Vehicle control method, device and vehicle

Abstract

The vehicle control method, device and vehicle provided by the present disclosure relate to intelligent driving technology, and include the following steps: determining a first scene corresponding to a vehicle and influencing a road shape, and a first path corresponding to the first scene, according to acquired external environment information of the vehicle, global path planning information, and a preset matching mode; determining a second scene on the first path and influencing a road speed, and a position of the second scene, according to a preset map; updating the first path according to the position of the second scene and the acquired position of the vehicle; processing the updated first path according to a preset motion planning to obtain a target path; and controlling the driving of the vehicle according to the target path. The present scheme can take scene analysis as a part of decision-making, so that the scene analysis and the planning module have unified judgment standards, and thus the success rate of scene switching can be improved.

Description

Technical Field

[0001] This disclosure relates to intelligent driving technology, and more particularly to a vehicle control method, device, and vehicle. Background Technology

[0002] Currently, in L3 level autonomous vehicles, vehicle control solutions can include scenario analysis, decision planning, and motion planning. The results of motion planning can be used for vehicle motion control.

[0003] In existing technologies, the rules for scene switching in scene analysis are set offline. When the preset rules are met, the scene analysis can output the identity document (ID) of the scene to be switched to. Based on the scene ID, decision planning and motion planning are triggered, and the vehicle is motion controlled according to the obtained motion planning results.

[0004] However, the scenario analysis process described above obtains the scenario ID based on preset rules, without considering the feasibility of downstream decision planning and motion planning, which reduces the success rate of scenario switching. Summary of the Invention

[0005] This disclosure provides a vehicle control method, apparatus, and vehicle to improve the success rate of scene switching in the prior art.

[0006] According to a first aspect of this disclosure, a vehicle control method is provided, comprising:

[0007] Based on the acquired vehicle's external environment information, global path planning information, and preset matching method, the first scene affecting the road shape corresponding to the vehicle and the first path corresponding to the first scene are determined.

[0008] Based on the preset map, determine the second scene affecting road speed on the first path, and the location of the second scene;

[0009] Update the first path based on the location of the second scene and the obtained location of the vehicle;

[0010] The updated first path is processed according to the preset motion plan to obtain the target path; the vehicle's movement is controlled according to the target path.

[0011] According to a second aspect of this disclosure, a vehicle control device is provided, comprising:

[0012] The path decision unit is used to determine the first scenario affecting the road shape corresponding to the vehicle and the first path corresponding to the first scenario based on the acquired external environment information of the vehicle, global path planning information, and preset matching method.

[0013] The speed decision unit is used to determine, based on a preset map, a second scene affecting road speed on the first path, and the location of the second scene;

[0014] The speed decision unit is further configured to update the first path based on the location of the second scene and the obtained location of the vehicle;

[0015] The motion planning unit is used to process the updated first path according to the preset motion plan to obtain the target path; and to control the driving of the vehicle according to the target path.

[0016] According to a third aspect of this disclosure, a vehicle control device is provided, including a memory and a processor; wherein,

[0017] The memory is used to store computer programs;

[0018] The processor is configured to read a computer program stored in the memory and execute the vehicle control method as described in the first aspect according to the computer program in the memory.

[0019] According to a fourth aspect of this disclosure, a computer-readable storage medium is provided, wherein computer-executable instructions are stored therein, which, when executed by a processor, implement the vehicle control method as described in the first aspect.

[0020] According to a fifth aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the vehicle control method as described in the first aspect.

[0021] According to a sixth aspect of this disclosure, a vehicle is provided, including a vehicle control device; the vehicle control device controls the driving of the vehicle; wherein the vehicle control device is the vehicle control device described in the third aspect.

