Non-conservative decision control method for autonomous vehicle with defense behavior

Abstract

The invention discloses a non-conservative decision control method for an automatic driving vehicle with a defense behavior, and the method comprises the steps: predicting the probability distribution of a future trajectory of a traffic participant through combining with the information of a vehicle and a surrounding traffic environment, and constructing a traffic environment space-time risk situation assessment model through combining with a spatial position relation. And meanwhile, environment uncertainty is integrated into an integrated decision control framework, a model prediction optimization control problem is constructed, and the vehicle is controlled to realize an automatic driving task by optimizing and solving a front wheel steering angle and longitudinal acceleration control instruction. According to the method, it can be ensured that the vehicle does not make over-excitation response when facing potential dangers, meanwhile, the driving quality cannot be reduced due to over-conservative, and safe and non-conservative driving of the automatic driving vehicle in the uncertain environment is achieved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving vehicle decision-making and control technology, and in particular to a non-conservative decision-making and control method for an autonomous driving vehicle with defensive behavior. Background Art

[0002] Autonomous driving has become a strategic direction for the development of the global automotive industry. Countries are accelerating the innovative development of autonomous driving vehicles to ensure that they stay ahead in the new round of scientific and technological revolution and industrial transformation. As technology continues to improve, automakers are focusing on the development of key technologies for L3-L5 autonomous driving to gradually achieve high-level autonomous driving functions.

[0003] Environmental perception, decision planning and motion control are the three key technologies of autonomous vehicles. Autonomous decision making and motion control can both be regarded as some type of optimization problems, and there is a strong coupling between them. Therefore, they can be integrated into a functional module, namely the decision control system. This system is the main embodiment of driving intelligence. However, in urban road scenes, the movement directions, speeds and modes of traffic participants (motor vehicles, non-motor vehicles and pedestrians) are different, making the situation faced by autonomous vehicles change rapidly. At the same time, there are many types and numbers of traffic participants in the environment, which affect each other and have diverse behaviors, making it difficult to accurately identify and predict the intentions and behaviors of each traffic participant. In addition, the decision control system of autonomous driving vehicles needs to consider many factors, including traffic regulations, road constraints, road conditions and the status of other traffic participants. In summary, the high dynamics, randomness and complexity of the urban road traffic environment put forward higher requirements for the decision control system of autonomous driving, and the design of the decision control system faces great challenges. The decision control strategies of autonomous driving vehicles currently demonstrated are usually too conservative and cautious, and sometimes show non-human driving behavior. This conservative behavior may reduce driving quality and may still pose safety risks when other road participants cannot predict such behavior. Summary of the invention

[0004] The present invention aims to solve one of the technical problems in the related art at least to a certain extent.

[0005] To this end, the present invention proposes a non-conservative decision-making and control method for autonomous driving vehicles with defensive behavior, which integrates environmental uncertainty information into an integrated decision-making and control architecture to ensure that the autonomous driving vehicle does not overreact when facing potential dangers, while not reducing the driving quality due to conservative operation, thereby achieving safe and non-conservative driving of autonomous driving vehicles in uncertain environments.

[0006] To achieve the above-mentioned object, the present invention proposes, on one hand, a non-conservative decision-making method for an autonomous driving vehicle with defensive behavior, comprising:

[0007] Predict the movement trajectory of traffic participants based on the vehicle and surrounding traffic environment information, model the environmental uncertainty information as a multimodal probability distribution, and build a spatiotemporal risk situation assessment model based on the spatial position relationship;

[0008] Based on the spatiotemporal risk situation assessment model, the optimal control strategy is selected from the two strategies of expected travel speed and expected stop speed set for each candidate static path; and the optimal path for autonomous driving is determined by evaluating the cost function constructed by the indicators of the candidate paths of the ego vehicle; and the constrained optimal control problem is constructed based on the model predictive control in combination with the ego vehicle dynamics model;

[0009] Based on the driving behavior and decision-making process of human drivers in interactive scenarios, environmental uncertainty information is integrated into the integrated decision-making and control architecture to optimize the front wheel angle and longitudinal acceleration control commands through the constrained optimal control problem, so as to control the vehicle to achieve the autonomous driving task.

