Intersection speed planning method and device

By establishing abstract space and optimization problems in the autonomous driving system, using nonlinear objective functions and exponential functions, the complexity and safety problems of autonomous driving vehicles when passing through intersections are solved, and smoother and safer intersection traffic is achieved.

CN118560527BActive Publication Date: 2024-11-26ZHIDAO NETWORK TECH (BEIJING) CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411036242.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-31
Publication Date
2024-11-26
Estimated Expiration
2044-07-31

Smart Images

  • Figure CN118560527B_ABST
    Figure CN118560527B_ABST
Patent Text Reader

Abstract

The present application discloses a method and device for intersection speed planning, the method comprising: establishing an abstract space according to the path planning information of the vehicle and the position information of other traffic participants, the abstract space comprising an interactive game and an intersection game, the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space; establishing an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space; outputting the intersection speed planning result by solving the optimization problem. The present application reduces the complexity of the design of the intersection speed planning optimization problem, while ensuring the smoothness and safety of the solution.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to a method and device for intersection speed planning. Background Art

[0002] In autonomous driving, speed planning at intersections is a key challenge facing motion planning technology. Specifically, when giving way, autonomous driving is prone to being overly conservative for safety reasons, leading to traffic jams, while when trying to overtake, human drivers may also overtake, causing safety hazards.

[0003] How to pass through intersections safely, smoothly and naturally, especially unprotected left-turn intersections, has become an important manifestation and significant symbol of autonomous driving motion planning technology. Summary of the invention

[0004] The embodiments of the present application provide a method and device for intersection speed planning to reduce the complexity of the design of the intersection speed planning optimization problem while ensuring the smoothness and safety of the solution.

[0005] The present application embodiment adopts the following technical solutions:

[0006] In a first aspect, an embodiment of the present application provides a method for intersection speed planning, wherein the method comprises:

[0007] According to the path planning information of the vehicle and the position information of other traffic participants, an abstract space is established, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space;

[0008] Establishing an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space;

[0009] By solving the optimization problem, the intersection speed planning result is output.

[0010] In some embodiments, outputting the intersection speed planning result by solving the optimization problem includes:

[0011] If the optimization problem is successfully solved, the first value of the acceleration sequence in the optimization result is output to the underlying controller;

[0012] If the optimization problem fails to be solved, a number of consecutive solution failures is maintained;

[0013] If the number of consecutive solution failures i is less than a preset first threshold, then during the solution failure period, the i+1th value of the acceleration sequence of the last successful solution is sequentially output to the bottom-level controller;

[0014] If the number of consecutive solution failures is higher than a preset second threshold, it is considered that the optimization problem has no solution, the optimization problem solving is terminated and the protection processing logic is entered.

[0015] In some embodiments, establishing an optimization problem based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space includes:

[0016] Setting the objective function of the optimization problem;

[0017] According to the objective function, a nonlinear objective function including future acceleration information of the ego vehicle is adopted;

[0018] According to the nonlinear objective function, the solution of the optimization problem is obtained as follows: the acceleration sequence of the vehicle within a period of time in the future.

[0019] In some embodiments, the objective function includes:

[0020] According to the actual application scenario, set the average speed of the vehicle;

[0021] Determining a hyper parameter according to the average speed of the vehicle;

[0022] The objective function is constructed based on the average vehicle speed, the hyperparameters, and the exponential function Pow.

[0023] In some embodiments, the method further comprises:

[0024] The comfort measure W_smooth* (sum of squares of the derivatives of the acceleration sequence) is added to the objective function.

[0025] In some embodiments, establishing an optimization problem based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space further includes:

[0026] Setting constraints according to the strategy adopted by the ego vehicle, wherein the strategy adopted by the ego vehicle includes yielding or overtaking;

[0027] If the strategy adopted by the ego vehicle is to yield, the constraint item is that the ego vehicle must enter the interaction or intersection area after other traffic participants exit the interaction or intersection area;

[0028] If the strategy adopted by the ego vehicle is to rush in, the constraint item is that the ego vehicle must exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0029] In some embodiments, the method further comprises:

[0030] When the self-vehicle yields, the speed of other traffic participants after emergency braking within a preset time is used to calculate the time when the self-vehicle enters the interaction or intersection area after the other traffic participants exit the interaction or intersection area;

[0031] When the vehicle is trying to overtake the other vehicle, the speed of the other vehicle after accelerating within the same preset time is used to calculate the time the vehicle needs to exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0032] In some embodiments, establishing an optimization problem based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space includes:

[0033] Setting an initial value of the objective function;

[0034] According to the tracking ID information of the vehicle or other traffic participants, record whether this solution is the first optimization solution for the vehicle or other traffic participants;

[0035] If it is the first optimization solution, the initial value of the variable is optimized to the middle position between the upper and lower bounds of the variable;

[0036] If this is not the first optimization solution, the initial value of the variable will be optimized to the optimization result of the last successful solution.