[0022] The vehicle control method, device, and vehicle disclosed herein include: determining a first scene affecting road shape and a first path corresponding to the first scene based on acquired external environment information, global path planning information, and a preset matching method; determining a second scene affecting road speed and its location on the first path based on a preset map; updating the first path based on the location of the second scene and the acquired vehicle position; processing the updated first path according to a preset motion plan to obtain a target path; and controlling the vehicle's movement based on the target path. In the vehicle control method, device, and vehicle provided by this solution, scene analysis can be incorporated as part of the decision-making process, unifying the judgment criteria between the scene analysis and planning modules, thereby improving the success rate of scene switching. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of this disclosure or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the control framework of a vehicle shown in an exemplary embodiment of the present disclosure;

[0025] Figure 2 This is a schematic diagram illustrating a lane-changing scenario, as shown in an exemplary embodiment of this disclosure.

[0026] Figure 3 This is a schematic flowchart illustrating a vehicle control method as an exemplary embodiment of the present disclosure;

[0027] Figure 4 A schematic flowchart illustrating a vehicle control method as another exemplary embodiment of this disclosure;

[0028] Figure 5 This is a structural diagram of a vehicle control device shown as an exemplary embodiment of the present disclosure;

[0029] Figure 6 This is a structural diagram of a vehicle control device shown as an exemplary embodiment of the present disclosure. Detailed Implementation

[0030] With the development of autonomous driving technology and the increasing sophistication of traffic regulations for autonomous driving, the demand for mass production of high-level autonomous driving is becoming increasingly clear. Level 2 and lower-level assisted driving solutions focus more on the participation of the driving subject (i.e., the driver). The driver's judgment based on the environment, combined with the vehicle's own state (such as steering mechanism state, powertrain state, and cockpit signals), undergoes rule-based arbitration to output corresponding assisted driving enable signals while ensuring safety, and completes the control of the actuators, thereby completing the assisted driving behavior. Level 3 autonomous driving, or conditional driverless driving, allows the vehicle to perform most functional operations and handle most situations independently. However, the driver must always maintain attention and be ready to take over the vehicle in emergencies. Unlike Level 2, Level 3 autonomous driving vehicles can perform scene analysis and automatic function switching under certain conditions, such as autonomously selecting structured roads for driving and parking, autonomously choosing lane changes and overtaking, automatic obstacle avoidance, and intelligent obstacle avoidance. Compared to Level 2 functions, the decision-planning framework is particularly important in Level 3 autonomous driving. Figure 1As shown, existing vehicle control solutions can include scenario analysis, decision-making planning, and motion planning. The results of motion planning can be used for vehicle motion control. Currently, rule-based scenario analysis is mostly adopted to distinguish scenarios that an autonomous vehicle may encounter during driving (such as going straight, lane changing, obstacle avoidance, overtaking, entering and leaving ramps, stopping at intersections, etc.), and the results are output to the decision-making planning and motion planning modules in the form of scenario IDs. The decision-making planning and motion planning are triggered based on this scenario ID. Then, the decision-making planning obtains a rough path based on external input information, perception information, and the vehicle's own state information, etc. The motion planning optimizes this rough path, and thus the vehicle is motion-controlled according to the obtained results of motion planning.

[0031] The distinction of scenarios is often based on rules set offline, such as Figure 2 As shown, taking the lane-changing scenario as an example for illustration. The vehicle itself is the middle vehicle, the vehicle in front is vehicle A, and the vehicle behind in the left lane is vehicle B. In scenario analysis, based on the rules for determining lane change (such as within a distance L1 in front of the vehicle itself, there is a vehicle in front with a speed lower than the vehicle's own speed, and there is no other vehicle behind in the left lane, or there are other vehicles, but the vehicle distance is greater than L2 and the speed is lower than the vehicle's own speed), it is judged that there is a vehicle A with a speed Va lower than the vehicle's own speed V0 at a distance La (La < L1) in front, there is a vehicle behind in the left lane, and there is a vehicle B with a speed Vb lower than the vehicle's own speed V0 at a distance Lb (Lb > L2) behind. Both the distance and speed meet the lane-changing rules. According to the rules, it is determined that the scenario analysis outputs a lane-changing scenario ID at this time, triggering the lane-changing logic of decision-making planning and motion planning.

