Vehicle speed planning method and system

Abstract

The invention relates to a vehicle speed planning method and system. The vehicle speed planning method comprises the steps of obtaining motion state data of a vehicle and one or more adjacent vehicles; acquiring map environment data, wherein the map environment data comprises data of a lane where the vehicle is located and data of left and right adjacent lanes; judging whether a lane changing demand exists or not based on the motion state data and the map environment data; if yes, determining a target vehicle with a lane changing demand, and determining a longitudinal distance space required by the target vehicle to complete lane changing; and performing dynamic speed planning based on the motion state data, the map environment data and the longitudinal distance space to generate a final speed planning curve.

Description

Technical Field

[0001] The present application relates to the field of intelligent assisted driving, and more specifically, to a vehicle speed planning method and system. Background Art

[0002] When a vehicle is driving on a closed road, it is necessary to reasonably plan the vehicle's movement speed for various scenarios on the road (such as automatically finding space to change lanes, giving way to merging vehicles, merging into the main road from ramps, etc.). Existing methods usually set the vehicle's speed based on the vehicle's current perception information and empirical rules, which usually results in too late start of speed adjustment, uneven acceleration and deceleration changes during speed adjustment, and poor ride comfort. Summary of the invention

[0003] In view of the above problems, the following technical solutions are provided.

[0004] The vehicle speed planning method of the present application includes: obtaining motion state data of the vehicle and one or more adjacent vehicles; obtaining map environment data, wherein the map environment data includes data of the lane where the vehicle is located and the left and right adjacent lanes; determining whether there is a need to change lanes based on the motion state data and the map environment data; if so, determining a target vehicle with a lane change need, and determining the longitudinal distance space required for the target vehicle to complete the lane change; and performing dynamic speed planning based on the motion state data, the map environment data, and the longitudinal distance space to generate a final speed planning curve.

[0005] Optionally, the motion state data includes: vehicle speed data and vehicle positioning data.

[0006] Optionally, the map environment data includes: topological connectivity of lanes, lane line types of lane boundaries, lane types, and lane section lengths.

[0007] Optionally, the dynamic speed planning further includes: mapping the motion state data, the map environment data and the longitudinal distance space to the planning space; discretizing the planning space; converting the received multi-source speed constraints into a speed planning curve; calculating a cost function based on the speed planning curve; and selecting the final speed planning curve based on the cost function.

[0008] Optionally, the multi-source speed limit includes: road speed limit, curvature speed limit required to ensure driving safety on curved roads, expected driving speed, and safe longitudinal speed limit required for current and future behavior decisions of the vehicle.

[0009] The vehicle speed planning system of the present application includes: a state perception module, which is configured to obtain motion state data of the vehicle and one or more adjacent vehicles; a map module, which is configured to obtain map environment data, wherein the map environment data includes data of the lane where the vehicle is located and the left and right adjacent lanes; a speed planning module, which is configured to: determine whether there is a lane change demand based on the motion state data and the map environment data; if so, determine the target vehicle with the lane change demand, and determine the longitudinal distance space required for the target vehicle to complete the lane change; and perform dynamic speed planning based on the motion state data, the map environment data and the longitudinal distance space to generate a final speed planning curve.

[0010] The computer-readable storage medium of the present application stores a computer program thereon, and when the computer program is executed by a processor, the above-mentioned vehicle speed planning method is implemented.

[0011] The computer device of the present application includes a storage module, a processor, and a computer program stored in the storage module and executable on the processor. When the processor executes the computer program, the above-mentioned vehicle speed planning method is implemented.

[0012] The computer program product of the present application includes a computer program, and when the computer program is executed by a processor, the above-mentioned vehicle speed planning method is implemented.

[0013] The vehicle of the present application comprises the above-mentioned vehicle speed planning system.