[0037] In some embodiments, an abstract space is established based on the vehicle path planning information and other traffic participant position information, and the abstract space includes an interactive game and an intersection game, including:

[0038] According to the interactive game in the abstract space, intersection calculation is performed based on the planned path information of the ego-vehicle and the predicted trajectory information of other traffic participants;

[0039] According to the intersection game in the abstract space, the intersection point is calculated based on the planned path information of the vehicle and the predicted trajectory information of other traffic participants.

[0040] In some embodiments, an optimization problem is established based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, including:

[0041] Determining the type of game in the abstract space;

[0042] If the game type is an interactive game problem, the first collision position and the last collision position of the vehicle and other traffic participants are calculated to obtain interactive area information;

[0043] Calculate the time for other traffic participants to arrive at and leave the interaction area based on their current speed information;

[0044] If the game type is an intersection game problem, the positions where the ego vehicle and other traffic participants first collide laterally and the positions where longitudinal safety is finally satisfied are calculated to obtain intersection area information;

[0045] The time for other traffic participants to arrive at and leave the intersection is calculated based on their current speed information.

[0046] In a second aspect, an embodiment of the present application further provides a device for planning intersection speed, wherein the device comprises:

[0047] An abstract space establishment module is used to establish an abstract space according to the path planning information of the ego vehicle and the position information of other traffic participants, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the ego vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the ego vehicle and other traffic participants will eventually converge in the lateral space;

[0048] An optimization problem establishment module, used to establish an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space;

[0049] The output module is used to output the intersection speed planning result by solving the optimization problem.

[0050] In a third aspect, an embodiment of the present application further provides an electronic device, comprising: a processor; and a memory arranged to store computer executable instructions, wherein the executable instructions, when executed, cause the processor to perform the above method.

[0051] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, which stores one or more programs. When the one or more programs are executed by an electronic device including multiple application programs, the electronic device executes the above method.

[0052] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects: an abstract space can be established based on the path planning information of the vehicle and the position information of other traffic participants. The abstract space includes interactive games and intersection games. The interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space. Then, based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, an optimization problem is established. Finally, by solving the optimization problem, the intersection speed planning result is output. Through the above method, the complexity of the design of the intersection speed planning optimization problem is reduced, while ensuring the smoothness and safety of the solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the basis of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0054] Figure 1 This is a schematic diagram of an abstract space for interactive gaming in an embodiment of the present application;

[0055] Figure 2 This is a schematic diagram of an abstract space of the intersection game in the embodiment of the present application;

[0056] Figure 3 A schematic diagram of the flow of the intersection speed planning method in the embodiment of the present application;

[0057] Figure 4 This is a schematic diagram of the structure of the intersection speed planning device in the embodiment of the present application;

[0058] Figure 5 This is a schematic diagram of the vehicle acceleration and time curve under the quadratic target function in the embodiment of the present application;

[0059] Figure 6 This is a schematic diagram of the vehicle speed and time curve under the quadratic target function in the embodiment of the present application;

[0060] Figure 7 It is a schematic diagram of the acceleration and time curve of the self-vehicle rushing under the exponential function objective function in the embodiment of the present application;

[0061] Figure 8 It is a schematic diagram of the vehicle speed and time curve under the exponential function objective function in the embodiment of the present application;

[0062] Fig. 9 This is a schematic diagram of the structure of an electronic device in an embodiment of the present application. DETAILED DESCRIPTION

[0063] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0064] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0065] The technical terms involved in the implementation of this application are as follows:

[0066] RSS model: An autonomous driving safety measurement model proposed by Mobileye that takes responsibility attribution into consideration.

[0067] Abstract space: Convert the real-world state into a feature representation space for solving game problems.

[0068] Nonlinear programming: A programming problem in which the objective function or constraints contain nonlinear functions.

[0069] For the speed planning problem in intersection traffic, it is usually necessary to rely on the prediction of the future trajectories of other traffic participants, and construct the ST graph and optimization problem based on the ego-vehicle path planning and the trajectory prediction results of other traffic participants.

[0070] The shortcomings of the related art are:

[0071] (1) The optimization problem is usually modeled as a quadratic programming problem, and the objective function includes longitudinal distance, longitudinal velocity, and longitudinal acceleration at the same time. This results in a large number of related constraints, especially as the number of obstacles increases, which in turn increases the time required to solve the problem.