[0032] However, in the above method, the scenario analysis process obtains the scenario ID based on preset rules, and the switching logic is rigid. The rule-based judgment is first somewhat blind and does not consider the feasibility of downstream decision-making planning and motion planning. The separation from the planning module (the planning module includes decision-making planning and motion planning) will greatly reduce the success rate of scenario switching. Moreover, the scalability of the above method is poor. The rule-based scenario judgment needs to judge the next scenario based on the current scenario. The switching conditions between adjacent scenarios are strongly related to the scenario type, and if scenarios are added or reduced, it will affect the entire scenario analysis logic.

[0033] To address the aforementioned technical issues, the solution provided in this disclosure categorizes scenarios into those affecting road shape and those affecting road speed. Scene analysis is integrated into the decision-making and planning process, unifying the judgment criteria between the scenario analysis and planning modules. This improves the success rate of scenario switching and eliminates the redundant judgments inherent in traditional scenario analysis (where judgments are not precise, leading to unreliable results; decision-making and planning require repeated judgments on certain aspects to arrive at more accurate conclusions). This makes the entire process more efficient. Furthermore, scenario switching is decoupled from scenario type, meaning that adding or removing scenarios does not affect the overall scenario analysis logic, resulting in higher scalability.

[0034] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties. Furthermore, the collection, use and processing of the relevant data must comply with the relevant laws, regulations and standards of the relevant countries and regions, and corresponding operation portals are provided for users to choose to authorize or refuse.

[0035] The technical solutions of this disclosure and how they solve the aforementioned technical problems will be described in detail below with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of this disclosure will now be described with reference to the accompanying drawings.

[0036] Figure 3 This is a schematic flowchart illustrating a vehicle control method as an exemplary embodiment of the present disclosure.

[0037] like Figure 3 As shown, the vehicle control method provided in this embodiment includes:

[0038] Step 301: Based on the acquired external environment information of the vehicle, global path planning information, and preset matching method, determine the first scene that affects the road shape corresponding to the vehicle, and the first path corresponding to the first scene.

[0039] The method provided in this disclosure can be executed by vehicle control equipment.

[0040] This vehicle control device can be installed in the vehicle and can acquire information about the vehicle's external environment, as well as global path planning information.

[0041] The vehicle's external environment information refers to information about the vehicle's external environment sensed by sensors installed on the vehicle. For example, this could be radar information sensed by radar installed on the vehicle, or image information sensed by cameras installed on the vehicle.

[0042] Global path planning information refers to the navigation information within the vehicle, which is a purely geometric path planning from the starting point to the destination, independent of time series and vehicle dynamics. Global path planning information can be determined based on map information set within the vehicle, the vehicle's current location, and the location of the destination point.

[0043] The preset matching method is a matching method that is pre-set according to the actual situation.

[0044] The first path may include location information.

[0045] Specifically, multiple scenarios that affect the road shape can be pre-set. Scenarios affecting road shape refer to those that influence the shape of the vehicle's subsequent path. These scenarios can include lane-changing scenarios and lane-keeping scenarios. Here, lane-changing refers to changing lanes, and lane-keeping refers to staying within the original lane.

[0046] Specifically, the system can utilize the acquired vehicle's external environment information and global path planning information, and perform matching according to a pre-set matching method to find the first scenario that affects the road shape corresponding to the vehicle. Then, based on the pre-set processing method corresponding to the first scenario, the first path corresponding to the first scenario can be determined.

[0047] Step 302: Based on the preset map, determine the second scene on the first path that affects road speed, and the location of the second scene.

[0048] The preset map is a map pre-installed on the vehicle, and this map can be a high-precision map.

[0049] This allows for the pre-setting of multiple scenarios that affect road speed. Scenarios affecting road shape refer to those that influence speed at certain locations along the first path. These scenarios can include those where traffic rules dictate that stopping may be required, such as intersections or traffic light scenarios.

[0050] Specifically, based on a preset map, a second scenario affecting road speed can be matched along the first path. This second scenario can include multiple scenarios. The positions of these multiple second scenarios along the first path can then be determined.