[0014] The vehicle speed planning method and system of the present application can automatically find space to perform tasks such as changing lanes and giving way to merging vehicles based on the high-precision map of the closed road and the surrounding vehicles perceived by the vehicle in real time, and reasonably plan the vehicle's movement speed, thereby improving the vehicle's driving safety and comfort in closed roads under automatic driving status. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and / or other aspects and advantages of the present application will become clearer and easier to understand through the following description of various aspects in conjunction with the accompanying drawings, in which the same or similar units are represented by the same reference numerals. In the accompanying drawings:

[0016] Figure 1 A schematic flow chart of a vehicle speed planning method 100 according to an embodiment of the present application is shown;

[0017] Figure 2 A schematic diagram showing lane change requirements of a vehicle and an adjacent vehicle according to an embodiment of the present application is shown;

[0018] Figure 3 A schematic flow chart of dynamic speed planning according to an embodiment of the present application is shown; and

[0019] Figure 4 A schematic block diagram of a vehicle speed planning system 400 according to an embodiment of the present application is shown. DETAILED DESCRIPTION

[0020] The description of the following specific embodiments is merely exemplary in nature and is not intended to limit the disclosed technology or the application and use of the disclosed technology. In addition, it is not intended to be bound by any express or implied theory presented in the aforementioned technical field, background technology or the following specific embodiments.

[0021] In the following detailed description of the embodiments, many specific details are set forth in order to provide a more thorough understanding of the disclosed technology. However, it is apparent to one of ordinary skill in the art that the disclosed technology can be practiced without these specific details. In other instances, well-known features are not described in detail to avoid unnecessarily complicating the description.

[0022] Terms such as “comprise” and “include” indicate that in addition to the units and steps directly and explicitly stated in the specification, the technical solution of the present application does not exclude the situation where there are other units and steps that are not directly or explicitly stated.

[0023] Hereinafter, various exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings.

[0024] Reference now Figure 1 , Figure 1 A schematic flow chart of a vehicle speed planning method according to an embodiment of the present application is shown.

[0025] like Figure 1 As shown, in step 101, the motion state data of the vehicle and one or more adjacent vehicles are obtained, specifically, the absolute posture of the vehicle and the relative position in the high-precision map are determined, wherein the relative position includes the road section position of the vehicle and the lane position in the road section.

[0026] In step 102, map environment data is obtained, wherein the map environment data includes data of the lane where the vehicle is located and the left and right adjacent lanes. In some embodiments, through high-precision map data reconstruction, the information of the lane where the vehicle is located and the left and right adjacent lanes is selected as input for scene constraint construction.

[0027] In step 103, it is determined whether there is a need to change lanes based on the motion state data and the map environment data. Figure 2 , the following comprehensive judgments are made on the topological connectivity of lanes in the high-precision map lane information, lane line types at lane boundaries, lane types, and lane section lengths:

[0028] 1) Whether the vehicle in the adjacent lane needs to change lanes to the lane where the vehicle is located because its lane ends;

[0029] 2) Whether the vehicle needs to change lanes to the left or right because the current lane cannot lead to the navigation destination;

[0030] 3) The longitudinal distance space required for this vehicle or the vehicle in the adjacent lane to complete the lane change.

[0031] If the judgment result of at least one of 1) and 2) is that there is a lane change demand, a target vehicle having a lane change demand is determined, and a longitudinal distance space required for the target vehicle to complete the lane change is determined.

[0032] In some embodiments, determining the road scene in which the vehicle is located includes: determining whether the positioning system is working normally and whether high-precision map data is available; if so, obtaining the lane information of the vehicle and its adjacent lanes based on the positioning information collected by the positioning system and the high-precision map data; determining the lane change demand of the vehicle or its adjacent vehicles based on the lane information; if there is a lane change demand, determining the longitudinal spatial distance in which the lane change can be performed based on the lane boundary line type and length of the vehicle and its adjacent vehicles; if not, the vehicle does not need to perform speed planning for the yielding scenario and continues to maintain the speed planning of the cruising state.

[0033] In step 104 , dynamic speed planning is performed based on the motion state data, the map environment data, and the longitudinal distance space to generate a final speed planning curve.

[0034] Optionally, refer to Figure 3 ,Dynamic speed planning further includes:

[0035] Step 301: mapping motion state data, map environment data and longitudinal distance space into planning space;

[0036] Step 302: discretize the planning space;

[0037] Step 303: converting the received multi-source speed constraints into a consistent “positioning-speed” speed planning curve;

[0038] Step 304: Calculate a cost function based on the speed planning curve; and

[0039] Step 305: Select a final speed planning curve based on the cost function.

