Control method, device and equipment for autonomous vehicle and medium

Abstract

The embodiment of the invention discloses a control method, device and equipment for an automatic driving vehicle and a medium. The method comprises the following steps: acquiring an electronic map of a to-be-driven road section of an automatic driving vehicle; determining a target global path of a to-be-driven road section according to the electronic map; determining a local driving road section with an obstacle from the target global path, and acquiring local state data of the local driving road section; and determining a target local path according to the local state data, and controlling the driving data of the autonomous vehicle based on the target local path. According to the technical scheme, the driving data in the driving process of the automatic driving vehicle is determined through path planning and decision control, and safe and orderly driving of the vehicle is achieved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a control method, device, equipment and medium for an autonomous driving vehicle. Background Art

[0002] With the continuous development and in-depth research of driverless technology, people's comprehensive demand for driving and using driverless technology to improve their car travel experience is gradually becoming possible.

[0003] Path planning and collaborative control are key components of autonomous vehicles. Against the backdrop of the rapid development of artificial intelligence, correctly understanding the impact of data-driven vehicle path planning and collaborative control systems on vehicle intelligence and automation has important practical and theoretical significance.

[0004] In the current research on path planning for driverless cars, prediction methods are often used to determine the speed of the final point during speed planning. This speed planning method has a long response time and a large amount of calculation, and cannot quickly handle situations where obstacles suddenly appear on the driving path, and cannot better ensure the safety of autonomous driving. Summary of the invention

[0005] The present invention provides a control method, device, equipment and medium for an autonomous driving vehicle, which determines the driving data of the autonomous driving vehicle during driving through path planning and decision control, thereby realizing safe and orderly driving of the vehicle.

[0006] According to one aspect of the present invention, there is provided a method for controlling an autonomous driving vehicle, comprising:

[0007] Obtaining an electronic map of the road section where the autonomous driving vehicle is to travel;

[0008] Determining a target global path for the road section to be traveled according to the electronic map;

[0009] Determining a local driving section where an obstacle exists from the target global path, and acquiring local state data of the local driving section;

[0010] A target local path is determined according to the local state data, and driving data of the autonomous driving vehicle is controlled based on the target local path.

[0011] Optionally, an electronic map of the road section where the autonomous driving vehicle is to travel is obtained, including:

[0012] Obtain a coordinate system map of the road section where the autonomous driving vehicle is to travel;

[0013] The coordinate system map is converted into an electronic map of the road section where the autonomous driving vehicle is to travel; wherein the electronic map is composed of nodes and edges.

[0014] Optionally, determining a target global path of the road section to be traveled according to the electronic map includes:

[0015] Determine the starting point and the end point of the road section to be traveled on the electronic map;

[0016] A graph search algorithm is used to plan a path from the starting point to the end point to obtain a target global path.

[0017] Optionally, a graph search algorithm is used to perform path planning from the starting point to the end point to obtain a target global path, including:

[0018] Starting from the starting point, determining a target node and a search direction on the electronic map; wherein the target node is any node between the starting point and the end point;

[0019] A path search is performed according to the target node and the search direction to obtain a target global path.

[0020] Optionally, determining a target local path according to the local state data includes:

[0021] Obtaining a vehicle motion model of the autonomous driving vehicle;

[0022] Determining a driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data;

[0023] A target local path of the autonomous driving vehicle is determined according to the driving trajectory.

[0024] Optionally, determining the driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data includes:

[0025] Obtaining an evaluation function of the autonomous driving vehicle;

[0026] determining speed data and displacement data according to the vehicle motion model;

[0027] determining a vehicle position based on the speed data and the displacement data;

[0028] The driving trajectory of the autonomous driving vehicle is determined according to the vehicle position, speed data and evaluation function.

[0029] Optionally, controlling the driving data of the autonomous driving vehicle based on the target local path includes:

[0030] determining acceleration state data and deceleration state data of the autonomous driving vehicle based on the target local path;

[0031] adjusting the driving acceleration of the autonomous driving vehicle in real time according to the acceleration state data and the deceleration state data;

[0032] The safe distance of the autonomous driving vehicle is determined according to the driving acceleration to control the autonomous driving vehicle to maintain the safe distance.