[0051] Step 303: Update the first path based on the location of the second scene and the obtained vehicle location.

[0052] Specifically, the vehicle's position can be determined and obtained based on the high-precision positioning device pre-installed in the vehicle.

[0053] Specifically, based on the positions of each second scene and the vehicle's position, the position of the first second scene ahead of the vehicle on the first path can be determined. The speed at and after that second scene position on the first path is then set to 0, updating the first path to obtain the updated first path.

[0054] Specifically, the updated first path is a coarse path.

[0055] Step 304: Process the updated first path according to the preset motion plan to obtain the target path; control the vehicle's movement according to the target path.

[0056] The preset motion plan is a motion planning method pre-set according to actual conditions. The preset motion plan can process the updated first path to obtain the target path. This allows the updated first path to be further smoothed and meets vehicle constraint and comfort requirements.

[0057] The target path may include location information, speed information, and time information.

[0058] Specifically, the vehicle's movement can be controlled based on the obtained target path.

[0059] The vehicle control method disclosed herein includes: determining a first scenario affecting road shape and a first path corresponding to the first scenario based on acquired external environment information, global path planning information, and a preset matching method; determining a second scenario affecting road speed on the first path and its location based on a preset map; updating the first path based on the location of the second scenario and the acquired vehicle position; processing the updated first path according to a preset motion plan to obtain a target path; and controlling the vehicle's movement according to the target path. In this method, scenarios can be divided into scenarios affecting road shape and scenarios affecting road speed, and scenario analysis is incorporated as part of the decision-making and planning process. This unifies the judgment criteria between the scenario analysis and planning modules, thereby improving the success rate of scenario switching and eliminating redundant judgments in the original scenario analysis, making the entire process more efficient. The switching between scenarios is decoupled from the scenario type; correspondingly, adding or removing scenarios will not affect the overall scenario analysis logic, resulting in higher scalability.

[0060] Figure 4 This is a schematic flowchart illustrating a vehicle control method as another exemplary embodiment of the present disclosure.

[0061] like Figure 4 As shown, the vehicle control method provided in this embodiment includes:

[0062] Step 401: Based on the acquired external environment information of the vehicle and global path planning information, match multiple scenarios that affect the road shape in sequence until a match is successful, and determine the first successfully matched scenario and the first path corresponding to the first scenario.

[0063] Specifically, multiple scenes that affect the shape of the road can be pre-set, and the matching order of each scene can be pre-set.

[0064] Specifically, by using the acquired external environment information of the vehicle and global path planning information, multiple scenarios affecting the road shape can be matched sequentially according to a pre-set matching order until a match is successful. The successfully matched scenario is then identified as the first scenario, and the first path corresponding to the first scenario can be determined.

[0065] In one feasible approach, the scenarios affecting road shape, in the order of matching, include: lateral movement scenarios, lane changing scenarios, obstacle avoidance scenarios, and driving within lanes scenarios.

[0066] Specifically, scenarios that affect road shape can include lateral movement scenarios, lane changing scenarios, obstacle avoidance scenarios, and driving within lanes scenarios.

[0067] Specifically, the matching order of scenarios that affect road shape, arranged from highest to lowest priority, can be: lateral movement scenario, lane change scenario, obstacle avoidance scenario, and driving within the lane scenario.

[0068] In lateral movement scenarios, such as when a large vehicle is traveling alongside your vehicle in the adjacent lane, creating a sense of pressure, your vehicle can veer to one side within your lane.

[0069] Among them, obstacle avoidance scenario refers to the situation where there is an obstacle in front of the vehicle in the lane, and the vehicle needs to avoid the obstacle in the lane to continue driving.

[0070] If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are not met, then the system will jump to the next scenario to continue matching; the current matching scenario is any one of the following: side-shift scenario, lane-change scenario, or obstacle avoidance scenario.

[0071] Specifically, matching conditions can be pre-set for each scenario that affects road shape. Then, using the vehicle's external environment information and global path planning information, the system matches the conditions for the lateral movement scenario. If no match is found, the system matches the conditions for the lane change scenario, and so on, matching the conditions for the obstacle avoidance scenario.

