A static path optimization method and device for integrated decision-making control of autonomous vehicles

Abstract

The present application relates to a static path optimization method and device for integrated decision-making and control of an autonomous vehicle, wherein the method includes: calculating the safety index, compliance index, patency index, economy index, and comfort index of each static path based on a set of static paths; calculating the comprehensive evaluation index of each static path based on the safety index, compliance index, patency index, economy index, and comfort index of each static path and the corresponding priority and weight; and selecting the optimal static path that meets preset conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path. This solves the problem in the related art that the integrated decision-making and dynamic tracking control integrates decision-making, planning, and control, resulting in high functional integration, complex algorithm design, large computational scale, and poor real-time performance.

Description

Technical Field

[0001] The present application relates to the field of intelligent automobile driving technology, and in particular to a static path optimization method and device for integrated decision-making and control of an autonomous driving vehicle. Background Art

[0002] Integrated decision-making and control for high-level autonomous driving integrates autonomous driving decision-making and control tasks into a constrained optimal control problem, which can improve the overall intelligence, adaptability and safety of autonomous driving vehicles.

[0003] The relevant technologies mainly include two modules: static path planning and dynamic tracking control. The static path planning module generates a set of trackable alternative paths based on static road environment information, and the dynamic tracking control constructs the path tracking problem into a constrained optimal control problem to achieve reference path optimization and vehicle tracking and obstacle avoidance.

[0004] However, in related technologies, since the integrated decision-making and dynamic tracking control integrates decision-making, planning and control into one, there are problems such as high functional integration, complex algorithm design, large calculation scale and poor real-time performance, which need to be solved urgently. Summary of the Invention

[0005] The present application provides a static path optimization method and device for integrated decision-making and control of an autonomous vehicle to solve the problems in related technologies such as high functional integration, complex algorithm design, large computational scale, and poor real-time performance due to the integration of decision-making, planning, and control in the integrated decision-making and dynamic tracking control.

[0006] The first aspect of the present application is an embodiment that provides a static path optimization method for integrated decision-making and control of an autonomous driving vehicle, comprising the following steps: based on a static path set, respectively calculating the safety index, compliance index, patency index, economy index and comfort index of each static path; calculating the comprehensive evaluation index of each static path according to the safety index, compliance index, patency index, economy index and comfort index of each static path and the corresponding priority and weight; and selecting the optimal static path that meets preset conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path.

[0007] Optionally, in one embodiment of the present application,

[0008] The calculation formula of the safety index is:

[0009]

[0010] in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient;

[0011] The calculation formula of the compliance indicator is:

[0012]

[0013] in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to the lane where the static path τ is located;

[0014] The calculation formula of the patency index is:

[0015]

[0016] in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight is set according to the traffic efficiency requirements for the distance and speed of the preceding vehicle, and there is ω d +ω v =1;

[0017] The calculation formula of the economic index is:

[0018]

[0019] in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t;

[0020] The calculation formula of the comfort index is:

[0021]

[0022] in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

[0023] Optionally, in one embodiment of the present application, the calculation formula of the comprehensive evaluation index is:

[0024]

[0025] in, represents the comprehensive evaluation index of the static path τ at the current moment t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

[0026] Optionally, in one embodiment of the present application, selecting the optimal static path that meets preset conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path includes: selecting the optimal static path in a manner that maximizes the comprehensive evaluation index; and setting the update frequency of the optimal static path according to the change information of the comprehensive evaluation index.

[0027] Optionally, in one embodiment of the present application, the update frequency is:

[0028]

[0029] in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

[0030] The second aspect of the present application provides a static path optimization device for integrated decision-making and control of an autonomous driving vehicle, including: a first calculation module for calculating the safety index, compliance index, patency index, economy index and comfort index of each static path based on a static path set; a second calculation module for calculating the comprehensive evaluation index of each static path based on the safety index, compliance index, patency index, economy index and comfort index of each static path and the corresponding priority and weight; and a selection module for selecting the optimal static path that meets preset conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path.