[0033] According to another aspect of the present invention, there is provided a control device for an autonomous driving vehicle, comprising:

[0034] A map acquisition module, used to obtain an electronic map of the road section where the autonomous driving vehicle is to travel;

[0035] A global path determination module, used to determine a target global path of a road section to be traveled according to the electronic map;

[0036] A local driving section determination module, used to determine a local driving section where an obstacle exists from the target global path, and obtain local state data of the local driving section;

[0037] A driving data control module is used to determine a target local path according to the local state data, and control the driving data of the autonomous driving vehicle based on the target local path.

[0038] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0039] at least one processor; and

[0040] a memory communicatively connected to the at least one processor; wherein,

[0041] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the control method of the autonomous driving vehicle described in any embodiment of the present invention.

[0042] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the control method of the autonomous driving vehicle described in any embodiment of the present invention when executed.

[0043] The technical solution of the embodiment of the present invention is to obtain an electronic map of the road section to be traveled by the autonomous driving vehicle; determine the target global path of the road section to be traveled according to the electronic map; determine the local driving section with obstacles from the target global path, and obtain the local state data of the local driving section; determine the target local path according to the local state data, and control the driving data of the autonomous driving vehicle based on the target local path. This technical solution determines the driving data of the autonomous driving vehicle during its driving process through path planning and decision control, so as to realize safe and orderly driving of the car.

[0044] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0046] Figure 1 is a flow chart of a control method for an autonomous driving vehicle provided according to Embodiment 1 of the present invention;

[0047] Figure 2 is a flow chart of a control method for an automatic driving vehicle provided according to Embodiment 2 of the present invention;

[0048] Figure 3 is a schematic diagram of the structure of a control device for an autonomous driving vehicle provided according to a third embodiment of the present invention;

[0049] Figure 4 It is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. DETAILED DESCRIPTION

[0050] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0051] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0052] Embodiment 1

[0053] Figure 1 This is a flow chart of a control method for an autonomous driving vehicle provided according to Embodiment 1 of the present invention. This embodiment is applicable to the case of controlling an autonomous driving vehicle. The method can be executed by a control device for an autonomous driving vehicle. The control device for an autonomous driving vehicle can be implemented in the form of hardware and / or software. The control device for an autonomous driving vehicle can be configured in an electronic device with data processing capabilities. Figure 1 As shown, the method includes:

[0054] S110: Obtain an electronic map of the road section where the autonomous driving vehicle is to travel.

[0055] Among them, the road section to be traveled can be understood as the road section that the autonomous driving vehicle is going to travel. In this embodiment, the road section to be traveled can include the starting position and the end position of the road section. The electronic map can be understood as a map obtained by converting the coordinate system map. The electronic map in this embodiment can be composed of edges and nodes. The coordinate system map can be understood as using longitude and latitude coordinates to represent the location data of the road section to be traveled. In this embodiment, the coordinate system map of the road section to be traveled by the autonomous driving vehicle can be converted to obtain a corresponding electronic map to obtain an electronic map of the road section to be traveled by the autonomous driving vehicle.

[0056] In this embodiment, optionally, obtaining an electronic map of the road section where the autonomous driving vehicle is to travel includes: obtaining a coordinate system map of the road section where the autonomous driving vehicle is to travel; and converting the coordinate system map into an electronic map of the road section where the autonomous driving vehicle is to travel.

[0057] The electronic map is composed of nodes and edges. The coordinate system map can be understood as using longitude and latitude coordinates to represent the location data of the road section to be traveled. In this embodiment, the coordinate system map of the road section to be traveled by the autonomous driving vehicle can be directly obtained through the global positioning system of the autonomous driving vehicle.

[0058] In this embodiment, the specific method of converting the coordinate system map into an electronic map of the road section where the autonomous driving vehicle is to travel is to convert the coordinate system map into a directed graph consisting of edges and nodes, and then assign values ​​to the edges in the directed graph according to the road length, and generate an electronic map based on the assignment results.

[0059] In this embodiment, through such a setting, the coordinate system map can be converted into an electronic map, so that searching and traversing on the electronic map to determine the global path is more convenient and quick.

[0060] S120: Determine a target global path of the road section to be traveled according to the electronic map.