[0072] If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions for the current matching scenario are met, but the preset safety conditions corresponding to the current matching scenario are not met, then the process will jump to the next scenario to continue matching.

[0073] Specifically, safety conditions can be pre-set for each scenario that affects the road shape. These safety conditions can include those designed to prevent collisions between vehicles and other objects.

[0074] Specifically, based on the vehicle's external environment information and global path planning information, it is matched with the preset conditions corresponding to the current matching scenario. If it is determined that the preset conditions of the current matching scenario are met, it is then matched with the preset safety conditions corresponding to the current matching scenario. If it is determined that the preset safety conditions corresponding to the current matching scenario are not met, it jumps to the next scenario to continue matching.

[0075] If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions for the current matching scenario are met, and the preset safety conditions corresponding to the current matching scenario are also met, then matching stops, and the matching is confirmed as successful. The current matching scenario is then designated as the first scenario, and the first path corresponding to the first scenario is determined. Matching continues until the first scenario is detected to have been completed, and then matching begins sequentially from the side-moving scenario.

[0076] Specifically, if, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions for the current matching scenario are met, and simultaneously, the preset safety conditions corresponding to the current matching scenario are also met, then matching stops and is confirmed as successful. The current matching scenario is then designated as the first scenario. Next, the first path corresponding to the first scenario can be determined according to the pre-set processing method corresponding to the first scenario.

[0077] Specifically, if the first scenario is a lateral movement scenario, the center line of the lane can be shifted, and the shifted center line can be used as the first path.

[0078] Specifically, if the first scenario is a lane-changing scenario, the first path can be determined based on a pre-set polynomial curve.

[0079] Specifically, if the first scenario is an obstacle avoidance scenario, several points that do not affect passage can be selected next to the obstacle, and these points can be connected to obtain the first path.

[0080] Specifically, after the first scene is completed, a start matching command is generated. When this start matching command is detected, it can be determined that the first scene has been completed, and the next round of matching begins according to the command, still starting with the side-moving scenes.

[0081] Optionally, if the current matching scenario is an obstacle avoidance scenario, and it is determined, based on the vehicle's external environment information and global path planning information, that the preset conditions for the obstacle avoidance scenario are not met, or that the preset safety conditions corresponding to the obstacle avoidance scenario are not met, then the driving scenario within the lane is determined as the first scenario.

[0082] Specifically, if the current scenario is an obstacle avoidance scenario, and the vehicle's external environment information and global path planning information are matched with the preset conditions corresponding to the obstacle avoidance scenario, and it is determined that the preset conditions of the obstacle avoidance scenario are not met, then the driving scenario within the lane is determined as the first scenario.

[0083] Alternatively, if the current scenario is an obstacle avoidance scenario, and the vehicle's external environment information and global path planning information are matched with the preset conditions corresponding to the obstacle avoidance scenario, and it is determined that the preset conditions of the obstacle avoidance scenario are met, then the vehicle's external environment information and global path planning information are matched with the preset safety conditions corresponding to the obstacle avoidance scenario. If it is determined that the preset safety conditions corresponding to the obstacle avoidance scenario are not met, then the driving scenario within the lane is determined as the first scenario.

[0084] Specifically, if the first scenario is a driving scenario within a lane, then the center line of this lane can be used as the first path.

[0085] Furthermore, it can receive a forced lane change command and, based on this command, determine the lane-changing scenario as the first scenario. Then, based on this scenario, it determines the first path. The forced lane change command can be a command determined based on the driver's actions.

[0086] Specifically, behavior trees can be used to determine the first scenario and the first path. A behavior tree is a formal graphical modeling language. In a behavior tree, each scenario affecting the road shape can be treated as a sequence node, and the root node is a fallback node. Each scenario affecting the road shape is executed from left to right, and the order of these scenarios is set offline, with priority decreasing from left to right. Typically, the default scenario affecting the road shape is the lane following scenario, so LaneFollowing is on the far right in the path decision behavior tree.