[0031] Optionally, in one embodiment of the present application,

[0032] The calculation formula of the safety index is:

[0033]

[0034] in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient;

[0035] The calculation formula of the compliance indicator is:

[0036]

[0037] in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to the lane where the static path τ is located;

[0038] The calculation formula of the patency index is:

[0039]

[0040] in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight is set according to the traffic efficiency requirements for the distance and speed of the preceding vehicle, and there is ω d +ω v =1;

[0041] The calculation formula of the economic index is:

[0042]

[0043] in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t;

[0044] The calculation formula of the comfort index is:

[0045]

[0046] in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

[0047] Optionally, in one embodiment of the present application, the calculation formula of the comprehensive evaluation index is:

[0048]

[0049] in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

[0050] Optionally, in one embodiment of the present application, the selection module includes:

[0051] A selection unit, configured to select the optimal static path in a manner of maximizing a comprehensive evaluation index;

[0052] A setting unit is used to set the update frequency of the optimal static path according to the change information of the comprehensive evaluation index.

[0053] Optionally, in one embodiment of the present application, the update frequency is:

[0054]

[0055] in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

[0056] The third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement a static path optimization method for integrated decision-making of an autonomous driving vehicle as described in the above embodiment.

[0057] The fourth aspect of the present application provides a computer-readable storage medium, which stores a computer program. When the program is executed by a processor, it implements the above-mentioned static path optimization method for integrated decision-making and control of an autonomous driving vehicle.

[0058] The embodiment of the present application evaluates static paths using five evaluation indicators, namely safety, compliance, patency, economy, and comfort, to closely follow the decision-making process of human drivers and improve the rationality and social compatibility of autonomous vehicle decisions. A comprehensive evaluation indicator is obtained by weighted fusion of the five evaluation indicators, which helps to achieve personalized decision-making for autonomous vehicles and meet the driving characteristics of different drivers / passengers. The current optimal static path is selected based on the size and change of the comprehensive evaluation indicator, avoiding the linear increase in the computational scale of the dynamic tracking control function with the number of static trajectories, thereby improving the overall real-time performance of the integrated decision-making control. This solves the problem in related technologies that the integrated decision-making dynamic tracking control integrates decision-making, planning, and control, resulting in high functional integration, complex algorithm design, large computational scale, and poor real-time performance.

[0059] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0061] Figure 1 This is a flowchart of a static path optimization method for integrated decision-making and control of an autonomous driving vehicle provided according to an embodiment of the present application;

[0062] Figure 2 A schematic diagram of lanes for illustrating a static path at an intersection according to a static path optimization method for integrated decision-making and control of an autonomous vehicle according to one embodiment of the present application;

[0063] Figure 3 This is a flowchart of a static path optimization method for integrated decision-making and control of an autonomous driving vehicle according to one embodiment of the present application;

[0064] Figure 4This is a schematic structural diagram of a static path optimization device for integrated decision-making and control of an autonomous vehicle according to an embodiment of the present application;

[0065] Figure 5 A schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0066] The following describes in detail embodiments of the present application, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0067] The following describes, with reference to the accompanying drawings, a static path optimization method and apparatus for integrated decision-making control of an autonomous vehicle according to an embodiment of the present application. In response to the related art mentioned in the background art, which integrates decision-making, planning, and control into one, resulting in high functional integration, complex algorithm design, large computational scale, and poor real-time performance, the present application provides a static path optimization method for integrated decision-making control of an autonomous vehicle. In this method, a static path is evaluated using five evaluation indicators, including safety, compliance, patency, economy, and comfort, to closely mimic the decision-making process of human drivers and improve the rationality and social compatibility of autonomous vehicle decisions. A comprehensive evaluation indicator is obtained by weighted fusion of the five evaluation indicators, facilitating personalized decision-making for autonomous vehicles and meeting the driving characteristics of different drivers / passengers. The optimal static path is selected based on the magnitude and variation of the comprehensive evaluation indicator, avoiding the linear increase in the computational scale of the dynamic tracking control function with the number of static trajectories, thereby improving the overall real-time performance of the integrated decision-making control. This solves the problems in related technologies, such as high functional integration, complex algorithm design, large calculation scale and poor real-time performance, caused by the integrated decision-making dynamic tracking control integrating decision-making, planning and control into one.

