the interaction scenario at each of the future moments comprises: obtaining the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments. (see at least [Fig. 1] [0062] “ The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents. Thus, the tree search 406 can represent various potential interactions between an object relative to another object and/or an object relative to an autonomous vehicle." [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period"”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments and obtain the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 7, modified Zhao discloses the limitations of Claim 1, and Zhao further discloses:
obtaining the driving trajectory of the vehicle at each moment based on the optimal interaction intention of the vehicle in the interaction scenario at each moment; and obtaining driving trajectories of the vehicle within time periods from the current moment to the plurality of future moments based on the driving trajectory of the vehicle at each moment. (see at least [0063] “By recording the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment in the order of the path, the target driving trajectory of the vehicle can be obtained. The target driving trajectory may include information such as angle, angular velocity, position, acceleration, and speed.”)
Regarding Claim 10, Zhao discloses:
comprising a processor (see at least [0016] “at least one processor”)
and a storage apparatus (see at least [0017] “a memory communicatively connected to at least one processor;”)
configured to store a plurality of pieces of program code, wherein the program code is adapted to be loaded and executed by the processor (see at least [0018] “a memory communicatively connected to at least one processor;”)
to perform a method for determining a vehicle driving trajectory, the method comprising: (see at least [0005] “a trajectory planning method is provided,”)
obtaining an interaction scenario of a vehicle at a current moment; (see at least [0006] “When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained, where the first state includes: driving states of the vehicle and the first obstacle at the first moment, respectively;”)
sequentially simulating, (see at least [0007] “Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period”)
based on the interaction scenario of the vehicle at the current moment (see at least [0006] “When an interaction between the vehicle and the first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained,”)
by using forward driving of the vehicle as a constraint condition, (see at least [0094] “the initial driving trajectory is used as a constraint”)
an interaction scenario of the vehicle at each of a plurality of future moments, (see at least [0052] “As the interaction between the main vehicle and the first obstacle progresses, the above process of constructing parent-child nodes is repeated until the interaction between the main vehicle and the first obstacle ends”)
to form a scenario tree consisting of the interaction scenarios at the current moment and the future moments; (see at least [0008] “Constructing a first game tree based on the first state and the M second states, where the first state is a state of a first node of the first game tree, the second state is a state of a second node of the first game tree, and the second node is a child node of the first node;”)
obtaining a scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree (see at least [0060] “All leaf results simulated in the first game tree can be scored, and the scoring criteria can take into account interaction safety, interaction sensation, traffic rules, etc”)
obtaining an interaction intention having a maximum scenario value of the vehicle in the interaction scenario ... and using the interaction intention having the maximum scenario value as an optimal interaction intention; (see at least [0061] “The leaf node with the highest score value may be determined as the target leaf node,”) [0062] "After determining the target leaf node, we can trace back from the target leaf node to the root node to obtain the nodes arranged along the path from the root node to the target leaf node
and determining a driving trajectory of the vehicle based on the optimal interaction intention, (see at least [0063] “By recording the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment in the order of the path, the target driving trajectory of the vehicle can be obtained.”)
wherein the interaction [scenarios comprise] an interaction intention of each environmental entity in an environment where the vehicle is located, (see at least [0047] “For example, at least one driving behavior that the main vehicle may decide includes driving behavior A1 and driving behavior A2, and at least one driving behavior that the first obstacle may decide includes driving behavior B1 and driving behavior B2. Then the M first behavior combinations include (A1, B1), (A1, B2), (A2, B1) and (A2, B2)." [0075] "during the simulation of the interaction between the main vehicle and the first obstacle, it is possible to detect whether there is a second obstacle around the main vehicle that interacts with it. If it is detected that the main vehicle interacts with the second obstacle, a second game tree for the interaction between the main vehicle and the second obstacle can be constructed.”)
and the environmental entity comprises at least the vehicle and other traffic agents. (see at least [0011] “the first behavior combinations include: driving behaviors of the vehicle and the first obstacle, respectively, within the first time period,”)
detecting road features of the road and entity features of the environmental entity in the environment; (see at least [0038] “In step S101, the vehicle may be an autonomous driving vehicle, which may be referred to as a master vehicle, and the first obstacle may be an obstacle around the master vehicle, which may be a motor vehicle, which may be referred to as a slave vehicle.”)