[0072] (2) When the quadratic programming problem includes a speed limit or an expected speed, the optimization problem tends to minimize the error between the speed and the expected speed as quickly as possible when the vehicle speed deviates from the expected speed. Even if adding an acceleration rate constraint can improve the situation to a certain extent, the contradiction between satisfying the hard constraint and ensuring ride comfort is difficult to eliminate due to the characteristics of the objective itself.

[0073] (3) Due to the reliance on the accuracy of the predicted trajectory, the uncertainty in the predicted trajectory or the unpredictability of the future trajectories of some traffic participants may not be adequately addressed.

[0074] In view of the above shortcomings, the embodiments of the present application provide a method for intersection speed planning, which reduces the complexity of the optimization problem design by establishing an abstract space, and at the same time ensures the smoothness and safety of solving the optimization problem.

[0075] The present application embodiment provides a method for intersection speed planning, such as Figure 3 As shown, a schematic flow chart of a method for intersection speed planning in an embodiment of the present application is provided, and the method at least includes the following steps S310 to S330:

[0076] Step S310, establishing an abstract space based on the vehicle path planning information and the position information of other traffic participants, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space.

[0077] The ego vehicle path planning information can be obtained according to the ego vehicle planning module.

[0078] The position information of other traffic participants can be obtained by receiving the predicted trajectory of other traffic participants. It should be noted that in order to reduce the dependence on the accuracy of the predicted trajectory, only the predicted position information is used (that is, speed and time information is not included). In this way, relying only on the predicted position information of other traffic participants reduces the dependence on the accuracy of the predicted information to a certain extent.

[0079] Step S320, establishing an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space.

[0080] For the optimization problem construction, in addition to making interactive game and intersection game judgments based on the abstract space and calculating the corresponding interactive area and intersection area, the current speed information of other traffic participants and the current speed information of the vehicle are also received, so as to carry out the following objective function construction, constraint item construction and initial value design, etc.:

[0081] (1) Regardless of the interaction problem or the intersection problem, the objective function of the optimization problem is to allow the vehicle to pass through the interaction area or the intersection area as quickly as possible while maintaining a certain level of comfort.

[0082] (2) Constraint construction: Regardless of whether it is an interaction problem or an intersection problem, the constraints are all related to the strategy adopted by the ego vehicle, that is, whether to give way or cut in.

[0083] (3) Design the initial value of the objective function. Based on the player’s tracking ID, record whether this solution is the first optimization solution for this player.

[0084] Step S330, outputting the intersection speed planning result by solving the optimization problem.

[0085] When solving the optimization problem, a back-end smoothing and protection strategy is adopted when the optimizer fails to solve the problem. The optimizer failure protection strategy weakens the impact of the optimizer failure and improves the robustness of the algorithm and the smoothness of vehicle driving to a certain extent.

[0086] Through the above method, the predicted trajectories of other traffic participants (but only the predicted position information is used) and the planned path information of the vehicle are received to construct an abstract space. At the same time, according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, an optimization problem is established. The current speed information of other traffic participants and the current speed information of the vehicle are also received. By relying only on the predicted position information and current speed information of other traffic participants, the dependence on the accuracy of the predicted information is reduced to a certain extent.

[0087] Through the above method, when establishing the optimization problem, the complex form of the speed planning problem is greatly reduced. When the vehicle is playing a game with multiple traffic participants, the speed planning problem also includes an upper-level decision to assist in the construction of the optimization problem. The method in the embodiment of the present application only targets some inherent defects in the mainstream speed planning technology, and the upper-level decision is completed by a decision maker other than the embodiment of the present application.

[0088] Through the above method, the constraint design in the optimization problem takes into account the sudden braking of other traffic participants during the yielding process and the sudden overtaking of other participants during the overtaking process, which improves the safety of the vehicle during the intersection game.

[0089] Different from the related technologies, the optimization problem is usually modeled as a quadratic programming, and the objective function includes longitudinal distance, longitudinal speed and longitudinal acceleration at the same time, which makes the problem with more related constraints. Through the above method, the complexity of the design of the intersection speed planning optimization problem is reduced in autonomous driving.

[0090] Different from the related art, which may not adequately deal with the uncertainty in the predicted trajectory or the unpredictability of the future trajectory of some traffic participants due to its reliance on the accuracy of the predicted trajectory, the above method greatly reduces the complexity of the speed planning problem.

[0091] In one embodiment of the present application, the output of the intersection speed planning result by solving the optimization problem includes: if the optimization problem is successfully solved, the first value of the acceleration sequence in the optimization result is output to the underlying controller; if the optimization problem is failed to be solved, a number of consecutive solution failures is maintained; if the number of consecutive solution failures i is less than a preset first threshold, the i+1th value of the acceleration sequence of the last successful solution is output in sequence to the underlying controller during the solution failure period; if the number of consecutive solution failures is higher than a preset second threshold, it is considered that the optimization problem has no solution, the optimization problem solving is terminated and the protection processing logic is entered.