[0068] Specifically, Figure 1 A flowchart of a static path optimization method for integrated decision-making and control of an autonomous vehicle provided in an embodiment of the present application.

[0069] like Figure 1 As shown, the static path optimization method for integrated decision-making control of an autonomous driving vehicle includes the following steps:

[0070] In step S101 , based on the static path set, the safety index, compliance index, patency index, economy index and comfort index of each static path are calculated respectively.

[0071] It can be understood that the static path set in the embodiment of the present application is a set of vehicle drivable paths generated based on static information of the road (such as road shape, stop lines, traffic light information, etc.).

[0072] During the actual implementation process, the embodiment of the present application can calculate the safety index, compliance index, smoothness index, economy index and comfort index of each static path based on the static path set, so as to evaluate the static path with five-dimensional evaluation indicators such as safety index, compliance index, smoothness index, economy index and comfort index, which is close to the decision-making process of human drivers and improves the rationality of decision-making and social compatibility of autonomous driving vehicles.

[0073] Optionally, in one embodiment of the present application,

[0074] The calculation formula of the safety index is:

[0075]

[0076] in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient;

[0077] The calculation formula for the compliance index is:

[0078]

[0079] in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to (or continues driving in) the lane where the static path τ is located;

[0080] The calculation formula of patency index is:

[0081]

[0082] in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight can be set according to the requirements of traffic efficiency on the distance and speed of the preceding vehicle, and there is ω d +ω v =1;

[0083] The calculation formula of economic index is:

[0084]

[0085] in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t;

[0086] The calculation formula of comfort index is:

[0087]

[0088] in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

[0089] In the actual implementation process, the embodiment of the present application can calculate the potential risk of the vehicle changing lanes from the current lane to (or continuing to drive in) the lane where the alternative static path is located as the safety index of the static path, wherein the lane where the alternative path is located at the intersection refers to the lane pointed to by the static path, such as Figure 2 As shown; the potential risks in the embodiment of the present application may include at least one of the following parameters or a combination of several parameters: potential collision damage, potential number of collisions, potential driving risks, etc.

[0090] In the embodiment of the present application, the driving risk is used as the safety index of the static path, and the calculation formula is:

[0091]

[0092] in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time τ, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient;

[0093] Furthermore, in an embodiment of the present application, the illegal driving behavior of the vehicle when changing lanes from the current lane to (or continuing to drive in) the lane where the alternative static path is located is used as the compliance indicator of the static path. The illegal driving behavior may include at least one of the following parameters or a combination of several of them: running a red light, overtaking on the right, not driving in the designated lane, speeding, driving on a solid line, continuous lane changing, etc.

[0094] In this embodiment of the application, the compliance of the static path is calculated based on three violations: overtaking on the right, continuous lane changing, and driving outside the designated lane. The calculation formula is:

[0095]

[0096] in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to (or continues driving in) the lane where the static path τ is located:

[0097]

[0098] Among them, d inter is the distance between the vehicle and the next intersection, D inter Indicates the distance from the next intersection where lane changes are prohibited, and d1 is the adjustment The coefficient of the trend.

[0099] The cost of violating the continuous lane change rule when the vehicle changes lanes to (or continues to drive in) the lane where the static path τ is located:

[0100]

[0101] Among them, t CLC Indicates the time interval between consecutive lane changes of a vehicle.