[determining environmental entity actions] by using an interaction intention recognition model; (see at least [0047] “at least one driving behavior that the first obstacle may decide includes driving behavior B1 and driving behavior B2." [0127] "computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units that run machine learning model algorithms”)
and obtaining the interaction scenario at the current moment based on the interaction intention of each environmental entity (see at least [0032] “When interaction between a vehicle and a first obstacle is detected, a first state at a first moment and M first behavior combinations within a first time period are obtained,")
Zhao does not explicitly disclose:
the scenario value representing a matching degree between the interaction intention and a human driving intention;
[having a maximum scenario value of the vehicle in the interaction scenario] at each moment
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located,
being in one tree
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment;
obtaining, based on the topological relationship of the road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment;
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity;
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment
by using an interaction intention recognition model;
and the probability thereof.
While not explicitly disclosing, Zhao makes obvious:
the scenario value representing a matching degree between the interaction intention and a human driving intention; (see at least [0060] “the higher the scoring value of the leaf node, the better the safety of the main vehicle and the first obstacle at the end of the interaction or during the interaction, the better the interaction sensation, and both comply with traffic rules;”)
As a sensation is felt by a person, and safety and traffic-rule compliance are both considerations taken into account by a human driver, the examiner considers it obvious to a person having ordinary skill in the art at the time of the applicant’s claimed invention to consider these as representing human driving intention. Therefore, as the Zhao reference discloses using these to determine a value of a scenario intention, the examiner understand it to be obvious that Zhao discloses “the scenario value representing a matching degree between the interaction intention and a human driving intention”
In the same field of endeavor, Pronovost discloses:
wherein the interaction scenario comprises an interaction intention of each environmental entity in an environment where the vehicle is located, (see at least [0052] “The decision tree can represent one or more objects (e.g., the vehicle 108) in the environment 100 (e.g., a simulated environment or a real-world environment).”)
wherein the obtaining the interaction scenario of the vehicle at the current moment comprises: detecting a topological structure of a road where the vehicle is located at the current moment to obtain a topological relationship of a road in the environment where the vehicle is located at the current moment; (see at least [Fig. 1] [0089] “the localization component 620 may include functionality to receive data from the sensor system(s) 606 to determine a position and/or orientation of the vehicle 602 (e.g., one or more of an x-, y-, z-position, roll, pitch, or yaw). For example, the localization component 620 may include and/or request/receive a map of an environment, such as from map(s) 628 and/or map component 628, and may continuously determine a location and/or orientation of the autonomous vehicle within the map." [0095] " a map may be any number of data structures modeled in two dimensions, three dimensions, or N-dimensions that are capable of providing information about an environment, such as, but not limited to, topologies”)
obtaining, based on the topological relationship of the road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment; (see at least [Fig. 1]) (*See the vehicles identified as being in certain lanes within the environment)
obtaining an interaction intention of each environmental entity based on the topological relationship of the environmental entity; (see at least [Fig. 1, items 118 and 120] [0066] “The object intent 306 can include, for example, one or more of: a) a reactive intent in which an object changes lanes," (*See Fig 1, in which potential intents of the vehicle are limited to those permitted by its relationship to the street direction and its travel lane) [0039] “ The object trajectories predicted by the model component 110 (e.g., the object trajectories 118 and 120) described herein may be based on passive prediction (e.g., independent of an action the vehicle and/or another object takes in the environment, substantially no reaction to the action of the vehicle and/or other objects, etc.), active prediction (e.g., based on a reaction to an action of the vehicle and/or another object in the environment), or a combination thereof”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to generate an interaction scenario which comprises an interaction intention of each environmental entity in an environment where the vehicle is located, rather than a plurality of decision trees for each object, as taught by Pronovost to represent one or more objects in a single scenario decision tree [0052] as well as obtain, based on a topological relationship of a road in the environment where the vehicle is located at the current moment, a topological relationship of each environmental entity in the environment and obtain an interaction intention of each environmental entity based on the topological relationship of the environmental entity, as taught by Pronovost to determine what action a vehicle may take [0066]..