[0010] The non-conservative decision-making method for an autonomous driving vehicle with defensive behavior according to an embodiment of the present invention may also have the following additional technical features:

[0011] In one embodiment of the present invention, the environmental uncertainty information includes: the movement direction, speed, acceleration of surrounding vehicles and / or pedestrians, and the intentions of surrounding vehicles and / or pedestrians.

[0012] In one embodiment of the present invention, predicting the movement trajectory of traffic participants based on the vehicle and surrounding traffic environment information to model the environmental uncertainty information as a multimodal probability distribution includes:

[0013] Defining first network input information; wherein the first network input information includes historical trajectory information and lane centerline information of traffic participants;

[0014] Inputting the second network input information into the fully connected layer, and constructing a long short-term memory network LSTM input tensor based on the first network input information and the second network input information to predict and output the multimodal distribution of the trajectory of the traffic participant in the future preset time domain; wherein the second network input information includes the vehicle state, static trajectory, road constraints, traffic participants and traffic light information;

[0015] A trajectory prediction model based on the vehicle's historical trajectory, driving intention and vehicle-to-vehicle motion interaction is established to output the multimodal probability distribution of the vehicle's trajectory in the future preset time domain according to the multimodal distribution and through an LSTM decoder.

[0016] In one embodiment of the present invention, the historical trajectory information of the participants is and lane centerline information L = {l j},in, is the trajectory information of the traffic participant numbered i in the historical time domain [tn,t]; l j =[x,y,j next ,I signal ,I inter ] represents the lane centerline information numbered j in the map, x, y are the longitudinal and lateral coordinate vectors of the lane centerline, j next is the number of the subsequent lane of the center line of the jth lane, I signal is the traffic light information of the lane, I inter Indicates whether the vehicle is in an intersection.

[0017] In one embodiment of the present invention, the optimal control strategy of the expected passing speed and the expected stopping speed set for each candidate static path is selected based on the spatiotemporal risk situation assessment model; and the optimal path for autonomous driving is determined by evaluating the cost function constructed by the indicators of the candidate paths of the vehicle, including:

[0018] Based on static information including at least road structure, speed limit, road surface markings, and traffic regulations, combined with human driving experience, a set of candidate paths without time information and an expected vehicle speed are designed, two strategies of expected passing speed and expected stopping speed are set for each candidate static path, and the two strategies are selected and switched based on the spatiotemporal risk situation assessment model;

[0019] In each control cycle, the optimal path for autonomous driving is determined by combining the multimodal distribution of the trajectories of traffic participants in a preset future time domain and evaluating the cost function constructed by three indicators: potential collision risk, traffic efficiency, and driving compliance of the candidate paths of the ego vehicle.

[0020] In one embodiment of the present invention, combining the vehicle dynamics model and constructing a constrained optimal control problem based on model predictive control includes:

[0021] Combined with the ego-vehicle dynamics model, with traffic participants as the main constraints, and based on road edge constraints and traffic light restrictions, a constrained optimal control problem is constructed based on model predictive control MPC; including:

[0022] The mathematical expression of the optimal control problem is described by finite-horizon predictive control that tracks the i-th path:

[0023]

[0024] satisfy:

[0025]

[0026] And subject to the constraints of traffic participants:

[0027] x self (τ)-x surr,i (τ)≥d self ,τ∈[t,t+T]

[0028] Road edge constraints:

[0029] x self (τ)-x road (τ)≥δ road ,τ∈[t,t+T]

[0030] Traffic light constraints:

[0031] x self (τ)∈free,ifgreen,τ∈[t,t+T]

[0032] x self (τ)≤L stop ,if red,τ∈[t,t+T]

[0033] Among them, t is the current time, τ is the virtual time of the prediction time domain, T is the length of the prediction time domain, is the desired tracking position, is the expected driving speed, x self is the state of the vehicle, u self is the vehicle control quantity, x surr (τ) is the state of the surrounding traffic participants, including the constraint relationship between C traffic participants and the vehicle, x road Refers to the drivable area enclosed by the edge of the road, d self is the safe distance of the surrounding vehicle, δ road is the safe distance from the edge of the road, L stop It is the distance from the stop line at the road intersection, R represents a red light and G represents a green light.