[0102] The cost of violating the right-side overtaking rule when the vehicle changes lanes to (or continues driving in) the lane where the static path τ is located:

[0103]

[0104] Among them, t RO Indicates the entire lane change time interval when the vehicle is overtaking from the right.

[0105] Furthermore, the embodiment of the present application can calculate the traffic efficiency of vehicles traveling in the lane where the alternative static path is located as a smoothness indicator. The traffic efficiency may include at least one or a combination of several parameters: the average traffic density, average driving speed, average driving time, the distance and speed of the nearest preceding vehicle in the lane where the alternative static path is located, etc.

[0106] In the embodiment of the present application, the patency index of the static path is calculated based on the distance and speed of the nearest preceding vehicle in the lane where the static path is located. The calculation formula is:

[0107]

[0108] in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight can be set according to the requirements of traffic efficiency on the distance and speed of the preceding vehicle, and there is ω d +ω v =1;

[0109] Furthermore, the embodiment of the present application can calculate the comprehensive energy consumption of the vehicle traveling at the average speed of all vehicles in the lane where the alternative static path is located as an economic indicator. The comprehensive energy consumption may include at least one of the following parameters or a combination of several parameters: the fuel consumption per 100 kilometers of the vehicle traveling in the lane where the alternative static path is located, fuel consumption, fuel consumption rate, power consumption, comprehensive fuel consumption per 100 kilometers, etc.

[0110] In this embodiment of the application, the fuel consumption per 100 kilometers of the vehicle traveling at the average speed of all vehicles in the lane where the static path is located is used as the economic indicator of the static path, and the calculation formula is:

[0111]

[0112] in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t;

[0113] Furthermore, the average driving comfort of all vehicles in the lane where the alternative static path is located is calculated as the comfort index of the static path. The driving comfort may include at least one or a combination of several of the following parameters: impact degree, acceleration, vibration frequency, yaw angular velocity, etc.

[0114] In this embodiment of the present application, the root mean square acceleration of all vehicles in the lane where the static path is located is used as the comfort index of the static path, and the calculation formula is:

[0115]

[0116] in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

[0117] The embodiments of the present application can accurately calculate the safety index, compliance index, smoothness index, economy index and comfort index of each static path through calculation formulas, further approaching the decision-making process of human drivers and improving the rationality and social compatibility of autonomous driving vehicle decisions.

[0118] In step S102, a comprehensive evaluation index of each static path is calculated according to the safety index, compliance index, patency index, economy index and comfort index of each static path and the corresponding priorities and weights.

[0119] During the actual implementation process, the embodiment of the present application can set the priorities of safety indicators, compliance indicators, smoothness indicators, economy indicators and comfort indicators according to driving tasks and driving characteristics requirements, set the weights of each indicator based on normalized evaluation indicators, and form a weighted combination to form a comprehensive evaluation index of the static path. Therefore, based on the safety indicators, compliance indicators, smoothness indicators, economy indicators and comfort indicators of each static path and the corresponding priorities and weights, the comprehensive evaluation index of each static path is calculated, which helps to realize personalized decision-making of autonomous driving vehicles and meet the driving characteristics requirements of different drivers / passengers.

[0120] It can be understood that the driving task in the embodiment of the present application is the requirement for the vehicle to arrive at the destination safely and smoothly, and the driving characteristics include but are not limited to the requirement for the vehicle to exhibit stable, aggressive, sporty, comfortable, economical and other driving behaviors.

[0121] Optionally, in one embodiment of the present application, the calculation formula of the comprehensive evaluation index is:

[0122]

[0123] in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

[0124] In the actual implementation process, the embodiment of the present application calculates the static trajectory comprehensive evaluation index with the primary goal of satisfying the driving task and the secondary goal of satisfying the economical driving characteristics requirement. The calculation formula is:

[0125]

[0126] in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

[0127] Furthermore, It represents the normalized * index of the static path τ at the current moment t, and its meaning is that when The larger the value, the better the corresponding * performance of the static path τ; driving safety can be basically guaranteed by the tracking and obstacle avoidance control function. Compliance is a mandatory requirement of the driving task, traffic efficiency is the primary goal of the driving task, and the demand for economical driving characteristics is a secondary goal. Based on this, the priorities set in this embodiment are compliance, safety, smoothness, economy and comfort, and ω2>ω1>ω3>ω4>ω5 are set.