In the same field of endeavor, Caldwell discloses:
obtaining a probability of the interaction intention of each environmental entity based on the road features of the road and the entity features of the environmental entity in the environment (see at least [Fig. 1] [0028] “the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).") (*See the vehicles identified as being in certain lanes within the environment, and the potential intents being constrained by their topological relationship to road features)
and the probability thereof. (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the probabilities of vehicle intents, and obtain a probability of the interaction intention of each environmental entity based on road features of the road and entity features of the environmental entity in the environment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
In the same field of endeavor, Narayanan discloses:
[having a maximum scenario value of the vehicle in the interaction scenario] at each moment (see at least [0036] “the planning component may iteratively, at each node in the search, determine a set of candidate actions (e.g., including inertial-based, route-based, and/or perturbed candidate actions), evaluate the associated candidate action nodes using one or more costs functions, and traverse the tree based on determining the one (or more) lowest-cost action nodes.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the max scenario value at each moment and use this to determine the optimal interaction intention, as taught by Narayanan to iteratively determine a set of candidate actions [0036].
Regarding Claim 11, modified Zhao discloses the limitations of Claim 10, and Zhao further discloses:
sequentially simulating, by using the interaction intention in the interaction scenario at the current moment as a starting point of deduction, an interaction intention of the vehicle (see at least [0006] “the first behavior combinations include: driving behaviors of the vehicle" [0007] "Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations" [0042] "The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are”)
simulating an interaction intention of another environmental entity (see at least [0006] “the first behavior combinations include: driving behaviors of... the first obstacle within the first time period" [0007] "Determining, based on the first state and the M first behavior combinations, M second states at a second moment at the end of the first time period, the second states comprising: simulated driving states of the vehicle and the first obstacle after each of them performs the driving behaviors according to the first behavior combinations" [0042] "The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are”)
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle ...and the interaction intention of the another environmental entity ... at each of the future moments. (see at least [0042] “a first game tree for the interaction between the host vehicle and the first obstacle may be constructed, and the initial state may be used as the node state of the root node of the first game tree. The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are.”)
Zhao does not explicitly disclose:
and a probability thereof when the vehicle drives forward to each of the future moments;
and a probability thereof at each of the future moments based on the interaction intention of the vehicle and the probability thereof at each of the future moments
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle and the probability thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments.
In the same field of endeavor, Caldwell disclose:
and a probability thereof when the vehicle drives forward to each of the future moments; (see at least [0023] “an object intent may comprise a set (e.g., zero, one, or more than one) potential responses of the object to an environmental condition (which may include the action of the autonomous vehicle)" [0028] "the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence)." [0030] "The vehicle 102 can prepare for the pedestrian 110 to enter the roadway by determining a vehicle trajectory that takes into consideration multiple object trajectories, or intents, as part of a decision tree”) (*Examiner considers a system capable of determining the probability of intent of an agent as capable of doing the same to the self vehicle. Further, as the system bases the vehicle trajectory, and therefore it's intents in the probabilities of an object such as a pedestrian, it discloses the probability of its own intent)
and a probability thereof at each of the future moments based on the interaction intention of the vehicle and the probability thereof at each of the future moments (see at least [0020] “object trajectories and object intents affecting how the object “reacts” to the vehicle (e.g., different reaction thresholds for different object intents which can be independently tested) to identify less likely actions by an object which, if taken by the object, may not otherwise be considered (e.g., in systems that only consider a most likely action by the object)." [0028] "the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).”)