[0087] A sequence can contain four leaf nodes: Request, Ready, Plan, and Force Approve, which represent the decision-making process for each scenario that affects the shape of the road.

[0088] Request: Checks if there is a request in the current matching scenario;

[0089] Ready: The preparation phase, checking whether it is safe to proceed with the next step (plan);

[0090] Plan: Calculates the first path corresponding to the current matching scenario and outputs it as the current matching scenario. It will remain in the running state until its internal state returns "success" and will not be transferred to another Sequence.

[0091] Force Approve: A node specific to lane changes that overrides the "Ready" result when a forced lane change command is issued externally.

[0092] Taking a lane change scenario as an example, if the vehicle is on a multi-lane road and its lane is not the optimal lane on the route, Request returns True; if the lane change path does not conflict with the trajectories of other obstacles in the space, Ready returns true; Plan is the calculated path, generating a lane change path based on the current lane and the target lane. The behavior tree will not jump to another sequence until Plan returns true. The path calculated by Plan will be used as the output of Lane Change. The path calculated by Plan is the lane change path and is also the output of this sequence. Force Approve is a human intervention signal that can be used for remote control.

[0093] Specifically, using behavior trees to manage scenarios is more efficient and has better scalability.

[0094] Step 402: Based on the preset map, determine the second scene on the first path that affects road speed, and the location of the second scene.

[0095] The preset map is a map pre-installed on the vehicle, and this map can be a high-precision map.

[0096] This can include pre-setting multiple scenarios that affect road speed. Scenarios affecting road shape refer to those that influence speed at certain locations along the first path. These scenarios can include those requiring vehicles to stop according to traffic rules, such as intersections or traffic lights.

[0097] Specifically, based on a preset map, a second scenario affecting road speed can be matched along the first path. This second scenario can include multiple scenarios. The positions of these multiple second scenarios along the first path can then be determined.

[0098] In one possible implementation, the scenarios affecting road speed include one or more of the following combinations: stop line scenarios, pedestrian crossing scenarios, intersection scenarios, and traffic light scenarios.

[0099] Specifically, scenarios that affect road speed can include one or more of the following combinations: stop line scenarios, pedestrian crossing scenarios, intersection scenarios, and traffic light scenarios.

[0100] Among them, the stop line scenario can refer to the presence of a stop line within a preset distance in front of the vehicle.

[0101] Among them, the pedestrian crossing scenario can refer to the existence of a pedestrian crossing within a preset distance in front of the vehicle.

[0102] The intersection scenario refers to an intersection that exists within a preset distance ahead of the vehicle.

[0103] Among them, the traffic light scenario can refer to the presence of traffic lights within a preset distance in front of the vehicle.

[0104] Step 403: Based on the obtained vehicle location and the location of the second scene, determine the third scene closest to the vehicle from each of the second scenes, and the location of the third scene.

[0105] Specifically, the vehicle's location can be obtained through a positioning device installed in the vehicle.

[0106] Specifically, based on the vehicle's location and the locations of each second scene, the distance between the vehicle and each second scene can be determined, and the second scene closest to the vehicle can be selected as the third scene, and the location of the third scene can be recorded.

[0107] Step 404: Set the velocity of the position of the third scene in the first path and the velocity of the position after the position of the third scene to 0 to obtain the updated first path.

[0108] Specifically, in the first path, the velocity at the position of the third scene and the position after the third scene can be set to 0 to obtain the updated first path.

[0109] Specifically, a Module Manager can be used to manage speed decisions. Factors affecting speed, such as stop lines, crosswalks, intersections, and traffic lights, each constitute a speed-affecting scenario. The speed decision-making process involves selecting the primary factor influencing speed, i.e., the factor that first affects speed changes. Speed ​​decision-making combines the speed-influencing factors with the path decision result (i.e., the first path), ultimately outputting a rough trajectory as the final output of the Behavior Planning in this solution. In this solution, the Behavior Planning includes both path decision and speed decision.