[0128] The embodiments of the present application can improve the accuracy of the calculation of the comprehensive evaluation index of the static trajectory, further realize the personalized decision-making of the autonomous driving vehicle, and meet the driving characteristics requirements of different drivers / passengers.

[0129] In step S103, an optimal static path that meets preset conditions is selected from the static path set according to the size and change information of the comprehensive evaluation index of each static path.

[0130] As a possible implementation method, the embodiment of the present application can select the optimal static path that meets certain conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path, thereby avoiding the linear increase in the calculation scale of the dynamic tracking control function with the number of static trajectories, thereby improving the overall real-time performance of the integrated decision-making control.

[0131] It should be noted that the preset conditions can be set by those skilled in the art according to actual conditions and are not specifically limited here.

[0132] Optionally, in one embodiment of the present application, selecting the optimal static path that meets preset conditions from the static path set based on the size and change information of the comprehensive evaluation index of each static path includes: selecting the optimal static path in a manner that maximizes the comprehensive evaluation index; and setting the update frequency of the optimal static path according to the change information of the comprehensive evaluation index.

[0133] It is understandable that the changes in the comprehensive evaluation indicators in the embodiments of the present application may include but are not limited to the time span of the comprehensive evaluation indicators and the value of the comprehensive evaluation indicators.

[0134] In some embodiments, the optimal static path is selected by maximizing the comprehensive evaluation index, and the update frequency of the optimal static path is set according to the changes in the comprehensive evaluation index, thereby further avoiding the linear increase in the calculation scale of the dynamic tracking control function with the number of static trajectories, and improving the overall real-time performance of the integrated decision-making control.

[0135] Optionally, in one embodiment of the present application, the update frequency is:

[0136]

[0137] in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

[0138] Specifically, the embodiment of the present application selects the optimal static path by maximizing the comprehensive evaluation index, and sets a threshold to limit the update frequency of the optimal path:

[0139]

[0140] The embodiments of the present application can improve the calculation accuracy of the update frequency, avoid the linear increase of the calculation scale of the dynamic tracking control function with the number of static trajectories, and thus improve the overall real-time performance of the integrated decision-making control, which helps to solve the problems of complex algorithm design and poor calculation real-time performance of the dynamic tracking control function in the integrated decision-making control.

[0141] Specifically, combined Figure 3 As shown, the working principle of a static path optimization method for integrated decision-making and control of an autonomous driving vehicle in an embodiment of the present application is described in detail using a specific embodiment.

[0142] like Figure 3 As shown, the embodiment of the present application may include the following steps:

[0143] Step S301: Deconstruct the dynamic tracking control function into static path selection and tracking obstacle avoidance control.

[0144] Among them, the embodiment of the present application can decompose the dynamic tracking control function in the integrated decision-making control into static path selection and tracking obstacle avoidance control. The static path selection function is responsible for evaluating the performance of each static path in the static path set and selecting the optimal static path at the current moment. The static path set is a set of vehicle drivable paths generated based on the static information of the road (such as road shape, stop lines, traffic light information, etc.). The trajectory tracking control function is responsible for tracking the optimal static path while dynamically avoiding obstacles.

[0145] Step S302: Calculate the five-dimensional evaluation index of the static path.

[0146] Among them, the embodiment of the present application can calculate the five-dimensional evaluation index of the static path, thereby being close to the decision-making process of human drivers and improving the rationality and social compatibility of the decision-making of autonomous driving vehicles.

[0147] Step S303: Calculate the static path comprehensive evaluation index.