and obtaining the interaction scenario at each of the future moments based on the interaction intention of the vehicle and the probability thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments. (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the probabilities of the vehicle and surrounding object intentions, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 12, modified Zhao discloses the limitations of Claim 11, and Zhao further discloses:
simulating all interaction intentions of the vehicle ... when the vehicle drives forward to each of the plurality of future moments; (see at least [0042] “a first game tree for the interaction between the host vehicle and the first obstacle may be constructed, and the initial state may be used as the node state of the root node of the first game tree. The number of layers of the first game tree is determined based on the interaction time between the main vehicle and the first obstacle. The longer the interaction time, the more layers there are.”)
Zhao does not explicitly disclose:
simulating all interaction intentions of the vehicle and probabilities thereof when the vehicle drives forward to each of the plurality of future moments;
and searching for a plurality of interaction intentions and probabilities thereof from all the interaction intentions by a predetermined first search algorithm,
as preferred interaction intentions of the vehicle and probabilities thereof at the future moment.
In the same field of endeavor, Caldwell discloses:
simulating all interaction intentions of the vehicle and probabilities thereof when the vehicle drives forward to each of the plurality of future moments; (see at least [0028] “The confidence values can be used to evaluate the potential interactions between the vehicle and the object 108 or to determine a speed (or other metric) associated with the vehicle trajectory 116 (e.g., to prepare the vehicle 102 for a left-turn by the object 108).”)
and searching for a plurality of interaction intentions and probabilities thereof from all the interaction intentions by a predetermined first search algorithm, (see at least [0062] “the decision tree component 304 can apply a tree search algorithm to perform a tree search 406 based at least in part on the search setup 404. The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents" [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period"”)
as preferred interaction intentions of the vehicle and probabilities thereof at the future moment. (see at least [0033] “he decision tree component 304 can apply a tree search algorithm to perform a tree search 406 based at least in part on the search setup 404. The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents" [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period")
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the probabilities of all intentions when the vehicle drives forward to each of the plurality of future moments, and search the intentions and their probabilities by a search algorithm toas preferred interactions intentions and probabilities thereof at the future moment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 13, modified Zhao discloses the limitations of Claim 12, but Zhao does not explicitly disclose:
simulating the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments;
and the obtaining the interaction scenario at each of the future moments comprises: obtaining the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments.
In the same field of endeavor, Caldwell discloses:
simulating the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments; (see at least [Fig. 1] [0009] “ A computing device can generate a decision tree having nodes to represent different object intents and/or nodes to represent vehicle actions at a future time. ”)
and the obtaining the interaction scenario at each of the future moments comprises: obtaining the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments. (see at least [Fig. 1] [0062] “ The tree search algorithm can, for example, initiate one or more scenarios for determining future positions of the objects based on the various object intents. Thus, the tree search 406 can represent various potential interactions between an object relative to another object and/or an object relative to an autonomous vehicle." [0063] "Generally, the nodes of the decision tree 308 represent a “belief” state of an environment, object, vehicle, etc. rather than an actual state of the environment, object, etc. ... the “belief” state node(s) can represent a probability distribution over states (e.g., an object position, etc.) associated with a time period"”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to simulate the interaction intention of the another environmental entity and the probability thereof at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof at each of the future moments and obtain the interaction scenario at each of the future moments based on the preferred interaction intentions of the vehicle and the probabilities thereof and the interaction intention of the another environmental entity and the probability thereof at each of the future moments, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
Regarding Claim 16, modified Zhao discloses the limitations of Claim 10, and Zhao further discloses:
obtaining the driving trajectory of the vehicle at each moment based on the optimal interaction intention of the vehicle in the interaction scenario at each moment; and obtaining driving trajectories of the vehicle within time periods from the current moment to the plurality of future moments based on the driving trajectory of the vehicle at each moment. (see at least [0063] “By recording the driving behavior of the main vehicle along the path from the root node to the target leaf node in the first game tree and the driving status of the vehicles corresponding to the first node set at each moment in the order of the path, the target driving trajectory of the vehicle can be obtained. The target driving trajectory may include information such as angle, angular velocity, position, acceleration, and speed.”)