[0040] In some embodiments, combined with the road structure, the front obstacle vehicle in the right lane and the front vehicle in the current lane can be screened out as target obstacles, and the future motion state of the obstacle vehicle is generated through the current motion state of the obstacle vehicle and projected into the planning space.

[0041] The constraints that this vehicle needs to meet are: in the executable space for lane change, give way to the target obstacle vehicle in the right lane and allow it to change lanes normally to this lane; during the lane change process of the target obstacle vehicle in the right lane, keep a safe distance from it to avoid collision; keep a safe distance from the target obstacle vehicle in this lane to avoid collision; ensure the smoothness and comfort of speed control; comprehensively consider various constraints and generate the final speed planning curve through reasonable planning.

[0042] When the vehicle is driving autonomously on a closed road, it is necessary to plan a reasonable speed planning curve in real time based on the surrounding environment information, so as to control the vehicle to drive autonomously safely and smoothly; the surrounding environment information includes but is not limited to the speed limit information of the road, the curvature information of the road, and the surrounding obstacle information; at the same time, autonomous driving needs to consider the driver's intention, including but not limited to the intention to change lanes and the expected speed, and comprehensively derive the future speed-time curve; by discretizing the planning space into a "position-speed" space, and at the same time, projecting the speed constraints and obstacle constraints into the planning space, using dynamic programming, combined with heuristic functions, the speed planning curve is obtained. The specific process is as follows:

[0043] First, the planning space is discretized;

[0044] For example: Set the planning time range to the current time to the future T max The allowed speed range of the vehicle under the current working condition is [0,V max ], time sampling interval delta T , speed sampling interval delta V , then the planning space is established as:

[0045] The horizontal axis is the time sampling space, which is distributed as {0,delta T ,2*delta T ,3*delta T ,…,T max}, the dimension is

[0046] The vertical axis is the velocity sampling space, which is distributed as {0, delta V ,2*delta V ,3*delta V ,…,V max}, the dimension is

[0047] common Dimensional speed-time planning space.

[0048] The received multi-source speed limits or the driver's desired speed are uniformly processed and converted into a consistent "position-speed limit" speed planning curve form;

[0049] At the same time, the curve smoothing method is used to merge multiple constraint curves together to obtain the final speed planning curve;

[0050] In this process, the multi-source speed limits include but are not limited to: road speed limit, curvature speed limit required to ensure safe driving on curved roads, driver's expected speed, and safe longitudinal speed limit required for the vehicle's current and future behavior decisions;

[0051] When performing autonomous driving on closed roads, different obstacles need to be considered separately and different attributes need to be set according to the obstacle type, motion state, road position, and vehicle decision, in order to achieve different interaction effects. For example, for obstacles in front of the lane, a certain safety distance needs to be maintained while avoiding collision with them. At the entrance and exit of the ramp, vehicles in different lanes have right-of-way relationships, and different interaction strategies with the target vehicle need to be set according to the different lanes.

[0052] According to the state information of obstacle j (j = 1, 2, ..., N, N is the number of obstacles), including the speed v obs_i , acceleration a obs_i , relative to the vehicle's position pos obs_i , length obs_i 、Width obs_i , calculate the future position information of the obstacle in the planning space, that is, the sampling points at each time relative to the initial position of the vehicle The location of s_obs_j i ;

[0053] At the same time, according to the speed of obstacle j, the safe distance safe_dis that needs to be maintained with it is calculated j ;

[0054] According to the current plan and environment status, including but not limited to the obstacle category, the lane position relationship with the vehicle, and the vehicle decision, the interaction attributes of the obstacle are set to the expected position expect_dis j to control;

[0055] The position list of obstacle j {s_obs_j}, the safety distance safe_dis j , expected position expect_dis j Together they are added to the planning space as constraints for obstacle j.