[0148] Among them, the embodiment of the present application can calculate the comprehensive evaluation index of the static path, which helps to realize personalized decision-making of autonomous driving vehicles and meet the driving characteristics requirements of different drivers / passengers.

[0149] Step S304: Select the optimal static path according to the size and change of the comprehensive evaluation index.

[0150] Among them, the embodiment of the present application can select the current optimal static path according to the size and change of the comprehensive evaluation index, avoid the linear increase of the calculation scale of the dynamic tracking control function with the number of static trajectories, and thus improve the overall real-time performance of the integrated decision-making control.

[0151] According to an embodiment of the present application, a static path optimization method for integrated decision-making and control of an autonomous vehicle is proposed. This method evaluates static paths using five evaluation indicators, including safety, compliance, patency, economy, and comfort, to closely mimic the decision-making process of human drivers and improve the rationality and social compatibility of autonomous vehicle decisions. A comprehensive evaluation indicator is obtained by weighted fusion of the five evaluation indicators, which helps to achieve personalized decision-making for autonomous vehicles and meet the driving characteristics of different drivers / passengers. The optimal static path is selected based on the size and variation of the comprehensive evaluation indicator, avoiding the linear increase in the computational scale of the dynamic tracking control function with the number of static trajectories, thereby improving the overall real-time performance of the integrated decision-making and control. This method solves the problems in related technologies, such as high functional integration, complex algorithm design, large computational scale, and poor real-time performance, caused by the integration of decision-making, planning, and control in integrated dynamic tracking control.

[0152] Next, a static path optimization device for integrated decision-making and control of an autonomous driving vehicle proposed in accordance with an embodiment of the present application will be described with reference to the accompanying drawings.

[0153] Figure 4 This is a structural diagram of a static path optimization device for integrated decision-making and control of an autonomous driving vehicle according to an embodiment of the present application.

[0154] like Figure 4 As shown, the static path optimization device 10 for integrated decision-making and control of an autonomous driving vehicle includes: a first calculation module 100, a second calculation module 200 and a selection module 300.

[0155] Specifically, the first calculation module 100 is used to calculate the safety index, compliance index, patency index, economy index and comfort index of each static path based on the static path set.

[0156] The second calculation module 200 is used to calculate the comprehensive evaluation index of each static path according to the safety index, compliance index, patency index, economy index and comfort index of each static path and the corresponding priorities and weights.

[0157] The selection module 300 is configured to select an optimal static path that meets preset conditions from the static path set according to the size and change information of the comprehensive evaluation index of each static path.

[0158] Optionally, in one embodiment of the present application,

[0159] The calculation formula of the safety index is:

[0160]

[0161] in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient;

[0162] The calculation formula of the compliance indicator is:

[0163]

[0164] in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to the lane where the static path τ is located;

[0165] The calculation formula of the patency index is:

[0166]

[0167] in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight is set according to the traffic efficiency requirements for the distance and speed of the preceding vehicle, and there is ω d +ω v =1;

[0168] The calculation formula of the economic index is:

[0169]

[0170] in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t;

[0171] The calculation formula of the comfort index is:

[0172]

[0173] in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

[0174] Optionally, in one embodiment of the present application, the calculation formula of the comprehensive evaluation index is:

[0175]

[0176]

[0177] in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

[0178] Optionally, in one embodiment of the present application, the selection module 300 includes: a selection unit and a setting unit.

[0179] The selection unit is configured to select the optimal static path in a manner of maximizing the comprehensive evaluation index.

[0180] A setting unit is used to set the update frequency of the optimal static path according to the change information of the comprehensive evaluation index.

[0181] Optionally, in one embodiment of the present application, the update frequency is:

[0182]

[0183] in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

[0184] It should be noted that the above explanation of the embodiment of a static path optimization method for integrated decision-making and control of an autonomous driving vehicle is also applicable to the static path optimization device for integrated decision-making and control of an autonomous driving vehicle in this embodiment, and will not be repeated here.