Regarding Claim 19, modified Zhao discloses the limitations of Claim 10, and Zhao further discloses:
A vehicle, comprising a computer device according to claim 10. (see at least [0021] “an autonomous driving vehicle is provided, comprising the electronic device”)
Claims 5, 9, 14, and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Zhao (CN 115675518), herein after referred to as Zhao, in view of Pronovost (US 20240174265), herein after referred to as Pronovost, Narayanan (US 20240174256), herein after referred to as Narayanan, Caldwell (US 20240092398), herein after referred to as Caldwell and Jafari Tafti (US 20190204842), herein after referred to as Jafari..
Regarding Claim 5, modified Zhao discloses the limitations of Claim 1, and Zhao further discloses:
obtaining the scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree (see at least [0060] “All leaf results simulated in the first game tree can be scored,”)
Zhao does not explicitly disclose:
using a reinforcement learning model trained based on first human driving behavior data,
wherein the first human driving behavior data is labeled with a human driving intention.
In the same field of endeavor, Jafari discloses:
using a reinforcement learning model trained based on first human driving behavior data, (see at least [0030] “The training method includes collecting training data for a desired human-like driving in different road scenarios and generating a search graph based on inputs to a trajectory planning system 100. ”)
wherein the first human driving behavior data is labeled with a human driving intention. wherein the second human driving behavior data is labeled with a human driving intention. (see at least [0038] “Once the search graph 306 is calculated, a reference trajectory 310 of the host vehicle 104 which was collected during a desired human-like driving or a computer simulated driving for navigating through the traffic scenario is provided. The reference trajectory 310 is superimposed over the search graph 306 and an optimal trajectory 312 in the search graph 306 which is closest to the reference trajectory 310 is found.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to use an interaction intention recognition model trained based on second human driving behavior data with the data labeled as such, as taught by Jafari to determine a trajectory similar to a human-likely selection [0038].
Regarding Claim 9, modified Zhao discloses the limitations of Claim 1, but Zhao does not explicitly disclose:
obtaining the probability of the interaction intention of each environmental entity in the environment based on the road features of the road and the entity features of the environmental entity in the environment using an interaction intention recognition model trained based on second human driving behavior data,
wherein the second human driving behavior data is labeled with a human driving intention.
In the same field of endeavor, Caldwell discloses:
obtaining the probability of the interaction intention of each environmental entity in the environment based on the road features of the road and the entity features of the environmental entity in the environment (see at least [Fig. 1] [0028] “the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).") (*See the vehicles identified as being in certain lanes within the environment, and the potential intents being constrained by their topological relationship to road features)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the probabilities of vehicle intents, and obtain a probability of the interaction intention of each environmental entity based on road features of the road and entity features of the environmental entity in the environment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
In the same field of endeavor, Jafari discloses
using an interaction intention recognition model trained based on second human driving behavior data, (see at least [0030] “The training method includes collecting training data for a desired human-like driving in different road scenarios and generating a search graph based on inputs to a trajectory planning system 100. ”)
wherein the second human driving behavior data is labeled with a human driving intention. (see at least [0038] “Once the search graph 306 is calculated, a reference trajectory 310 of the host vehicle 104 which was collected during a desired human-like driving or a computer simulated driving for navigating through the traffic scenario is provided. The reference trajectory 310 is superimposed over the search graph 306 and an optimal trajectory 312 in the search graph 306 which is closest to the reference trajectory 310 is found.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to use an interaction intention recognition model trained based on second human driving behavior data with the data labeled as such, as taught by Jafari to determine a trajectory similar to a human-likely selection [0038].