[0034] In one embodiment of the present invention, based on the driving behavior and decision-making process of a human driver in an interactive scenario, environmental uncertainty information is integrated into an integrated decision-making control architecture to optimize the front wheel steering angle and longitudinal acceleration control instructions through the constrained optimal control problem to control the vehicle to achieve the autonomous driving task, including:

[0035] By characterizing the contribution of different possible future probability distributions to the cost function, the uncertainty problem is structured as a model prediction optimization problem.

[0036] Through scene data, fully connected layers, and LSTM networks, the associated vehicles r are selected based on the multimodal distribution of the trajectories of traffic participants in the future preset time domain and the static path set of the autonomous driving vehicle. i and potential collision area ci , for each collision area c i , set a safety line k and stop line k ;

[0037] The time from the current position of the vehicle to the potential collision area is defined as TTC, and the constraint-modified TTC criterion is introduced; when evaluating the risk situation of the traffic environment, the Bayesian network is used to evaluate the potential risks in the traffic scene;

[0038] A shared safety set and a preview safety set are designed in the MPC prediction domain: in the shared safety set, the uncertainty of the traffic environment is not considered; in the preview safety set, the probability distribution of potential threats in the traffic environment is combined, and the probability constraints are integrated into the MPC optimization problem;

[0039] According to the real-time environmental information, the probability model is updated and the MPC optimization problem is re-solved to achieve dynamic processing of environmental uncertainty: the MPC prediction time domain is divided into the shared safety set and the preview safety set, a constrained multi-objective optimization control problem is constructed, and environmental uncertainty factors are uniformly integrated into the integrated decision-making and control architecture;

[0040] The shared action sequence and the bifurcated action sequence of the front wheel steering angle and the longitudinal acceleration are optimized and determined, and the optimized control instructions are input to the vehicle to realize the vehicle's autonomous driving task.

[0041] In one embodiment of the present invention, the time from the current position of the vehicle to the potential collision area is defined as TTC, and a constraint-modified TTC criterion is introduced, and the formula is as follows:

[0042]

[0043] in, The revised TTC, is the self-car and the surrounding car r i The distance is the k-th surrounding vehicle r in the MPC prediction domain at time t i The driving speed is ξ, and ξ is the set safety distance.

[0044] In one embodiment of the present invention, when evaluating the risk situation of the traffic environment, a Bayesian network is used to evaluate the potential risks in the traffic scene, including:

[0045] For the associated vehicle r i, define a random variable z to characterize the three risk levels of danger, warning and safety associated with TTC; comprehensively consider driving safety and vehicle tracking performance, define threshold values ​​associated with potential risk levels, and construct a likelihood function of TTC to parameterize scenario risks; assume that the prior probability density function P(z) of the potential threat level of the associated vehicle follows a uniform distribution, then the probability distribution of the potential threat is determined by the Bayesian theorem, as follows:

[0046]

[0047] in, is the kth step of the MPC prediction domain at time t and the surrounding vehicles r i The risk level, represent The risk level under the condition is The probability of The collision time under the risk level z condition is The probability of N Z Represents the possible risk level, namely danger, warning and safety, The collision time for each risk condition probability.

[0048] In one embodiment of the present invention, in the preview safety set, a probability constraint is constructed in combination with the probability distribution of potential threats in the traffic environment. ε is the set probability constraint threshold, and the probability constraint is finally integrated into the MPC optimization problem.

[0049] The non-conservative decision-making and control method for an autonomous driving vehicle with defensive behavior in an embodiment of the present invention combines the information of the vehicle and the surrounding traffic environment, and uses probability distribution to represent the environmental uncertainty information; predicts the multimodal distribution of the future motion trajectories of traffic participants, and constructs a spatiotemporal risk situation assessment model for the traffic environment in combination with the spatial position relationship. At the same time, environmental uncertainty is integrated into the integrated decision-making and control architecture, and a model predicts the optimization control problem. By optimizing and solving the front wheel steering angle and longitudinal acceleration control instructions, the vehicle is controlled to achieve the autonomous driving task. It can ensure that the vehicle does not overreact when facing potential dangers, and at the same time, the driving quality will not be reduced due to excessive conservatism, thereby achieving safe and non-conservative driving of autonomous driving vehicles in uncertain environments.