[0185] According to the embodiment of the present application, a static path optimization device for integrated decision-making and control of an autonomous vehicle is proposed. The static path is evaluated using five evaluation indicators, namely safety, compliance, patency, economy, and comfort, which is close to the decision-making process of human drivers and improves the rationality and social compatibility of autonomous vehicle decisions. The five evaluation indicators are weighted and integrated to obtain a comprehensive evaluation indicator, which helps to realize personalized decision-making of autonomous vehicles and meet the driving characteristics of different drivers / passengers. The current optimal static path is selected based on the size and change of the comprehensive evaluation indicator, avoiding the linear increase in the computational scale of the dynamic tracking control function with the number of static trajectories, thereby improving the overall real-time performance of the integrated decision-making and control. This solves the problems in the related art that the integrated decision-making and dynamic tracking control integrates decision-making, planning, and control, resulting in high functional integration, complex algorithm design, large computational scale, and poor real-time performance.

[0186] Figure 5 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0187] Memory 501 , processor 502 , and computer programs stored in the memory 501 and executable on the processor 502 .

[0188] When the processor 502 executes the program, it implements a static path optimization method for integrated decision-making and control of an autonomous driving vehicle provided in the above embodiment.

[0189] Furthermore, the electronic device further includes:

[0190] The communication interface 503 is used for communication between the memory 501 and the processor 502 .

[0191] The memory 501 is used to store computer programs that can be run on the processor 502 .

[0192] The memory 501 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0193] If the memory 501, processor 502, and communication interface 503 are implemented independently, the communication interface 503, memory 501, and processor 502 can be connected to each other via a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 Only one thick line is used in the diagram, but this does not mean that there is only one bus or one type of bus.

[0194] Optionally, in a specific implementation, if the memory 501, the processor 502 and the communication interface 503 are integrated on a chip, the memory 501, the processor 502 and the communication interface 503 can communicate with each other through an internal interface.

[0195] The processor 502 may be a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0196] An embodiment of the present application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the above-mentioned static path optimization method for integrated decision-making and control of an autonomous driving vehicle.

[0197] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" 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 application. 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 can be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0198] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of technical features indicated. Thus, a feature specified as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of this application, "N" means at least two, for example, two, three, etc., unless otherwise specifically defined.

[0199] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or N executable instructions for implementing a custom logical function or process step, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may be performed in a different order than shown or discussed, including performing functions in a substantially simultaneous manner or in a reverse order depending on the functions involved, which should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0200] The logic and / or steps represented in the flowcharts or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing the logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (e.g., a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device). For purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection with one or N wires (electronic devices), a portable computer disk cartridge (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and programmable read-only memory (EPROM or flash memory), fiber optic devices, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program can be obtained electronically by optically scanning the paper or other medium and then editing, interpreting or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0201] It should be understood that various parts of the present application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiment, the N steps or methods can be implemented using software or firmware stored in a memory and executed by a suitable instruction execution system. If implemented using hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application-specific integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0202] Those skilled in the art will understand that all or part of the steps in the method of the above embodiment can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiment.

[0203] In addition, the functional units in the various embodiments of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into a module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0204] The storage medium mentioned above may be a read-only memory, a magnetic disk, or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application. Persons skilled in the art may make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

Claims

1. A static path optimization method for integrated decision-making control of an autonomous vehicle, characterized in that: The following steps are involved: Based on the static path set, the safety index, compliance index, patency index, economy index and comfort index of each static path are calculated respectively; Calculating a comprehensive evaluation index for each static path according to the safety index, compliance index, patency index, economy index, and comfort index of each static path and the corresponding priorities and weights; as well as Selecting an optimal static path that meets preset conditions from the static path set according to the size and change information of the comprehensive evaluation index of each static path; in, The calculation formula of the safety index is: in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient; The calculation formula of the compliance indicator is: in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to the lane where the static path τ is located; The calculation formula of the patency index is: in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current moment, ω d and ω v They are and The weight is set according to the traffic efficiency requirements for the distance and speed of the preceding vehicle, and there is ω d +ω v =1; The calculation formula of the economic index is: in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t; The calculation formula of the comfort index is: in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