[0061] Among them, the target global path can be understood as a conventional global path that meets the requirements and is obtained by planning the road section to be traveled on the electronic map. The target global path in this embodiment can be understood as the shortest global path of the autonomous driving vehicle on the road section to be traveled. In this embodiment, the starting point and the end point of the road section to be traveled can be determined according to the electronic map, and then a search algorithm is used to search from the starting point to the end point to determine a global path that meets the requirements as the target global path. This embodiment uses global path planning to implement conventional path planning for a single vehicle. Given the coordinates of the target point, the optimal path is obtained by searching the current position of the unmanned vehicle and the known map to achieve high-level guidance of the movement of the car; wherein the target point can be understood as the starting point and the end point position.

[0062] In this embodiment, optionally, determining a target global path of the road section to be traveled according to an electronic map includes: determining a starting point and an end point of the road section to be traveled on the electronic map; and performing path planning from the starting point to the end point using a graph search algorithm to obtain a target global path.

[0063] The graph search algorithm may be used to search for paths in the graph structure of an electronic map. In this embodiment, the graph search algorithm may be a Dijkstra algorithm or an A* algorithm. In this embodiment, the corresponding graph search algorithm may be selected according to actual needs, and this embodiment does not limit this.

[0064] Specifically, in this embodiment, the coordinate system map is converted into a graph composed of edges and nodes, and then the road length is assigned to the edges in the graph, that is, the global path planning problem is abstracted into the shortest path planning problem with a weighted graph, and then the high-precision global map is abstracted into an electronic map that can be used by the algorithm. For the planning of the route of the conventional path of the car, the Dijkstra graph search algorithm is used, and the potential path search is performed on the driving section based on the prior road network information to plan a global path that meets the requirements. In this embodiment, when the graph search algorithm is used to plan the path from the starting point to the end point, all nodes on the electronic map will be traversed or greedily. The Dijkstra algorithm in this embodiment is suitable for calculating the shortest path planning of non-negative road weights, and the A* algorithm can calculate the shortest path from a node in the graph to all other nodes, and combines the Dijkstra algorithm and the BFS algorithm based on the greedy search strategy to improve the reliability and accuracy of path planning.

[0065] In this embodiment, through such a setting, the coordinate system map can be converted into an electronic map, and a global path that meets the requirements can be determined through a graph search algorithm, thereby improving the reliability of the target global path.

[0066] In this embodiment, optionally, a graph search algorithm is used to perform path planning from the starting point to the end point to obtain a target global path, including: starting from the starting point, determining the target node and search direction on the electronic map; performing a path search based on the target node and the search direction to obtain the target global path.

[0067] Among them, the target node is any node between the starting point and the end point. It can be understood that the target node can be the node that the autonomous driving vehicle is going to pass through by traversing from the starting point. In this embodiment, the target node can also be understood as a calculation node. The search direction can be understood as the direction of searching for the next node based on the target node. Specifically, in this embodiment, the starting point and end point of the road section that the driverless car is going to travel on the electronic map are first determined, and then the calculation node and search direction are determined based on the starting point and the end point, and then the search node is updated based on the calculation node and the search direction, and finally the optimal global path of the driverless car from the starting point to the end point is planned based on the updated search node, that is, the target global path is obtained.

[0068] In this embodiment, through such a setting, the target global path can be determined by searching according to each node on the planned path, so that the determined target global path is more accurate.

[0069] S130: Determine a local driving section where an obstacle exists from the target global path, and obtain local state data of the local driving section.

[0070] Among them, obstacles may include static obstacles and dynamic obstacles. Exemplarily, static obstacles may be roadblocks, trees or buildings, etc. Dynamic obstacles may be other vehicles, pedestrians or bicycles, etc. The local driving section may be understood as the local section of obstacles existing in the global path. There may be one or more local driving sections in this embodiment, which may be determined according to actual conditions; the starting point and the end point of the local driving section may be determined according to actual conditions. The local state data may be understood as the surrounding environment data and vehicle position data of the local driving section where obstacles exist. Among them, the surrounding environment data may specifically include the specific location distribution of obstacles.

[0071] In this embodiment, one or more local driving sections where obstacles exist can be determined from conventional target global path planning. In this embodiment, the specific method of obtaining local state data of the local driving section can be to obtain the surrounding environment data and vehicle position data of the local driving section where obstacles exist based on a local map established according to the environmental information within the local range sensed by the sensor.