[0050] Additional aspects and advantages of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0052] Figure 1 is a flow chart of a non-conservative decision-making method for an autonomous driving vehicle with defensive behavior according to an embodiment of the present invention;

[0053] Figure 2 Schematic diagram of a non-conservative decision-making method with defensive behavior according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0055] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0056] The following describes a non-conservative decision-making method for an autonomous driving vehicle with defensive behavior proposed according to an embodiment of the present invention with reference to the accompanying drawings.

[0057] Figure 1 is a flow chart of a non-conservative decision-making method for an autonomous driving vehicle with defensive behavior according to an embodiment of the present invention. Figure 1 As shown, including:

[0058] S1, predict the movement trajectory of traffic participants based on the information of the vehicle and the surrounding traffic environment, so as to model the environmental uncertainty information as a multimodal probability distribution, and build a spatiotemporal risk situation assessment model in combination with the spatial position relationship.

[0059] It is understandable that this step S1 designs a spatiotemporal risk situation assessment method that takes into account environmental uncertainty, and models the uncertainty in the environment as a probability distribution to better understand possible situations and events. The environmental uncertainty information may include: the movement direction, speed, acceleration of surrounding vehicles and / or pedestrians, and the intentions of surrounding vehicles and / or pedestrians. This step S1 may specifically include:

[0060] S11, comprehensively considers the historical trajectory information and possible future path information of traffic participants, combines the map topology relationship, predicts the multimodal distribution of future movement trajectories of traffic participants, and models the uncertainty in the environment as a probability distribution;

[0061] S12, by quantifying uncertainty and combining spatial position relationships, a spatiotemporal risk situation prediction model is constructed to evaluate the risks associated with each decision, select the optimal control strategy, and improve the decision-making and control performance and reliability in complex environments.

[0062] Specifically, the first network input information is defined, including the historical trajectory information of traffic participants and lane centerline information L = {l j},in is the trajectory information of the traffic participant numbered i in the historical time domain [tn,t]; l j =[x,y,j next ,I signal ,I inter ] represents the lane centerline information numbered j in the map, x, y are the longitudinal and lateral coordinate vectors of the lane centerline, j next is the number of the subsequent lane of the center line of the jth lane, I signal is the traffic light information of the lane (0: non-red light, 1: red light), I inter Indicates whether the vehicle is in an intersection (0: not in an intersection, 1: in an intersection); at the same time, the acceleration and speed information of the historical trajectory and the static road facilities are considered to construct an environmental uncertainty function.

[0063] The second network input information: vehicle status, static trajectory, road constraints, traffic participants and traffic light information are input into the fully connected layer, and the Long Short-Term Memory (LSTM) network input tensor is constructed based on the above information to predict the multimodal distribution of the trajectory of traffic participants in the future time domain [t, t+T]. inter The information is integrated into the interaction layer of the LSTM network, which can simplify the network structure of the LSTM in simple scenarios. When the vehicle is in an intersection, considering the interaction diversity and uncertainty of the workshop, all feasible lane centerlines and subsequent lane centerlines are screened out from the map lane centerline information, and the lane centerlines with topological relationships are spliced ​​to form a set of feasible paths. For each feasible path, its longitudinal and lateral uncertainty parameters are calculated respectively. When predicting trajectories, high-precision digital maps and static candidate path sets of autonomous driving vehicles are combined to screen threatening vehicles. Using natural driving data and "long tail" data, combined with vehicle motion status and historical trajectory information, a driving intention recognition and vehicle trajectory prediction model is constructed based on the LSTM network. Secondly, a pooling strategy is designed to integrate the interaction information of the workshop into the LSTM network, and learn to characterize the interaction influence relationship between vehicles. Finally, a trajectory prediction model that comprehensively considers the vehicle's historical trajectory, driving intention, and workshop motion interaction is established, and the multimodal probability distribution of the vehicle's future trajectory, that is, the uncertainty set of the predicted trajectory, is output through the LSTM decoder;

[0064] Furthermore, when evaluating the spatiotemporal risk situation of the traffic environment, the autonomous vehicle is represented by three circles, the surrounding vehicles are represented by two circles, and pedestrians and cyclists are represented by one circle. A traffic risk penalty function is constructed based on the center distance between the vehicle and other participants, and incorporated into the safety constraints of the MPC to ensure that the vehicle can drive safely in various traffic scenarios.