[0092] As a back-end protection and smoothing method when the solver fails, if the solver succeeds, the optimization result, i.e. the first value of an acceleration sequence, is output to the underlying controller.

[0093] If the solver fails, the number of consecutive failures is maintained. If the number of consecutive failures (such as i times) is less than a given threshold (such as 5 times), the i+1th value of the last successful acceleration sequence is output to the underlying controller in sequence during the period of solution failure.

[0094] If the number of solution failures is higher than a certain threshold, it means that the optimization problem may have no solution, and the optimization problem solving is terminated and the default protection logic is entered.

[0095] It can be understood that the protection logic uses a conservative approach to output intersection speed planning results to reduce safety hazards caused by overtaking.

[0096] In one embodiment of the present application, an optimization problem is established based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, including: setting the objective function of the optimization problem to: the vehicle passes through the interactive area or the intersection area as quickly as possible while maintaining comfort; according to the objective function, a nonlinear objective function that only includes the future acceleration information of the vehicle is adopted; according to the nonlinear objective function, the solution to the optimization problem is obtained as: the acceleration sequence of the vehicle in a future period of time.

[0097] When constructing the optimization problem, the objective function of the optimization problem is that the vehicle passes through the interaction area or the intersection area as quickly as possible while maintaining a certain degree of comfort. In the embodiment of the present application, in order to solve the problem that the secondary programming problem in the mainstream speed planning is complex in form, has many constraints, and the solution may not be smooth enough when deviating from the set speed upper limit (or expected vehicle speed), a new nonlinear objective function that only contains the future acceleration information of the vehicle is given, thereby simplifying the objective function form, that is, it does not need to contain position and speed information, that is, the solution result of the optimization problem is the acceleration sequence of the vehicle in the future period of time.

[0098] In one embodiment of the present application, the objective function includes: setting the average speed of the vehicle according to the actual application scenario; determining the hyperparameter according to the average speed of the vehicle; constructing the objective function based on the average speed of the vehicle, the hyperparameter, and using the exponential function Pow (hyperparameter, average speed of the vehicle), and the objective function is used to describe the traffic efficiency of the vehicle.

[0099] Regarding the objective function of the optimization problem, a new objective function that describes the traffic efficiency of the vehicle is provided in the embodiment of the present application, that is, an exponential function Pow (hyperparameter, average speed of the vehicle) is used. In this objective function, the lower the average speed of the vehicle, the higher its value will increase exponentially, and the higher the average speed, the calculated value will decrease exponentially and approach 0 (this flat characteristic will weaken the pursuit of the target speed to a certain extent). The hyperparameter is preferably 0.85, and can be designed according to different vehicle speed requirements.

[0100] In one embodiment of the present application, the method further includes: adding a comfort metric W_smooth* (the sum of squares of acceleration sequence derivatives) to the objective function to improve the smoothness of the acceleration sequence solved by the objective function.

[0101] In order to ensure the smoothness of the acceleration sequence, a comfort metric, namely W_smooth* (the sum of the squares of the derivatives of the acceleration sequence) is added to the objective function to further improve the smoothness of the acceleration sequence. Figure 5 and 6 As shown and Figure 7 and 8 As shown in the figure, it can be seen that the exponential function objective function designed in the embodiment of the present application has a smoother and more human-like acceleration output in the over take scenario under the same initial conditions.

[0102] In one embodiment of the present application, the optimization problem is established based on the interactive game, the intersection game, the speed information of the vehicle, and the speed information of other traffic participants in the abstract space, and also includes: setting constraints according to the strategy adopted by the vehicle, and the strategy adopted by the vehicle includes giving way or overtaking; if the strategy adopted by the vehicle is to give way, the constraint is that the vehicle must enter the interactive or intersection area after other traffic participants leave the interactive or intersection area; if the strategy adopted by the vehicle is to overtake, the constraint is that the vehicle must exit the interactive or intersection area before other traffic participants enter the interactive or intersection area.

[0103] In one embodiment of the present application, the method also includes: when the own vehicle gives way, using the speed of other traffic participants after emergency braking within a preset time to calculate the time it takes for the own vehicle to enter the interaction or intersection area after other traffic participants leave the interaction or intersection area; when the own vehicle overtakes, using the speed of the other vehicle after accelerating within the same preset time to calculate the time it takes for the own vehicle to exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0104] For constraint design, no matter it is an interaction problem or a merging problem, the constraints are all related to the strategy adopted by the ego vehicle, i.e., giving way or cutting in.

[0105] Specifically, for the yielding problem, the constraint is that the vehicle must enter the interaction or intersection area after other traffic participants leave the interaction or intersection area.