[0072] Furthermore, in this embodiment, obtaining the surrounding local state data through the perception of the surrounding data may include multi-perspective lidar point cloud data fusion and multi-perspective image data fusion. Among them, multi-perspective same-modal data fusion, for the lidar point cloud data system collected by the multi-perspective lidar device, the original data level fusion is adopted. The specific test plan may be that two lidars deployed in the scene respectively collect the lidar point cloud data of the scene, and then send the collected data to the MEC unit in real time, and the data from different devices from the MEC unit are fused at the original data level, that is, the point cloud level, and a denser and more covered fused point cloud is obtained from the fusion of the two point clouds. For multi-perspective image data fusion, the features extracted from the image are used to fuse with the point cloud in the 3D space. In this embodiment, a perception model can be constructed based on multi-perspective lidar point cloud data fusion and multi-perspective image data fusion to further improve the vehicle perception performance and reliability.

[0073] S140. Determine a target local path according to the local state data, and control the driving data of the autonomous driving vehicle based on the target local path.

[0074] Among them, the target local path can be understood as a local path obtained by path planning through local state data. The target local path in this embodiment can be understood as a local path that meets the set requirements, wherein the set requirements can be a vehicle detour path that can reasonably avoid obstacles, or a local path that can reasonably avoid obstacles and has the shortest path, or a local path that meets the requirements of reasonably avoiding obstacles and having few path intersections, etc., which can be set according to actual needs. Driving data can be understood as the safe distance parameter between the autonomous driving vehicle and the front or rear vehicle, or it can also be speed data, etc. The target local path in this embodiment is to perform local path planning based on local state data, which can respond quickly to dynamic changes in the environment and provide precise guidance, thereby determining the local path. In local path planning, it is necessary to consider how the vehicle reaches the target position by the optimal path under multiple constraints. Among them, the various constraints mainly include environmental constraints and vehicle constraints, wherein environmental constraints can include road boundary constraints and obstacle vehicle constraints, etc.; vehicle constraints can include dynamic and kinematic constraints. In this embodiment, the dynamic window method (DWA) can be used to plan the local driving section where obstacles appear. The algorithm can also be adjusted according to the actual situation, and then the global path planning can be adjusted by combining the local planning, thereby improving the reliability of the driving path of the autonomous driving vehicle.

[0075] In this embodiment, the specific method of determining the target local path based on the local state data can be by determining the vehicle motion model used by the autonomous driving vehicle and determining the real-time speed data of the autonomous driving vehicle based on the local state data, determining the driving trajectory of the autonomous driving vehicle based on the vehicle motion model and the real-time speed data, and then determining the target local path of the autonomous driving vehicle based on the driving trajectory. Among them, the real-time speed data may include the real-time linear speed, angular velocity and other data of the autonomous driving vehicle. In this embodiment, the specific method of controlling the driving data of the autonomous driving vehicle based on the target local path can be by analyzing the acceleration trend of the autonomous driving vehicle in the free state and the deceleration trend of the collision with the front vehicle, setting the safety distance parameters related to the stationary state and the speed for the autonomous driving vehicle, and adjusting the driving data such as the vehicle driving acceleration in real time, so that each vehicle maintains a certain distance from the front vehicle to avoid collision.

[0076] It can be understood that in this embodiment, conventional path planning can be first performed according to the starting point and end point of the road section to be traveled by the autonomous driving vehicle to determine the target global path, and then refined local path planning can be performed on the local area where the obstacle area appears in the target global path to determine the target local path, and then the acceleration and deceleration trend of the autonomous driving vehicle is analyzed according to the target local path; the driving acceleration of the unmanned vehicle is adjusted in real time according to the analysis results; the front and rear vehicle distance that the autonomous driving vehicle needs to maintain is obtained according to the real-time adjusted driving acceleration. In this embodiment, the driving acceleration of the autonomous driving vehicle is adjusted in real time based on the planned vehicle driving path, so that in the process of multiple vehicles driving, the vehicle always maintains an appropriate front and rear vehicle distance, ensuring the controllability of the unmanned vehicle while taking into account the driving safety and efficiency.

[0077] The technical solution of the embodiment of the present invention obtains an electronic map of the road section to be traveled by the autonomous driving vehicle; determines the target global path of the road section to be traveled based on the electronic map; determines the local driving section with obstacles from the target global path, and obtains the local state data of the local driving section; determines the target local path based on the local state data, and controls the driving data of the autonomous driving vehicle based on the target local path. This technical solution determines the driving data of the autonomous driving vehicle during its driving process through path planning and decision control, so as to realize safe and orderly driving of the car.