[0065] S2, based on the spatiotemporal risk situation assessment model, selects the optimal control strategy of the expected passing speed and expected stopping speed set for each candidate static path; and determines the optimal path for autonomous driving by constructing a cost function through evaluating the indicators of the candidate paths of the ego vehicle; and constructs a constrained optimal control problem based on the model predictive control in combination with the ego vehicle dynamics model.

[0066] S2 of the embodiment of the present invention designs a non-conservative decision-making control method for an autonomous driving vehicle with defensive behavior, which integrates autonomous decision-making and motion control into a unified framework, including two key submodules: static path planning and dynamic optimal tracking. Specifically, step S2 includes:

[0067] S21, the static path planning module uses static information such as road structure, speed limit, road signs, and traffic regulations, combined with human driving experience to design a set of candidate paths without time information and the expected speed, to improve the real-time performance of local path planning. This module sets the expected speed and expected stopping speed for each candidate static path, and these two strategies will be selected and switched during the strategy application process; the static path planning module does not select the optimal trajectory, nor does it consider any information of dynamic traffic participants, so that it has the characteristics of being pre-stored in the map;

[0068] S22. The dynamic optimal tracking module is the core of the integrated decision-making and control framework. It reshapes the autonomous driving decision-making and control task and integrates it into an optimal control problem, which only includes one performance indicator and one dynamic system. It solves a decision-making and control strategy and improves the decision-making and control level. In each control cycle, it combines the future trajectory distribution of traffic participants and determines the optimal path for autonomous driving by evaluating the cost function constructed by three indicators: potential collision risk, traffic efficiency and driving compliance of the candidate paths of the vehicle.

[0069] S23. Based on the above, combined with the vehicle dynamics model, taking traffic participants as the main constraints, and considering road edge constraints and traffic light restrictions, a constrained optimal control problem is constructed based on MPC. The following will take the finite time domain predictive control of tracking the i-th path as an example to describe the mathematical expression of the optimal control problem:

[0070]

[0071] satisfy:

[0072]

[0073] And it is subject to the constraints of traffic participants (no collision with C surrounding vehicles in the prediction time domain):

[0074] x self (τ)-x surr,i (τ)≥d self ,τ∈[t,t+T]

[0075] Road edge constraints:

[0076] x self (τ)-x road (τ)≥δ road ,τ∈[t,t+T]

[0077] Traffic light constraints:

[0078] x self (τ)∈free,if green,τ∈[t,t+T]

[0079] x self (τ)≤L stop ,if red,τ∈[t,t+T]

[0080] Among them, t is the current time, τ is the virtual time of the prediction time domain, T is the length of the prediction time domain, is the desired tracking position, is the expected driving speed, x self is the state of the vehicle, u self is the vehicle control quantity, x surr (τ) is the state of the surrounding traffic participants, including the constraint relationship between C traffic participants and the vehicle, x road Refers to the drivable area enclosed by the edge of the road, d self is the safe distance of the surrounding vehicle, δ road is the safe distance from the edge of the road, L stop is the distance to the stop line at the road intersection, R represents the red light, and G represents the green light. When the light is green, the driving state is not restricted by the traffic light; when the light is red, the vehicle position within the predicted time domain cannot exceed the stop line.

[0081] S3, based on the driving behavior and decision-making process of human drivers in interactive scenarios, integrates environmental uncertainty information into the integrated decision-making and control architecture to optimize the front wheel steering angle and longitudinal acceleration control instructions through the constrained optimal control problem, and controls the vehicle to achieve the autonomous driving task.

[0082] Step S3 of the embodiment of the present invention is used to combine the driving behavior and decision-making process of human drivers in interactive scenarios and integrate environmental uncertainty into the integrated decision-making control architecture, such as Figure 2 As shown, it includes the following sub-steps:

[0083] S31. By characterizing the contribution of different probability distributions of future possibilities to the cost function, the uncertainty problem is constructed as a model prediction optimization problem, and then a non-conservative decision-making method for defensive behavior is designed to deal with various uncertainties in the urban road environment.

[0084] S32, through the scene data, the fully connected layer and the LSTM network, considering the multimodal distribution of the future trajectories of traffic participants and the static path set of the autonomous driving vehicle, select the associated vehicle r i and potential collision area c i , for each collision area c i , set a safety line k and stop line k These safety lines and stop lines form a set, and the integrated decision-making and control system uses these sets to adopt corresponding maneuvering strategies to ensure driving safety and avoid excessive conservatism.