[0106] For the rush-to-passenger problem, the constraint is that the vehicle must exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0107] In addition, in order to cope with the uncertainty of the predicted trajectory itself or the unpredictability of other traffic participants' behaviors such as sudden braking, when calculating the time for other traffic participants to leave the interaction or intersection area when the ego vehicle yields, the speed of other vehicles after emergency braking (such as taking the maximum braking amount) within a certain period of time is always used for calculation. At the same time, when the ego vehicle is overtaking, the speed of other vehicles after accelerating (such as taking the maximum acceleration) within the same certain period of time as yielding is always used for calculation.

[0108] It can be understood that a certain time is related to the ego vehicle planning cycle, such as 0.2 seconds.

[0109] In one embodiment of the present application, an optimization problem is established based on the interactive game, the intersection game, the speed information of the vehicle, and the speed information of other traffic participants in the abstract space, including: setting the initial value of the objective function; recording whether this solution is the first optimization solution for the vehicle or other traffic participants based on the tracking ID information of the vehicle or other traffic participants; if it is the first optimization solution, optimizing the initial value of the variable to the middle position between the upper and lower bounds of the variable; if it is not the first optimization solution, optimizing the initial value of the variable to the optimization result of the last successful solution.

[0110] Design of the initial value of the objective function: Based on the tracking ID of the vehicle or other traffic participants, record whether this solution is the first optimization solution for the vehicle or other traffic participants. If so, the initial value of the optimization variable is the middle position of the upper and lower bounds of the optimization variable. If it has been solved, the initial value of the optimization variable is the optimization result of the last successful solution. The above design can greatly improve the success rate of the solver.

[0111] In one embodiment of the present application, an abstract space is established based on the self-vehicle path planning information and the position information of other traffic participants, and the abstract space includes interactive games and intersection games, including: according to the interactive game in the abstract space, intersection points are calculated based on the self-vehicle planned path information and other traffic participants' predicted trajectory information; according to the intersection game in the abstract space, intersection points are calculated based on the self-vehicle planned path information and other traffic participants' predicted trajectory information.

[0112] like Figure 1 and Figure 2 As shown in Figure 1, when other traffic participants interact with the ego vehicle (usually given by the ego vehicle prediction module), the ego vehicle constructs an abstract space. The schematic diagram of the abstract space is shown in Figure 1. Figure 1 and Figure 2 As shown in Figure 1, points A and C represent the entry into the game range, and points B and D represent the exit from the game range.

[0113] The established abstract space supports two types of abstract spaces, namely, interaction games (the ego vehicle and other traffic participants will eventually separate in the lateral space) and intersection games (the ego vehicle and other traffic participants will eventually converge in the lateral space).

[0114] For interactive games, the intersection is calculated based on the planned path information of the vehicle and the predicted trajectory information of other traffic participants. In the plane diagram, the predicted trajectory of other traffic participants is divided into positive and negative halves in the y direction with the intersection as the local origin.

[0115] For the intersection game, the intersection point is calculated based on the planned path information of the ego vehicle and the predicted trajectory information of other traffic participants, and the location point information of the first lateral collision between the ego vehicle and other traffic participants on the planned path of the ego vehicle or the predicted trajectory of other traffic participants is represented in the plane graph.

[0116] In one embodiment of the present application, an optimization problem is established based on the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, including: determining the game type in the abstract space; if the game type is an interactive game problem, calculating the first and last collision positions of the vehicle and other traffic participants to obtain interactive area information; calculating the time for other traffic participants to arrive at and exit the interactive area based on the current speed information of other traffic participants; if the game type is an intersection game problem, calculating the first lateral collision position of the vehicle and other traffic participants and the final position that satisfies longitudinal safety to obtain intersection area information; calculating the time for other traffic participants to arrive at and exit the intersection area based on the current speed information of other traffic participants.

[0117] For the interactive game problem, the first and last collision locations between the vehicle and other traffic participants are calculated to obtain the interactive area information, and the time for other traffic participants to arrive at and leave the interactive area is calculated based on the current speed information of other traffic participants.

[0118] For the intersection game problem, the position where the ego vehicle and other traffic participants first collide laterally and the position where longitudinal safety is finally satisfied (for example, the position can be obtained by RSS model calculation) are calculated (the ego vehicle may be in front or in the back), the intersection area information is obtained, and the time for other traffic participants to arrive at and leave the intersection area is calculated based on the current speed information of other traffic participants.