Regarding Claim 14, modified Zhao discloses the limitations of Claim 10, and Zhao further discloses:
obtaining the scenario value of each interaction intention in the interaction scenario at each moment in the scenario tree (see at least [0060] “All leaf results simulated in the first game tree can be scored,”)
Zhao does not explicitly disclose:
using a reinforcement learning model trained based on first human driving behavior data,
wherein the first human driving behavior data is labeled with a human driving intention.
In the same field of endeavor, Jafari discloses:
using a reinforcement learning model trained based on first human driving behavior data, (see at least [0030] “The training method includes collecting training data for a desired human-like driving in different road scenarios and generating a search graph based on inputs to a trajectory planning system 100. ”)
wherein the first human driving behavior data is labeled with a human driving intention. wherein the second human driving behavior data is labeled with a human driving intention. (see at least [0038] “Once the search graph 306 is calculated, a reference trajectory 310 of the host vehicle 104 which was collected during a desired human-like driving or a computer simulated driving for navigating through the traffic scenario is provided. The reference trajectory 310 is superimposed over the search graph 306 and an optimal trajectory 312 in the search graph 306 which is closest to the reference trajectory 310 is found.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to use an interaction intention recognition model trained based on second human driving behavior data with the data labeled as such, as taught by Jafari to determine a trajectory similar to a human-likely selection [0038].
Regarding Claim 18, modified Zhao discloses the limitations of Claim 10, but Zhao does not explicitly disclose:
obtaining the probability of the interaction intention of each environmental entity in the environment based on the road features of the road and the entity features of the environmental entity in the environment using an interaction intention recognition model trained based on second human driving behavior data,
wherein the second human driving behavior data is labeled with a human driving intention.
In the same field of endeavor, Caldwell discloses:
obtaining the probability of the interaction intention of each environmental entity in the environment based on the road features of the road and the entity features of the environmental entity in the environment (see at least [Fig. 1] [0028] “the vehicle computing device can determine a first confidence that the object 108 follows the first object trajectory 112 (e.g., a 70% confidence) and a second confidence that the objects 108 follows the second object trajectory 114 (e.g., a 30% confidence).") (*See the vehicles identified as being in certain lanes within the environment, and the potential intents being constrained by their topological relationship to road features)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to determine the probabilities of vehicle intents, and obtain a probability of the interaction intention of each environmental entity based on road features of the road and entity features of the environmental entity in the environment, as taught by Caldwell to determine what vehicle actions to take based on the probability of different intentions by the vehicle as surrounding actors [0023].
In the same field of endeavor, Jafari discloses
using an interaction intention recognition model trained based on second human driving behavior data, (see at least [0030] “The training method includes collecting training data for a desired human-like driving in different road scenarios and generating a search graph based on inputs to a trajectory planning system 100. ”)
wherein the second human driving behavior data is labeled with a human driving intention. (see at least [0038] “Once the search graph 306 is calculated, a reference trajectory 310 of the host vehicle 104 which was collected during a desired human-like driving or a computer simulated driving for navigating through the traffic scenario is provided. The reference trajectory 310 is superimposed over the search graph 306 and an optimal trajectory 312 in the search graph 306 which is closest to the reference trajectory 310 is found.”)
The above pieces of prior art are considered analogous as they both represent inventions in the vehicle control field. It would have been obvious to a person having ordinary skill in the art before the effective filing date of the claimed invention to have modified the teachings of Zhao to use an interaction intention recognition model trained based on second human driving behavior data with the data labeled as such, as taught by Jafari to determine a trajectory similar to a human-likely selection [0038].
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any 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 JACOB D UNDERBAKKE whose telephone number is (571)272-6657. The examiner can normally be reached Monday-Friday 8:00-5:00.
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.
/JACOB DANIEL UNDERBAKKE/Examiner, Art Unit 3662
/MAHMOUD S ISMAIL/Primary Examiner, Art Unit 3662 mittor