[0085] S33. Define the time from the current position of the vehicle to the potential collision area as TTC, introduce the constraint-corrected TTC criterion, and the specific formula is as follows:

[0086]

[0087] in, The revised TTC, is the self-car and the surrounding car r i The distance is the k-th surrounding vehicle r in the MPC prediction domain at time t i The driving speed is ξ, and ξ is the set safety distance.

[0088] In the risk assessment of the traffic environment, in order to describe the uncertainty of the environment, the Bayesian network is used to evaluate the potential risks in the traffic scene. i , define a random variable z to characterize the three risk levels of danger, warning and safety associated with TTC; comprehensively consider driving safety and vehicle tracking performance, define threshold values ​​associated with potential risk levels, and construct a likelihood function of TTC to parameterize scenario risks; assuming that the prior probability density function P(z) of the potential threat level of the associated vehicle follows a uniform distribution, the probability distribution of the potential threat can be determined by Bayes’ theorem, as follows:

[0089]

[0090] in, is the kth step of the MPC prediction domain at time t and the surrounding vehicles r i The risk level, represent The risk level under the condition is The probability of The collision time under the risk level z condition is The probability of N Z Represents the possible risk level, namely danger, warning and safety, The collision time for each risk condition probability.

[0091] On this basis, probabilistic constraints are constructed to incorporate potential risks into the constraints of MPC to deal with the uncertainty of the system. In order to cope with various changes that may occur in the future, autonomous vehicles need to make decisions and control their driving behaviors under different events. At this time, if MPC optimizes and solves an open-loop control sequence that satisfies all constraints, the decision-making behavior may be too conservative. To solve this problem, the corresponding front wheel steering angle and longitudinal acceleration control action sequence will be optimized and decided based on the multimodal distribution of the predicted trajectories of traffic participants. However, in the optimization framework of the rolling time domain, autonomous vehicles usually execute the first action in the optimization sequence. Therefore, the short-term control instructions of the vehicle in the prediction time domain should be consistent, because the action that the vehicle needs to perform at the next moment must be certain.

[0092] S34. When designing an MPC control system, a shared safety set and a preview safety set are designed in the prediction time domain. In the shared safety set, the uncertainty of the traffic environment will not be considered to avoid the direct impact of future potential risks on the current decision-making results; in the preview safety set, the probability distribution of potential threats in the traffic environment is combined to construct a probability constraint. ε is the set probability constraint threshold, and the probability constraint is finally integrated into the MPC optimization problem.

[0093] S35. Based on real-time environmental information, the probability constraint model is updated and the MPC optimization problem is re-solved to achieve dynamic processing of environmental uncertainty; this can not only ensure the stability of the current decision-making control, but also take future uncertainties into account. In specific implementation, the MPC prediction domain is divided into two sets: a shared safety set (the first t1 steps in the prediction domain, only considering safety factors, not environmental uncertainties) and a preview safety set (considering the multimodal distribution of the prediction trajectory), and a constrained multi-objective optimization control problem is constructed to integrate environmental uncertainty factors into the integrated decision-making control architecture.

[0094] S36. Optimize and determine the shared action sequence and bifurcated action sequence of the front wheel turning angle and longitudinal acceleration, and input the first action of the control sequence to the vehicle verification module to realize the vehicle's autonomous driving task. Finally, determine whether the vehicle has completed the autonomous driving task. If the autonomous driving task is completed, the algorithm terminates; if the autonomous driving task is not completed, re-acquire the information of the vehicle and the surrounding traffic environment, and repeat the above steps until the autonomous driving task is completed. This design will not overreact to low-probability potential collision risks, and the final decision-making control strategy will not be formulated immediately, but will be formulated when necessary, so that the autonomous driving vehicle exhibits non-conservative driving characteristics with defensive behavior. This design is intended to enable autonomous driving vehicles to calmly respond to potential threats and ensure driving safety, while not being too conservative and reducing driving quality.