[0119] The present application embodiment also provides a road intersection speed planning device 400, such as Figure 4 As shown, a schematic diagram of the structure of the intersection speed planning device in an embodiment of the present application is provided, and the intersection speed planning device 400 at least includes: an abstract space establishment module 410, an optimization problem establishment module 420, and an output module 430, wherein:

[0120] In one embodiment of the present application, the abstract space establishment module 410 is specifically used to: establish an abstract space based on the vehicle path planning information and the position information of other traffic participants, and the abstract space includes an interactive game and an intersection game. The interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space.

[0121] The ego vehicle path planning information can be obtained according to the ego vehicle planning module.

[0122] The position information of other traffic participants can be obtained by receiving the predicted trajectory of other traffic participants. It should be noted that in order to reduce the dependence on the accuracy of the predicted trajectory, only the predicted position information is used (that is, speed and time information is not included). In this way, relying only on the predicted position information of other traffic participants reduces the dependence on the accuracy of the predicted information to a certain extent.

[0123] In one embodiment of the present application, the optimization problem establishing module 420 is specifically used to establish an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space.

[0124] For the optimization problem construction, in addition to making interactive game and intersection game judgments based on the abstract space and calculating the corresponding interactive area and intersection area, the current speed information of other traffic participants and the current speed information of the vehicle are also received, so as to carry out the following objective function construction, constraint item construction and initial value design, etc.:

[0125] (1) Regardless of the interaction problem or the intersection problem, the objective function of the optimization problem is to allow the vehicle to pass through the interaction area or the intersection area as quickly as possible while maintaining a certain level of comfort.

[0126] (2) Constraint construction: Regardless of whether it is an interaction problem or an intersection problem, the constraints are all related to the strategy adopted by the ego vehicle, that is, whether to give way or cut in.

[0127] (3) Design the initial value of the objective function. Based on the player’s tracking ID, record whether this solution is the first optimization solution for this player.

[0128] In one embodiment of the present application, the output module 430 is specifically used to output the intersection speed planning result by solving the optimization problem.

[0129] When solving the optimization problem, a back-end smoothing and protection strategy is adopted when the optimizer fails to solve the problem. The optimizer failure protection strategy weakens the impact of the optimizer failure and improves the robustness of the algorithm and the smoothness of vehicle driving to a certain extent.

[0130] In one embodiment of the present application, the output module 430 is also used to

[0131] If the optimization problem is successfully solved, the first value of the acceleration sequence in the optimization result is output to the underlying controller;

[0132] If the optimization problem fails to be solved, a number of consecutive solution failures is maintained;

[0133] If the number of consecutive solution failures i is less than a preset first threshold, then during the solution failure period, the i+1th value of the acceleration sequence of the last successful solution is sequentially output to the bottom-level controller;

[0134] If the number of consecutive solution failures is higher than a preset second threshold, it is considered that the optimization problem has no solution, the optimization problem solving is terminated and the protection processing logic is entered.

[0135] In one embodiment of the present application, the abstract space establishment module 420 is also used to

[0136] The objective function of the optimization problem is set as follows: the vehicle passes through the interaction area or the intersection area as quickly as possible while maintaining comfort;

[0137] According to the objective function, a nonlinear objective function including only the future acceleration information of the ego vehicle is adopted;

[0138] According to the nonlinear objective function, the solution of the optimization problem is obtained as follows: the acceleration sequence of the vehicle within a period of time in the future.

[0139] In one embodiment of the present application, the objective function in the abstract space establishment module 420 includes:

[0140] According to the actual application scenario, set the average speed of the vehicle;

[0141] Determining a hyper parameter according to the average speed of the vehicle;

[0142] The objective function is constructed based on the average speed of the vehicle and the hyperparameters and using an exponential function Pow (hyperparameter, average speed of the vehicle), and the objective function is used to describe the travel efficiency of the vehicle.

[0143] In one embodiment of the present application, a comfort measurement module is provided to

[0144] A comfort metric W_smooth* (the sum of squares of the derivatives of the acceleration sequence) is added to the objective function to improve the smoothness of the acceleration sequence solved by the objective function.

[0145] In one embodiment of the present application, the abstract space establishment module 420 is also used to

[0146] Setting constraints according to the strategy adopted by the ego vehicle, wherein the strategy adopted by the ego vehicle includes yielding or overtaking;

[0147] If the strategy adopted by the ego vehicle is to yield, the constraint item is that the ego vehicle must enter the interaction or intersection area after other traffic participants exit the interaction or intersection area;

[0148] If the strategy adopted by the ego vehicle is to rush in, the constraint item is that the ego vehicle must exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0149] In one embodiment of the present application, a module for giving way or grabbing way is also included.