[0056] According to the current speed v of the vehicle curr , confirm t 0= Position v in velocity space at time 0 0 ;

[0057] And with v 0 t 0 = All elements of the feasible velocity point set V_list at time 0 0 , perform the following search process:

[0058] (1) Setting t i-1 The feasible speed point set V_list at the moment i-1 Elements in V_list i-1 For each element, under the premise of satisfying the vehicle dynamic constraints and smoothness requirements, search for t i The feasible speed point at time t i The feasible point set in the velocity space at time

[0059] (2) Setting t i The feasible speed point set at time The elements in the equation satisfy the vehicle dynamic constraints and the requirements of ride comfort. i-1 moment, can be used as The point set composed of the velocity points at the previous moment is set up for The elements in , calculated from arrive The price

[0060] (3) Among them, speed cost

[0061]

[0062] v speedlimit for The speed limit value of the speed planning curve at the speed point, w vel is the speed cost coefficient;

[0063] Acceleration cost w acc is the acceleration cost coefficient;

[0064] Cost of acceleration jerk =w jerk *|jerk|,w jerk is the acceleration cost coefficient, jerk is arrive The magnitude of the acceleration;

[0065] Planning distance cost w spatial is the distance cost coefficient, pos goal To plan the target distance, for The distance of the velocity point relative to the initial point;

[0066] Obstacle cost calculation:

[0067]

[0068] Among them, w overtake represents the cost of the target surpassing the obstacle, w follow Indicates the cost of the target following the obstacle. expect_dis is set according to the attributes of the obstacle set in step 103 and is a preset value related to the speed, category, and decision of the vehicle.

[0069] Finally, from arrive The cost calculation formula is:

[0070]

[0071] (4) Traversal For all elements in The smallest value As a node The parent node of As a node the cost;

[0072] Repeat the above process (1) to (4) until all T max feasible elements;

[0073] For all elements of the traversed planning space, from T max In all corresponding speed spaces, find the node with the smallest cost value as the final node, and then traverse forward continuously according to the parent node of the node to obtain the speed planning sequence, which is the final speed planning curve.

[0074] In the process of longitudinal speed planning of autonomous driving for closed road scenarios, the present application discretizes the planning space into two dimensions, time and speed, according to preset time and speed sampling intervals; in order to unify the planning information, both obstacle and environmental road information are projected into the planning space; taking the current state as the starting point, the dynamic programming algorithm is used to continuously search for feasible speed points in the order of time sampling, and at the same time, according to the preset cost function, the cost value of each speed point is calculated from the dimensions of safety, smoothness, comfort, etc.; by minimizing the cost value, the speed point at the final moment is confirmed, and then the final speed planning curve is generated through reverse search.

[0075] Figure 4 A schematic block diagram of a vehicle speed planning system 400 according to an embodiment of the present application is shown. Figure 4 As shown, the vehicle speed planning system 400 includes:

[0076] A state perception module 410 configured to obtain motion state data of the vehicle and one or more adjacent vehicles;

[0077] A map module 420 configured to obtain map environment data, wherein the map environment data includes data of the lane where the vehicle is located and the left and right adjacent lanes;

[0078] The speed planning module 430 is configured to: determine whether there is a lane change demand based on the motion state data and the map environment data; if so, determine the target vehicle that has the lane change demand, and determine the longitudinal distance space required for the target vehicle to complete the lane change; and perform dynamic speed planning based on the motion state data, the map environment data and the longitudinal distance space to generate a final speed planning curve.

[0079] The solution of the present application maps the road topology relationship and lane line type and length information of the high-precision map to the expected lane change intention and urgency of the surrounding vehicles. Therefore, compared with the solution that only perceives the movement trend of surrounding vehicles, the speed of the vehicle expected to change lanes can be adjusted earlier, so that comfortable following distance control and deceleration and yielding effects can be achieved with smaller acceleration and deceleration. At the same time, the innovative construction of the speed-time dynamic planning search space can achieve the accuracy requirements of vehicle speed control with a lower matrix dimension than the position-time planning space. The number of computational searches for planning the speed trajectory with a fixed prediction time is lower than the implementation plan of the position-time planning space, so it is suitable for low-cost and low-computing-power computing controllers.