[0078] Embodiment 2

[0079] Figure 2 This is a flow chart of a control method for an autonomous driving vehicle provided according to the second embodiment of the present invention. This embodiment is optimized based on the above embodiment. The specific optimization is: determining the target local path according to the local state data, including: obtaining the vehicle motion model of the autonomous driving vehicle; determining the driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data; determining the target local path of the autonomous driving vehicle according to the driving trajectory. Figure 2 As shown, the method includes:

[0080] S210: Obtain an electronic map of the road section where the autonomous driving vehicle is to travel.

[0081] S220: Determine the target global path of the road section to be traveled according to the electronic map.

[0082] S230: Determine a local driving section where an obstacle exists from the target global path, and obtain local state data of the local driving section.

[0083] S240: Obtain a vehicle motion model of the autonomous driving vehicle.

[0084] Among them, the vehicle motion model may include a non-omnidirectional vehicle model and an omnidirectional vehicle model. In this embodiment, for the non-omnidirectional vehicle model, the vehicle movement mode may be set to non-omnidirectional, that is, forward and rotation, so that at adjacent moments in milliseconds, the vehicle's motion trajectory may be considered a straight line; for the omnidirectional vehicle model, although at adjacent moments in milliseconds, the vehicle's motion trajectory may still be considered a straight line, the vehicle's motion may perform translation in addition to forward and rotation.

[0085] In this embodiment, a non-omnidirectional mobile vehicle model and an omnidirectional mobile vehicle model of the autonomous driving vehicle can be determined based on the kinematic characteristics and dynamic characteristics of the autonomous driving vehicle. In this embodiment, the vehicle motion model corresponding to the current autonomous driving vehicle can be directly obtained.

[0086] S250: Determine the driving trajectory of the autonomous driving vehicle based on the vehicle motion model and local state data.

[0087] In this embodiment, the motion sampling method can be used to plan the local driving section containing obstacles. After obtaining the determined vehicle motion model, the vehicle driving trajectory is inferred based on the body length of the autonomous driving vehicle, the real-time speed information obtained by sampling, the evaluation function, and the reserved braking distance.

[0088] In this embodiment, optionally, the driving trajectory of the autonomous driving vehicle is determined based on the vehicle motion model and local state data, including: obtaining an evaluation function of the autonomous driving vehicle; determining speed data and displacement data based on the vehicle motion model; determining the vehicle position based on the speed data and displacement data; and determining the driving trajectory of the autonomous driving vehicle based on the vehicle position, speed data and the evaluation function.

[0089] Among them, the speed data can be understood as the current speed and linear speed of the sampled autonomous driving vehicle. In this embodiment, the current data of the autonomous driving vehicle can be sampled by setting the speed resolution. The displacement data can be understood as the displacement data of the autonomous driving vehicle in the corresponding direction. The vehicle position can be a real-time position determined based on the determined speed data and displacement data. The evaluation function can be a trajectory evaluation function obtained by evaluating and estimating based on multiple influencing factors. Specifically, the evaluation function can be an evaluation function estimated based on factors such as the vehicle avoiding obstacles, the vehicle orientation, and faster speed driving data. In this embodiment, the real-time speed of the autonomous driving vehicle can be sampled by setting the speed resolution, while considering the impact of the vehicle motor performance on the acceleration, and the reserved braking distance to infer the vehicle's driving trajectory, and the evaluation function is estimated and determined from the influencing factors such as "vehicle avoiding obstacles", "vehicle orientation", and "driving at a faster speed".

[0090] After acquiring the vehicle motion model, this embodiment can determine the current position of the vehicle based on the vehicle sensor data, and determine the driving trajectory of the autonomous driving vehicle based on the collected real-time speed range and the trajectory evaluation function.