[0150] When the self-vehicle yields, the speed of other traffic participants after emergency braking within a preset time is used to calculate the time when the self-vehicle enters the interaction or intersection area after the other traffic participants exit the interaction or intersection area;

[0151] When the vehicle is trying to overtake the other vehicle, the speed of the other vehicle after accelerating within the same preset time is used to calculate the time the vehicle needs to exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

[0152] In one embodiment of the present application, the optimization problem establishment module 420 is also used to

[0153] Setting an initial value of the objective function;

[0154] According to the tracking ID information of the vehicle or other traffic participants, record whether this solution is the first optimization solution for the vehicle or other traffic participants;

[0155] If it is the first optimization solution, the initial value of the variable is optimized to the middle position between the upper and lower bounds of the variable;

[0156] If this is not the first optimization solution, the initial value of the variable will be optimized to the optimization result of the last successful solution.

[0157] In one embodiment of the present application, the abstract space establishment module 410 is also used to

[0158] According to the interactive game in the abstract space, intersection calculation is performed based on the planned path information of the ego-vehicle and the predicted trajectory information of other traffic participants;

[0159] According to the intersection game in the abstract space, the intersection point is calculated based on the planned path information of the vehicle and the predicted trajectory information of other traffic participants.

[0160] In one embodiment of the present application, the optimization problem establishment module 430 is also used to

[0161] Determining the type of game in the abstract space;

[0162] If the game type is an interactive game problem, the first collision position and the last collision position of the vehicle and other traffic participants are calculated to obtain interactive area information;

[0163] Calculate the time for other traffic participants to arrive at and leave the interaction area based on their current speed information;

[0164] If the game type is an intersection game problem, the positions where the ego vehicle and other traffic participants first collide laterally and the positions where longitudinal safety is finally satisfied are calculated to obtain intersection area information;

[0165] The time for other traffic participants to arrive at and leave the intersection is calculated based on their current speed information.

[0166] It can be understood that the above-mentioned intersection speed planning device can implement each step of the intersection speed planning method provided in the above-mentioned embodiment, and the relevant explanations about the intersection speed planning method are applicable to the intersection speed planning device, which will not be repeated here.

[0167] Fig. 9 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Fig. 9At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0168] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Fig. 9 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0169] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0170] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming an intersection speed planning device at the logical level. The processor executes the program stored in the memory and is specifically used to perform the following operations:

[0171] According to the path planning information of the vehicle and the position information of other traffic participants, an abstract space is established, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space;

[0172] Establishing an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space;

[0173] By solving the optimization problem, the intersection speed planning result is output.

[0174] The above application Figure 3The method performed by the intersection speed planning device disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a mature storage medium in the field such as random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0175] The electronic device may also perform Figure 3 The method for executing the speed planning device at the intersection is realized by Figure 3 The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0176] The present application also provides a computer-readable storage medium, which stores one or more programs, wherein the one or more programs include instructions, which, when executed by an electronic device including multiple application programs, enable the electronic device to execute Figure 3 The method executed by the intersection speed planning device in the illustrated embodiment is specifically used to execute:

[0177] According to the path planning information of the vehicle and the position information of other traffic participants, an abstract space is established, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space;

[0178] Establishing an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space;

[0179] By solving the optimization problem, the intersection speed planning result is output.

[0180] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0181] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0182] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0183] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0184] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0185] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0186] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0187] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0188] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0189] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for intersection speed planning, in, The method comprises: According to the path planning information of the vehicle and the position information of other traffic participants, an abstract space is established, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the vehicle and other traffic participants will eventually converge in the lateral space; According to the interactive game in the abstract space, intersection calculation is performed based on the planned path information of the ego-vehicle and the predicted trajectory information of other traffic participants; According to the intersection game in the abstract space, the intersection point is calculated based on the planned path information of the ego vehicle and the predicted trajectory information of other traffic participants; According to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, an optimization problem is established, which includes: Determining the type of game in the abstract space; If the game type is an interactive game problem, the first collision position and the last collision position of the vehicle and other traffic participants are calculated to obtain interactive area information; Calculate the time for other traffic participants to arrive at and leave the interaction area based on their current speed information; If the game type is an intersection game problem, the positions where the ego vehicle and other traffic participants first collide laterally and the positions where longitudinal safety is finally satisfied are calculated to obtain intersection area information; Calculate the time for other traffic participants to arrive at and leave the intersection area based on their current speed information; The objective function of the optimization problem is set as follows: the vehicle passes through the interaction area or the intersection area as quickly as possible while maintaining comfort; According to the objective function, a nonlinear objective function including only the future acceleration information of the ego vehicle is adopted; According to the nonlinear objective function, the solution of the optimization problem is: the acceleration sequence of the vehicle in the future period of time; The objective function includes: setting the average speed of the vehicle according to the actual application scenario; Determining a hyper parameter according to the average speed of the vehicle; The objective function is constructed based on the average speed of the vehicle and the hyperparameters and using the exponential function Pow; the product of the comfort metric and the sum of the squares of the acceleration sequence derivatives is added to the objective function; When the self-vehicle yields, the speed of other traffic participants after emergency braking within a preset time is used to calculate the time when the self-vehicle enters the interaction or intersection area after the other traffic participants exit the interaction or intersection area; When the vehicle is trying to overtake the other vehicle, the speed of the other vehicle after accelerating within the same preset time is used to calculate the time the vehicle needs to exit the interaction or intersection area before other traffic participants enter the interaction or intersection area; By solving the optimization problem, the intersection speed planning result is output.