[0080] The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the vehicle speed planning method of the present application is realized. The computer-readable medium referred to in the present application includes various types of computer storage media, which can be any available medium that a general or special computer can access. For example, the computer-readable medium may include RAM, ROM, EPROM, E2PROM, register, hard disk, removable disk, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other temporary or non-temporary medium that can be used to carry or store a desired program code unit in the form of an instruction or data structure and can be accessed by a general or special computer, or a general or special processor. As used herein, the disk usually copies data magnetically, while the dish uses a laser to optically copy data. The above combination should also be included in the protection scope of the computer-readable medium. The exemplary storage medium is coupled to the processor so that the processor can read and write information from / to the storage medium. In an alternative solution, the storage medium can be integrated into the processor. The processor and the storage medium can reside in an ASIC. The ASIC can reside in a user terminal. In the alternative, the processor and the storage medium may reside as discrete components in a user terminal (eg, an onboard vehicle system, an external diagnostic device).

[0081] The present application also provides a computer device, including a storage module, a processor, and a computer program stored on the storage module and executable on the processor, wherein the vehicle speed planning method of the present application is implemented when the processor executes the computer program.

[0082] The present application also provides a computer program product, including a computer program, which implements the vehicle speed planning method of the present application when executed by a processor.

[0083] The present application also provides a vehicle, the vehicle comprising the vehicle speed planning system of the present application. The vehicle referred to in the present application may represent any appropriate vehicle having a drive system consisting of at least a battery, a power conversion device, and a drive motor, such as a hybrid vehicle, an electric vehicle, a plug-in hybrid electric vehicle, etc. A hybrid vehicle is a vehicle having two or more power sources, such as a gasoline-powered and an electric vehicle.

[0084] The specific embodiments described above in this application are only for more clearly describing the principles of this application, wherein each component is clearly shown or described to make the principles of this application easier to understand. Without departing from the scope of this application, those skilled in the art can easily make various modifications or changes to this application. Therefore, it should be understood that these modifications or changes should be included in the scope of patent protection of this application.

Claims

1. A vehicle speed planning method, characterized in that: The method comprises: Obtaining motion state data of the vehicle and one or more adjacent vehicles; Acquiring map environment data, wherein the map environment data includes data of the lane where the vehicle is located and the left and right adjacent lanes; Determining whether there is a need to change lanes based on the motion state data and the map environment data; If yes, determining a target vehicle that has a lane change requirement, and determining a longitudinal distance space required for the target vehicle to complete the lane change; Dynamic speed planning is performed based on the motion state data, the map environment data and the longitudinal distance space to generate a final speed planning curve.

2. The vehicle speed planning method according to claim 1, characterized in that: The motion state data includes: vehicle speed data and vehicle positioning data.

3. The vehicle speed planning method according to claim 1, characterized in that: The map environment data includes: topological connectivity of lanes, lane line types at lane boundaries, lane types, and lane section lengths.

4. The vehicle speed planning method according to claim 1, characterized in that: The dynamic speed planning further comprises: Mapping the motion state data, the map environment data and the longitudinal distance space to a planning space; discretizing the planning space; Convert the received multi-source speed constraints into a speed planning curve; Calculating a cost function based on the speed planning curve; and The final velocity planning curve is selected based on the cost function.

5. The vehicle speed planning method according to claim 4, characterized in that: The multi-source speed limits include: road speed limit, curvature speed limit required to ensure driving safety on curved roads, expected driving speed, and safe longitudinal speed limit required for the vehicle's current and future behavior decisions.

6. A vehicle speed planning system, characterized in that: The system comprises: A state perception module configured to obtain motion state data of the vehicle and one or more adjacent vehicles; A map module configured to obtain map environment data, wherein the map environment data includes data of a lane where the vehicle is located and left and right adjacent lanes; The speed planning module is configured to: Determining whether there is a need to change lanes based on the motion state data and the map environment data; If yes, determining a target vehicle that has a lane change requirement, and determining a longitudinal distance space required for the target vehicle to complete the lane change; And dynamic speed planning is performed based on the motion state data, the map environment data and the longitudinal distance space to generate a final speed planning curve.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the vehicle speed planning method according to any one of claims 1 to 5 is implemented.

8. A computer device comprising a storage module, a processor, and a computer program stored in the storage module and executable on the processor, characterized in that: When the processor executes the computer program, the vehicle speed planning method according to any one of claims 1 to 5 is implemented.

9. A computer program product, comprising a computer program, which, when executed by a processor, implements the vehicle speed planning method according to any one of claims 1 to 5.

10. A vehicle, characterized in that: The vehicle comprises a vehicle speed planning system as claimed in claim 6.

Images