[0091] The specific method of determining the speed data and displacement data according to the vehicle motion model in this embodiment can determine the vehicle linear speed and displacement data according to different vehicle operation models. For a non-omnidirectional mobile vehicle model, the linear speed of the vehicle in the first direction and the movement displacement in the first direction can be determined accordingly. Exemplarily, the first direction can be the X direction. For an omnidirectional mobile vehicle model, the linear speed of the vehicle in the first direction and the movement displacement in the first direction, as well as the linear speed of the vehicle in the second direction and the movement displacement in the second direction can be determined accordingly. Exemplarily, the first direction can be the X direction; the second direction can be the Y direction. Here, only the first direction and the second direction are exemplified, and the specific direction can be determined according to actual needs.

[0092] In this embodiment, a specific method for determining the vehicle position based on the speed data and the displacement data is to determine the new coordinate position (x, y) of the vehicle, that is, the vehicle position, based on the acquired real-time linear speed data and the displacement data in the corresponding direction.

[0093] In this embodiment, the specific method of determining the driving trajectory of the autonomous driving vehicle based on the vehicle position, speed data and evaluation function is to determine the vehicle's driving trajectory by determining the vehicle's position and speed data, adjust the driving path by avoiding obstacles, and adjust the driving trajectory by the influence of the evaluation function on the driving path, so as to determine the final driving trajectory that meets the requirements.

[0094] Through such a setting in this embodiment, the driving trajectory of the autonomous driving vehicle can be planned and determined according to the differences in the vehicle motion model and the changes in the local state data, thereby improving the flexibility and accuracy of the driving trajectory.

[0095] S260: Determine a target local path of the autonomous driving vehicle according to the driving trajectory.

[0096] In this embodiment, a driving trajectory that meets actual needs can be selected from the inferred driving trajectory as the target local path of the autonomous driving vehicle.

[0097] In this embodiment, by determining the non-omnidirectional mobile car model or omnidirectional mobile car model to be used by the autonomous driving vehicle, and then obtaining the real-time linear speed, angular velocity and other data of the autonomous driving vehicle collected by the sensor, the vehicle position of the autonomous driving vehicle is determined according to the linear vehicle model and the data collected by the sensor, and then the set speed resolution and trajectory evaluation function are obtained, and then the driving trajectory of the autonomous driving vehicle is determined according to the vehicle position, speed resolution and trajectory evaluation function, and finally the optimal local path that meets the set requirements is selected according to the inferred driving trajectory of the autonomous driving vehicle.

[0098] S270. Control driving data of the autonomous driving vehicle based on the target local path.

[0099] In this embodiment, optionally, driving data of the autonomous driving vehicle is controlled based on the target local path, including: determining acceleration status data and deceleration status data of the autonomous driving vehicle based on the target local path; adjusting the driving acceleration of the autonomous driving vehicle in real time according to the acceleration status data and the deceleration status data; determining the safe distance of the autonomous driving vehicle according to the driving acceleration, so as to control the autonomous driving vehicle to maintain the safe distance.

[0100] The acceleration state data can be understood as the acceleration data of the autonomous driving vehicle in a free state. The deceleration state data can be understood as the speed data in the deceleration state if a collision occurs with the vehicle in front. The safe vehicle distance can include the safe distance from the vehicle in front and the safe distance from the vehicle behind.

[0101] In this embodiment, the acceleration data of the autonomous driving vehicle in a free state and the deceleration data of the collision with the vehicle in front can be analyzed based on the determined target local path. According to the acceleration trend of the autonomous driving vehicle in a free state and the deceleration trend of the collision with the vehicle in front, the safety distance parameters related to the vehicle's speed when the vehicle is stationary can be determined, and the vehicle's driving acceleration can be adjusted in real time so that the autonomous driving vehicle maintains a certain safety distance from the vehicles in front and behind to avoid collision.

[0102] Through such a setting in this embodiment, the autonomous driving vehicle can be cooperatively controlled based on the global path and the local path, so that the front and rear safe distances of the vehicles can be determined during the driving process, and the driverless car can be driven safely and orderly.

[0103] In addition, in this embodiment, during the testing phase of the autonomous driving vehicle, traffic simulation software can be used to construct road scenarios, and then the behavior of the autonomous driving vehicles in cooperative driving can be simulated to analyze the impact of different scenarios on the driving behavior of the car from aspects such as vehicle driving safety and operating performance.