2. The method according to claim 1, characterized in that The calculation formula of the comprehensive evaluation index is: in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

3. The method according to claim 1, characterized in that The selecting, based on the size and change information of the comprehensive evaluation index of each static path, the optimal static path that meets the preset conditions from the static path set includes: Selecting the optimal static path in a manner of maximizing a comprehensive evaluation index; The update frequency of the optimal static path is set according to the change information of the comprehensive evaluation index.

4. The method according to claim 3, characterized in that The update frequency is: in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

5. A static path optimization device for integrated decision-making control of an autonomous vehicle, characterized in that: include: A first calculation module is used to calculate the safety index, compliance index, patency index, economy index and comfort index of each static path based on the static path set; a second calculation module, configured to calculate a comprehensive evaluation index of each static path according to the safety index, compliance index, patency index, economy index, and comfort index of each static path and the corresponding priorities and weights; as well as A selection module, configured to select an optimal static path that meets preset conditions from the static path set according to the size and change information of the comprehensive evaluation index of each static path; in, The calculation formula of the safety index is: in, represents the safety index of the static path τ at the current time t, ∏ is the set of static paths, t∈[t,t+Δt] represents the prediction time domain starting from the current time t, Δt represents the prediction duration, j∈{1,2,…,J} represents the number of traffic participants at time t, and the total number is J; represents the total damage to both parties caused by a hypothetical collision between traffic participant i and the ego vehicle at time t in the prediction domain when the vehicle is traveling along the static path τ; ω D represents the distance attenuation coefficient, ω t represents the time attenuation coefficient; The calculation formula of the compliance indicator is: in, is the compliance index of the alternative static path τ at the current time t, The cost of violating the rule of not driving in the designated lane when the vehicle changes lanes to the lane where the static path τ is located; The calculation formula of the patency index is: in, Indicates the smoothness of the lane where the static path τ is located at the current time t, and They represent the distance and speed between the nearest preceding vehicle and the vehicle in the lane where the static path τ is located at the current time t, ω d and ω v They are and The weight is set according to the traffic efficiency requirements for the distance and speed of the preceding vehicle, and there is ω d +ω v =1; The calculation formula of the economic index is: in, represents the economic index of the static path τ at the current time t, f(·) represents the fuel consumption model of the vehicle per 100 kilometers, represents the average speed of all vehicles in the lane of the static path τ at the current time t; The calculation formula of the comfort index is: in, represents the comfort index of the static path τ at the current moment t, represents the longitudinal acceleration of the i∈{1,2,…,N}th vehicle at the current time t, and N represents the number of all surrounding vehicles in the lane where the static path τ is located.

6. The device according to claim 5, characterized in that The calculation formula of the comprehensive evaluation index is: in, represents the comprehensive evaluation index of the static path τ at the current time t, ω1, ω2, ω3, ω4, and ω5 are the weight coefficients of safety, compliance, smoothness, economy, and comfort, respectively. Represents the normalized * index of the static path τ at the current time t.

7. The device according to claim 5, characterized in that The selection module includes: A selection unit, configured to select the optimal static path in a manner of maximizing a comprehensive evaluation index; A setting unit is used to set the update frequency of the optimal static path according to the change information of the comprehensive evaluation index.

8. The device according to claim 7, characterized in that The update frequency is: in, represents the optimal static path at time t, represents the optimal static path at time t ΔJ represents the comprehensive evaluation index change threshold allowed for static path update.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement a static path optimization method for integrated decision-making of an autonomous vehicle as described in any one of claims 1 to 4.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement a static path optimization method for integrated decision-making and control of an autonomous driving vehicle as described in any one of claims 1 to 4.

Images