[0110] The mode manager mainly performs three functions: loading the scenarios that affect speed (human-defined factors that affect vehicle speed); calculating the speed on the first path (analyzing the impact of each loaded scenario on speed); and outputting the most important factor affecting the current vehicle speed.

[0111] Specifically, this solution upgrades the simple output scene ID to path decision and speed decision, which can simplify scene types and reduce development workload.

[0112] Step 405: Process the updated first path according to the preset motion plan to obtain the target path; control the vehicle's movement according to the target path.

[0113] Specifically, the principle and implementation of step 405 are similar to those of step 304, and will not be repeated here.

[0114] Figure 5 This is a structural diagram of a vehicle control device shown as an exemplary embodiment of the present disclosure.

[0115] like Figure 5 As shown, the vehicle control device 500 provided in this disclosure includes:

[0116] The path decision unit 510 is used to determine the first scene that affects the road shape and the first path corresponding to the first scene based on the acquired external environment information of the vehicle, global path planning information and preset matching method.

[0117] Speed ​​decision unit 520 is used to determine, based on a preset map, a second scene affecting road speed on the first path, as well as the location of the second scene;

[0118] The speed decision unit 520 is also used to update the first path based on the location of the second scene and the obtained vehicle location;

[0119] The motion planning unit 530 is used to process the updated first path according to the preset motion plan to obtain the target path; and to control the vehicle's movement according to the target path.

[0120] The path decision unit 510 is specifically used to match multiple scenarios that affect the road shape in sequence based on the acquired external environment information of the vehicle and global path planning information, until a match is successful, and to determine the first successfully matched scenario and the first path corresponding to the first scenario.

[0121] The path decision unit 510 is specifically used to jump to the next scenario to continue matching if it determines, based on the vehicle's external environment information and global path planning information, that the preset conditions of the current matching scenario are not met. The current matching scenario is any one of the following: lateral movement scenario, lane change scenario, or obstacle avoidance scenario. The scenarios that affect the road shape, in the order of matching, include: lateral movement scenario, lane change scenario, obstacle avoidance scenario, and lane driving scenario.

[0122] If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions for the current matching scenario are met, but the preset safety conditions corresponding to the current matching scenario are not met, then the process will jump to the next scenario to continue matching.

[0123] If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions for the current matching scenario are met, and the preset safety conditions corresponding to the current matching scenario are also met, then matching stops, and the matching is confirmed as successful. The current matching scenario is then designated as the first scenario, and the first path corresponding to the first scenario is determined. Matching continues until the first scenario is detected to have been completed, and then matching begins sequentially from the side-moving scenario.

[0124] The path decision unit 510 is specifically used to determine the driving scenario within the lane as the first scenario if the current matching scenario is an obstacle avoidance scenario, and the vehicle's external environment information and global path planning information determine that the preset conditions of the obstacle avoidance scenario are not met, or the preset safety conditions corresponding to the obstacle avoidance scenario are not met.

[0125] The speed decision unit 520 is specifically used to determine the third scene closest to the vehicle from each of the second scenes, and the location of the third scene, based on the acquired vehicle position and the position of the second scene;

[0126] Set the velocity of the position of the third scene in the first path and the velocity of the positions after the third scene to 0 to obtain the updated first path.

[0127] In one possible implementation, the scenarios affecting road speed include one or more of the following combinations: stop line scenarios, pedestrian crossing scenarios, intersection scenarios, and traffic light scenarios.

[0128] Figure 6 This is a structural diagram of a vehicle control device shown as an exemplary embodiment of the present disclosure.

[0129] like Figure 6 As shown, the vehicle control device provided in this embodiment includes:

[0130] Memory 601;

[0131] Processor 602; and

[0132] Computer programs;

[0133] The computer program is stored in memory 601 and configured to be executed by processor 602 to implement any of the vehicle control methods described above.

[0134] This embodiment also provides a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement any of the vehicle control methods described above.