[0095] The non-conservative decision-making and control method for an autonomous driving vehicle with defensive behavior according to an embodiment of the present invention fully utilizes intelligent network information, comprehensively considers the uncertainty in the traffic environment, quantifies the uncertainty in the environment as a probability distribution, and designs a non-conservative decision-making and control method for an autonomous driving vehicle with defensive behavior, so that the vehicle will not overreact when facing potential dangers, and at the same time will not reduce the driving quality due to being too conservative, thereby achieving safe and non-conservative driving of autonomous driving vehicles in uncertain environments.

[0096] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0097] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

Claims

1. A non-conservative decision-making method for an autonomous driving vehicle with defensive behavior, characterized in that: include: Predict the movement trajectory of traffic participants based on the vehicle and surrounding traffic environment information, model the environmental uncertainty information as a multimodal probability distribution, and build a spatiotemporal risk situation assessment model based on the spatial position relationship; Selecting the optimal control strategy of the two strategies of expected passing speed and expected stopping speed set for each candidate static path based on the spatiotemporal risk situation assessment model; and determining the best path for autonomous driving by constructing a cost function through evaluating the indicators of candidate paths for the ego vehicle; and constructing a constrained optimal control problem based on model predictive control in combination with the ego vehicle dynamics model; Based on the driving behavior and decision-making process of human drivers in interactive scenarios, environmental uncertainty information is integrated into the integrated decision-making and control architecture to optimize the front wheel angle and longitudinal acceleration control commands through the constrained optimal control problem, so as to control the vehicle to achieve the autonomous driving task.

2. The method according to claim 1, characterized in that The environmental uncertainty information includes: the movement direction, speed, acceleration of surrounding vehicles and / or pedestrians, and the intentions of surrounding vehicles and / or pedestrians.

3. The method according to claim 1, characterized in that The method of predicting the movement trajectory of traffic participants based on the vehicle and surrounding traffic environment information to model the environmental uncertainty information as a multimodal probability distribution includes: Defining first network input information; wherein the first network input information includes historical trajectory information and lane centerline information of traffic participants; Inputting the second network input information into the fully connected layer, and constructing a long short-term memory network LSTM input tensor based on the first network input information and the second network input information to predict and output the multimodal distribution of the trajectory of the traffic participant in the future preset time domain; wherein the second network input information includes the vehicle state, static trajectory, road constraints, traffic participants and traffic light information; A trajectory prediction model based on the vehicle's historical trajectory, driving intention and vehicle-to-vehicle motion interaction is established to output the multimodal probability distribution of the vehicle's trajectory in the future preset time domain according to the multimodal distribution and through an LSTM decoder.

4. The method according to claim 3, characterized in that Historical trajectory information of traffic participants and lane centerline information L = {l j }in, is the trajectory information of the traffic participant numbered i in the historical time domain [tn,t]; l j =[x,y,j next ,I signal ,I inter ] represents the lane centerline information numbered j in the map, x, y are the longitudinal and lateral coordinate vectors of the lane centerline, j next is the number of the subsequent lane of the center line of the jth lane, I signal is the traffic light information of the lane, I inter Indicates whether the vehicle is in an intersection.

5. The method according to claim 4, characterized in that Selecting the optimal control strategy of the two strategies of expected passing speed and expected stopping speed set for each candidate static path based on the spatiotemporal risk situation assessment model; And the cost function constructed by evaluating the indicators of the candidate paths of the ego vehicle to determine the best path for autonomous driving, including: Based on static information including at least road structure, speed limit, road surface markings, and traffic regulations, combined with human driving experience, a set of candidate paths without time information and an expected vehicle speed are designed, two strategies of expected passing speed and expected stopping speed are set for each candidate static path, and the two strategies are selected and switched based on the spatiotemporal risk situation assessment model; In each control cycle, the optimal path for autonomous driving is determined by combining the multimodal distribution of the trajectories of traffic participants in a preset future time domain and evaluating the cost function constructed by three indicators: potential collision risk, traffic efficiency, and driving compliance of the candidate paths of the ego vehicle.