[0104] Specifically, the safety distance of vehicles when driving can be analyzed by combining the actual road length of the vehicle inspection site, the physical properties of the vehicle and other factors. By comparing the vehicle spacing and the safety distance, the vehicle state can be judged. The micro-following model can be used and dynamically adjusted and optimized according to the traffic conditions of the inspection line. By analyzing the acceleration trend of the car in the free state and the deceleration trend of the collision with the front vehicle, the safety distance parameters related to the speed are set for the vehicles in the inspection line in the static state, the acceleration and deceleration behaviors of different vehicles are simulated, and the driving acceleration of the car is adjusted in real time so that each vehicle keeps a certain distance from the front vehicle to avoid collision. Considering that the headway time value of the self-driving car is smaller, a smaller headway time can be set. In addition, since there is no human intervention, the deviation from the optimal driving strategy is smaller, and the self-driving vehicle will be more patient than the human-driven vehicle when driving on the road. These can be achieved by adjusting the driving imperfection coefficient and driving impatience of the car. The adjustment range of the above two parameters is set to the interval [0,1].

[0105] During the test phase, the time window constraints, speed constraints, and vehicle distance constraints for the actual safe driving of the vehicle can be designed based on the completed path planning subtasks on the detection line road, by analyzing the motion properties of the vehicle to be detected, as well as the static environment of the road and obstacles, to ensure that the vehicle can pass through the detection area in an orderly and safe manner. During the driving process of the vehicle, the priority of the vehicle driving is set through the geographical location information such as the road and obstacles in the driving scene, and the vehicle following parameters are calculated. The vehicle driving safety evaluation index is combined with micro-simulation and on-site field testing to ensure that the autonomous driving vehicle drives safely and orderly in the detection area in scenarios such as vehicle starting, straight driving, and turning.

[0106] The technical solution of the embodiment of the present invention is to obtain an electronic map of the road section to be traveled by the autonomous driving vehicle; determine the target global path of the road section to be traveled according to the electronic map; determine the local driving section with obstacles from the target global path, and obtain the local state data of the local driving section; obtain the vehicle motion model of the autonomous driving vehicle; determine the driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data; determine the target local path of the autonomous driving vehicle according to the driving trajectory; and control the driving data of the autonomous driving vehicle based on the target local path. This technical solution determines the driving data of the autonomous driving vehicle during the driving process through path planning and decision control, so as to realize the safe and orderly driving of the car.

[0107] Embodiment 3

[0108] Figure 3 Schematic diagram of a control device for an autonomous driving vehicle according to Embodiment 3 of the present invention. Figure 3 As shown, the device comprises:

[0109] A map acquisition module 310 is used to acquire an electronic map of the road section where the autonomous driving vehicle is to travel;

[0110] A global path determination module 320, for determining a target global path of a road section to be traveled according to an electronic map;

[0111] A local driving section determination module 330 is used to determine a local driving section where an obstacle exists from the target global path, and obtain local state data of the local driving section;

[0112] The driving data control module 340 is used to determine the target local path according to the local state data, and control the driving data of the autonomous driving vehicle based on the target local path.

[0113] Optionally, the map acquisition module 310 is specifically used to obtain a coordinate system map of the road section to be traveled by the autonomous driving vehicle; convert the coordinate system map into an electronic map of the road section to be traveled by the autonomous driving vehicle; wherein the electronic map is composed of nodes and edges.

[0114] Optionally, the global path determination module 320 includes:

[0115] A location determination unit, used to determine the starting point and the end point of the road section to be traveled on the electronic map;

[0116] The path planning unit is used to plan the path from the starting point to the end point using a graph search algorithm to obtain a target global path.

[0117] Optionally, a path planning unit is specifically used to determine the target node and search direction on the electronic map starting from the starting point; wherein the target node is any node between the starting point and the end point; and perform a path search based on the target node and the search direction to obtain a target global path.

[0118] Optionally, the driving data control module 340 includes:

[0119] A model acquisition unit, used to acquire a vehicle motion model of the autonomous driving vehicle;

[0120] A driving trajectory determination unit, used to determine the driving trajectory of the autonomous driving vehicle based on the vehicle motion model and the local state data;

[0121] The target local path determination unit is used to determine the target local path of the autonomous driving vehicle according to the driving trajectory.

[0122] Optionally, a driving trajectory determination unit is specifically used to obtain an evaluation function of the autonomous driving vehicle; determine speed data and displacement data based on a vehicle motion model; determine a vehicle position based on the speed data and displacement data; and determine a driving trajectory of the autonomous driving vehicle based on the vehicle position, speed data and the evaluation function.