[0135] This embodiment also provides a computer program product, including a computer program that, when executed by a processor, implements any of the above-described vehicle control methods.

[0136] This embodiment also provides a vehicle, including a vehicle control device; the vehicle's movement is controlled by the vehicle control device; wherein, the vehicle control device is... Figure 6 Vehicle control equipment in the vehicle.

[0137] Those skilled in the art will understand that all or part of the steps of the above-described method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments; and the aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0138] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A vehicle control method, characterized in that, include: The scenarios affecting road shape, in the order of matching, include: lateral movement scenarios, lane changing scenarios, obstacle avoidance scenarios, and lane-keeping scenarios. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are not met, the process jumps to the next scenario to continue matching. The current matching scenario is any one of the lateral movement scenario, lane changing scenario, or obstacle avoidance scenario. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are met, but the preset safety conditions corresponding to the current matching scenario are not met, the process jumps to the next scenario to continue matching. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are met, and the preset safety conditions corresponding to the current matching scenario are met, the matching stops, and the matching is determined to be successful. The current matching scenario is designated as the first scenario, and the first path corresponding to the first scenario is determined. Matching continues sequentially from the lateral movement scenario until a start matching command generated after the first scenario is completed is detected. Based on the preset map, determine the second scene affecting road speed on the first path, and the location of the second scene; Update the first path based on the location of the second scene and the obtained location of the vehicle; The updated first path is processed according to the preset motion plan to obtain the target path; the vehicle's movement is controlled according to the target path.

2. The method according to claim 1, characterized in that, If the current matching scenario is the obstacle avoidance scenario, and based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the obstacle avoidance scenario are not met, or the preset safety conditions corresponding to the obstacle avoidance scenario are not met, then the driving scenario within the lane is determined to be the first scenario.

3. The method according to claim 1, characterized in that, The step of updating the first path based on the location of the second scene and the obtained location of the vehicle includes: Based on the obtained location of the vehicle and the location of the second scene, determine the third scene closest to the vehicle from each of the second scenes, and the location of the third scene; The velocity of the position of the third scene in the first path and the velocity of the position after the position of the third scene are set to 0 to obtain the updated first path.

4. The method according to any one of claims 1-3, characterized in that, The scenarios that affect road speed include one or more of the following combinations: stop line scenario, pedestrian crossing scenario, intersection scenario, and traffic light scenario.

5. A vehicle control device, characterized in that, include: The path decision unit is used to determine scenarios that affect road shape. These scenarios, in order of matching, include: lateral movement scenarios, lane changing scenarios, obstacle avoidance scenarios, and lane-keeping scenarios. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are not met, the system jumps to the next scenario to continue matching. The current matching scenario is any one of a lateral movement scenario, a lane changing scenario, or an obstacle avoidance scenario. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are met, but the preset safety conditions corresponding to the current matching scenario are not met, the system jumps to the next scenario to continue matching. If, based on the vehicle's external environment information and global path planning information, it is determined that the preset conditions of the current matching scenario are met, and the preset safety conditions corresponding to the current matching scenario are met, the matching stops, and a successful match is determined. The current matching scenario is designated as the first scenario, and the first path corresponding to the first scenario is determined. Matching continues sequentially from the lateral movement scenario until a start matching command generated after the first scenario is completed is detected. The speed decision unit is used to determine, based on a preset map, a second scene affecting road speed on the first path, and the location of the second scene; The speed decision unit is further configured to update the first path based on the location of the second scene and the obtained location of the vehicle; The motion planning unit is used to process the updated first path according to the preset motion plan to obtain the target path; and to control the driving of the vehicle according to the target path.

6. A vehicle control device, characterized in that, Includes memory and processor; among which, The memory is used to store computer programs; The processor is configured to read a computer program stored in the memory and execute the method described in any one of claims 1-4 according to the computer program in the memory.

7. A vehicle, characterized in that, Including vehicle control equipment; The vehicle is controlled by a vehicle control device; wherein the vehicle control device is the vehicle control device described in claim 6.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, implement the method described in any one of claims 1-4.

Images