6. The method according to claim 5, characterized in that The constrained optimal control problem is constructed by combining the vehicle dynamics model and based on model predictive control, including: Combined with the ego-vehicle dynamics model, with traffic participants as the main constraints, and based on road edge constraints and traffic light restrictions, a constrained optimal control problem is constructed based on model predictive control MPC; including: The mathematical expression of the optimal control problem is described by finite-horizon predictive control that tracks the i-th path: satisfy: And subject to the constraints of traffic participants: x self (τ)-x surr,i (τ)≥d self ,τ∈[t,t+T] Road edge constraints: x self (τ)-x road (τ)≥δ road ,τ∈[t,t+T] Traffic light constraints: x self (τ)∈free,if green,τ∈[t,t+T] x self (τ)≤L stop ,if red,τ∈[t,t+T] Among them, t is the current time, τ is the virtual time of the prediction time domain, T is the length of the prediction time domain, is the desired tracking position, is the expected driving speed, x self is the state of the vehicle, u self is the vehicle control quantity, x surr (τ) is the state of the surrounding traffic participants, including the constraint relationship between C traffic participants and the vehicle, x road Refers to the drivable area enclosed by the edge of the road, d self is the safe distance of the surrounding vehicle, δ road is the safe distance from the edge of the road, L stop It is the distance from the stop line at the road intersection, R represents a red light and G represents a green light.

7. The method according to claim 6, characterized in that Based on the driving behavior and decision-making process of human drivers in interactive scenarios, environmental uncertainty information is integrated into the integrated decision-making control architecture to optimize the front wheel angle and longitudinal acceleration control instructions through the constrained optimal control problem, and control the vehicle to achieve the autonomous driving task, including: By characterizing the contribution of different possible future probability distributions to the cost function, the uncertainty problem is structured as a model prediction optimization problem. Through scene data, fully connected layers, and LSTM networks, the associated vehicles r are selected based on the multimodal distribution of the trajectories of traffic participants in the future preset time domain and the static path set of the autonomous driving vehicle. i and potential collision area c i , for each collision area c i , set a safety line k and stop line k ; The time from the current position of the vehicle to the potential collision area is defined as TTC, and the constraint-modified TTC criterion is introduced; when evaluating the risk situation of the traffic environment, the Bayesian network is used to evaluate the potential risks in the traffic scene; A shared safety set and a preview safety set are designed in the MPC prediction domain: in the shared safety set, the uncertainty of the traffic environment is not considered; in the preview safety set, the probability distribution of potential threats in the traffic environment is combined, and the probability constraints are integrated into the MPC optimization problem; According to the real-time environmental information, the probability model is updated and the MPC optimization problem is re-solved to achieve dynamic processing of environmental uncertainty: the MPC prediction time domain is divided into the shared safety set and the preview safety set, a constrained multi-objective optimization control problem is constructed, and environmental uncertainty factors are uniformly integrated into the integrated decision-making and control architecture; The shared action sequence and the bifurcated action sequence of the front wheel steering angle and the longitudinal acceleration are optimized and determined, and the optimized control instructions are input to the vehicle to realize the vehicle's autonomous driving task.

8. The method according to claim 7, characterized in that The time from the current position of the vehicle to the potential collision area is defined as TTC, and the constraint-corrected TTC criterion is introduced. The formula is as follows: in, The revised TTC, is the self-car and the surrounding car r i The distance is the k-th surrounding vehicle r in the MPC prediction domain at time t i The driving speed is ξ, and ξ is the set safety distance.

9. The method according to claim 8, characterized in that When assessing the risk situation of the traffic environment, a Bayesian network is used to evaluate the potential risks in the traffic scenario, including: For the associated vehicle r i , define a random variable z to characterize the three risk levels of danger, warning and safety associated with TTC; comprehensively consider driving safety and vehicle tracking performance, define threshold values ​​associated with potential risk levels, and construct a likelihood function of TTC to parameterize scenario risks; assume that the prior probability density function P(z) of the potential threat level of the associated vehicle follows a uniform distribution, then the probability distribution of the potential threat is determined by the Bayesian theorem, as follows: in, is the kth step of the MPC prediction domain at time t and the surrounding vehicles r i The risk level, represent The risk level under the condition is The probability of The collision time under the risk level z condition is The probability of N Z Represents the possible risk level, namely danger, warning and safety, The collision time for each risk condition probability.

10. The method according to claim 9, characterized in that In the preview safety set, combined with the probability distribution of potential threats in the traffic environment, a probability constraint is constructed ε is the set probability constraint threshold, and the probability constraint is finally integrated into the MPC optimization problem.

Images