[0123] Optionally, the driving data control module 340 is specifically used to determine the acceleration status data and deceleration status data of the autonomous driving vehicle based on the target local path; adjust the driving acceleration of the autonomous driving vehicle in real time according to the acceleration status data and the deceleration status data; determine the safe distance of the autonomous driving vehicle according to the driving acceleration, so as to control the autonomous driving vehicle to maintain a safe distance.

[0124] A control device for an autonomous driving vehicle provided in an embodiment of the present invention can execute a control method for an autonomous driving vehicle provided in any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0125] Embodiment 4

[0126] Figure 4 1 is a schematic diagram of the structure of an electronic device provided according to Embodiment 4 of the present invention. The electronic device 10 is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device may also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0127] like Figure 4 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, ROM 12 and RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0128] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0129] The processor 11 may be a variety of general and / or dedicated processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a control method for an autonomous driving vehicle.

[0130] In some embodiments, the control method of the autonomous driving vehicle may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the control method of the autonomous driving vehicle described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the control method of the autonomous driving vehicle in any other appropriate manner (e.g., by means of firmware).

[0131] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0132] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0133] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, device, or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0134] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0135] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0136] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0137] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0138] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A control method for an autonomous driving vehicle, characterized in that: include: Obtaining an electronic map of the road section where the autonomous driving vehicle is to travel; Determining a target global path for the road section to be traveled according to the electronic map; Determining a local driving section where an obstacle exists from the target global path, and acquiring local state data of the local driving section; A target local path is determined according to the local state data, and driving data of the autonomous driving vehicle is controlled based on the target local path.

2. The method according to claim 1, characterized in that Obtain an electronic map of the road section where the autonomous driving vehicle is to travel, including: Obtain a coordinate system map of the road section where the autonomous driving vehicle is to travel; The coordinate system map is converted into an electronic map of the road section where the autonomous driving vehicle is to travel; wherein the electronic map is composed of nodes and edges.

3. The method according to claim 1, characterized in that Determining a target global path of the road section to be traveled according to the electronic map includes: Determine the starting point and the end point of the road section to be traveled on the electronic map; A graph search algorithm is used to plan a path from the starting point to the end point to obtain a target global path.

4. The method according to claim 3, characterized in that A graph search algorithm is used to plan a path from the starting point to the end point to obtain a target global path, including: Starting from the starting point, determining a target node and a search direction on the electronic map; wherein the target node is any node between the starting point and the end point; A path search is performed according to the target node and the search direction to obtain a target global path.

5. The method according to claim 1, characterized in that Determining a target local path according to the local state data includes: Obtaining a vehicle motion model of the autonomous driving vehicle; Determining a driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data; A target local path of the autonomous driving vehicle is determined according to the driving trajectory.

6. The method according to claim 5, characterized in that Determining a driving trajectory of the autonomous driving vehicle according to the vehicle motion model and the local state data includes: Obtaining an evaluation function of the autonomous driving vehicle; determining speed data and displacement data according to the vehicle motion model; determining a vehicle position based on the speed data and the displacement data; The driving trajectory of the autonomous driving vehicle is determined according to the vehicle position, speed data and evaluation function.

7. The method according to claim 1, characterized in that Controlling the driving data of the autonomous driving vehicle based on the target local path includes: determining acceleration state data and deceleration state data of the autonomous driving vehicle based on the target local path; adjusting the driving acceleration of the autonomous driving vehicle in real time according to the acceleration state data and the deceleration state data; The safe distance of the autonomous driving vehicle is determined according to the driving acceleration to control the autonomous driving vehicle to maintain the safe distance.

8. A control device for an autonomous driving vehicle, characterized in that: include: A map acquisition module, used to obtain an electronic map of the road section where the autonomous driving vehicle is to travel; A global path determination module, used to determine a target global path of a road section to be traveled according to the electronic map; A local driving section determination module, used to determine a local driving section where an obstacle exists from the target global path, and obtain local state data of the local driving section; A driving data control module is used to determine a target local path according to the local state data, and control the driving data of the autonomous driving vehicle based on the target local path.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the control method of the autonomous driving vehicle described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, which are used to enable a processor to implement the control method of an autonomous driving vehicle according to any one of claims 1 to 7 when executed.

Images