2. The method according to claim 1, in, The method of outputting the intersection speed planning result by solving the optimization problem includes: If the optimization problem is successfully solved, the first value of the acceleration sequence in the optimization result is output to the underlying controller; If the optimization problem fails to be solved, a number of consecutive solution failures is maintained; If the number of consecutive solution failures i is less than a preset first threshold, then during the solution failure period, the i+1th value of the acceleration sequence of the last successful solution is sequentially output to the bottom-level controller; If the number of consecutive solution failures is higher than a preset second threshold, it is considered that the optimization problem has no solution, the optimization problem solving is terminated and the protection processing logic is entered.

3. The method according to claim 1, in, The establishing of the optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space also includes: Setting constraints according to the strategy adopted by the ego vehicle, wherein the strategy adopted by the ego vehicle includes yielding or taking over; If the strategy adopted by the ego vehicle is to yield, the constraint item is that the ego vehicle must enter the interaction or intersection area after other traffic participants exit the interaction or intersection area; If the strategy adopted by the ego vehicle is to rush in, the constraint item is that the ego vehicle must exit the interaction or intersection area before other traffic participants enter the interaction or intersection area.

4. The method according to claim 1, in, The optimization problem is established according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, including: Setting an initial value of the objective function; According to the tracking ID information of the vehicle or other traffic participants, record whether this solution is the first optimization solution for the vehicle or other traffic participants; If it is the first optimization solution, the initial value of the variable is optimized to the middle position between the upper and lower bounds of the variable; If this is not the first optimization solution, the initial value of the variable will be optimized to the optimization result of the last successful solution.

5. A road intersection speed planning device, in, The device comprises: An abstract space establishment module is used to establish an abstract space according to the path planning information of the ego vehicle and the position information of other traffic participants, wherein the abstract space includes an interactive game and an intersection game, wherein the interactive game is used to indicate that the ego vehicle and other traffic participants will eventually separate in the lateral space, and the intersection game is used to indicate that the ego vehicle and other traffic participants will eventually converge in the lateral space; According to the interactive game in the abstract space, intersection calculation is performed based on the planned path information of the ego-vehicle and the predicted trajectory information of other traffic participants; According to the intersection game in the abstract space, the intersection point is calculated based on the planned path information of the ego vehicle and the predicted trajectory information of other traffic participants; The optimization problem establishment module is used to establish an optimization problem according to the interactive game, the intersection game, the vehicle speed information, and the speed information of other traffic participants in the abstract space, including: Determining the type of game in the abstract space; If the game type is an interactive game problem, the first collision position and the last collision position of the vehicle and other traffic participants are calculated to obtain interactive area information; Calculate the time for other traffic participants to arrive at and leave the interaction area based on their current speed information; If the game type is an intersection game problem, the positions where the ego vehicle and other traffic participants first collide laterally and the positions where longitudinal safety is finally satisfied are calculated to obtain intersection area information; Calculate the time for other traffic participants to arrive at and leave the intersection area based on their current speed information; The objective function of the optimization problem is set as follows: the vehicle passes through the interaction area or the intersection area as quickly as possible while maintaining comfort; According to the objective function, a nonlinear objective function including only the future acceleration information of the ego vehicle is adopted; According to the nonlinear objective function, the solution of the optimization problem is: the acceleration sequence of the vehicle in the future period of time; The objective function includes: setting the average speed of the vehicle according to the actual application scenario; Determining a hyper parameter according to the average speed of the vehicle; The objective function is constructed based on the average speed of the vehicle and the hyperparameters and using the exponential function Pow; the product of the comfort metric and the sum of the squares of the acceleration sequence derivatives is added to the objective function; When the self-vehicle yields, the speed of other traffic participants after emergency braking within a preset time is used to calculate the time when the self-vehicle enters the interaction or intersection area after the other traffic participants exit the interaction or intersection area; When the vehicle is trying to overtake the other vehicle, the speed of the other vehicle after accelerating within the same preset time is used to calculate the time the vehicle needs to exit the interaction or intersection area before other traffic participants enter the interaction or intersection area; The output module is used to output the intersection speed planning result by solving the optimization problem.