Automatic driving motion planning control system based on space-time decoupling and vehicle

Abstract

The invention relates to the technical field of automatic driving, in particular to an automatic driving motion planning control system based on space-time decoupling and a vehicle. The control system comprises a motion planning unit, a control instruction generation unit and a motion control unit. The motion planning unit is used for acquiring the state information, the environment perception information and the behavior prediction data of the vehicle, and planning the motion path and the motion speed of the vehicle in a layered manner according to the state information, the environment perception information and the behavior prediction data of the vehicle; the control instruction generation unit is used for generating a corresponding motion control instruction by taking the expected driving track as a target; and the motion control unit is used for correspondingly controlling each execution mechanism of the vehicle according to the motion control instruction so as to complete automatic driving of the vehicle. It can be seen that the trajectory planning problem is decomposed into two sub-problems of motion path planning and speed planning, the data processing efficiency and the response speed of the system are improved, and the response requirement of the complex traffic environment is met.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving technology, and in particular to an autonomous driving motion planning control system and vehicle based on time-space decoupling. Background Art

[0002] In recent years, with the rapid development of artificial intelligence and autonomous driving technology, autonomous vehicles have gradually become an important part of the future transportation system. Autonomous driving technology aims to reduce human operations, achieve autonomous driving of vehicles, and improve traffic safety and transportation efficiency. The progress in this field has not only promoted the development of intelligent transportation, but also greatly improved people's travel experience.

[0003] In the autonomous driving system, trajectory planning and trajectory control are two crucial components. In the related technologies, trajectory planning and control technologies have been implemented in engineering applications mainly through multi-objective optimization, dynamic programming and some basic control algorithms, and have made significant progress. However, with the complexity of the driving environment and the improvement of driving requirements, the trajectory planning algorithms in the related technologies have large computational complexity and poor real-time performance when dealing with complex traffic environments, making it difficult to meet the actual needs of autonomous driving vehicles. Especially in the face of highly dynamic and highly uncertain traffic environments, the computational efficiency and response speed of the autonomous driving motion control system in the related technologies cannot meet the requirements. Summary of the invention

[0004] The present application provides an autonomous driving motion planning and control system based on time-space decoupling, which aims to solve the technical problems of low computational efficiency and response speed of autonomous driving motion control systems in related technologies.

[0005] In a first aspect, the present application provides an autonomous driving motion planning and control system based on time-space decoupling, comprising: a motion planning unit, a control instruction generation unit, and a motion control unit;

[0006] The motion planning unit is used to obtain the vehicle's state information, environmental perception information and behavior prediction data, and plan the vehicle's motion path and motion speed according to the vehicle's state information, environmental perception information and behavior prediction data;

[0007] The control instruction generating unit is used to solve the motion path and motion speed based on the vehicle dynamics model to generate corresponding motion control instructions;

[0008] The motion control unit is used to perform corresponding control on each actuator of the vehicle according to the motion control instruction to complete the automatic driving of the vehicle.

[0009] In some possible designs, the motion planning unit includes a path planning module and a speed planning module;

[0010] The path planning module is used to plan multiple initial paths for the vehicle's movement based on the vehicle's state information, environmental perception information, and behavior prediction data using a dynamic planning method; and then use a quadratic planning method to determine the optimal path from the multiple initial paths as the vehicle's movement path;

[0011] The speed planning module is used to plan an optimal speed curve of the vehicle according to the state information of the vehicle and the movement path of the vehicle, and the speed curve is used to represent the movement speed of the vehicle.

[0012] In some possible designs, solving the motion path and motion speed based on the vehicle dynamics model to generate corresponding motion control instructions includes:

[0013] The vehicle dynamics model is linearized and discretized to construct a prediction model, and the prediction model is used to generate corresponding motion control instructions according to the motion path and motion speed.

[0014] In some possible designs, the motion control instructions include: direction control instructions, gear control instructions, acceleration control instructions, braking control instructions and lighting control instructions.

[0015] In some possible designs, the control instruction generation unit also includes a vehicle air resistance module, a vehicle steering mechanism module, a longitudinal dynamics module, a suspension dynamics module, a vehicle spin motion module and a longitudinal angular dynamics module.

[0016] In some possible designs, the control instruction generation unit is also used to obtain multiple parameter information output by the vehicle air resistance module, vehicle steering mechanism module, longitudinal dynamics module, suspension dynamics module, vehicle spin motion module and longitudinal angle dynamics module, and construct the vehicle dynamics model based on the multiple parameter information.

[0017] In some possible designs, the motion control system further includes an environment perception unit; the environment perception unit is used to obtain environment perception information of the current vehicle surrounding environment.

[0018] In some possible designs, the environmental perception unit is also used to obtain the speed, acceleration and motion trajectory information of the target object in the environmental perception information; the behavior prediction data includes the speed, acceleration and motion trajectory information of the target object.

[0019] In a second aspect, the present application also provides an autonomous driving vehicle, which includes an autonomous driving motion planning control system as described in any one of the above items.

[0020] According to the automatic driving motion planning control system provided in the first aspect above, it includes: a motion planning unit, a control instruction generation unit and a motion control unit. Among them, the motion planning unit is used to obtain the vehicle's state information, environmental perception information and behavior prediction data, and plan the vehicle's motion path and motion speed according to the vehicle's state information, environmental perception information and behavior prediction data; the control instruction generation unit is used to solve the motion path and motion speed based on the vehicle dynamics model and generate corresponding motion control instructions; the motion control unit is used to perform corresponding control on each actuator of the vehicle according to the motion control instructions to complete the automatic driving of the vehicle. It can be seen that in this application, the trajectory planning problem is decomposed into two sub-problems: motion path planning and speed planning, which improves the data processing efficiency and response speed of the system to meet the response requirements of complex traffic environments.

[0021] Based on the implementations provided in the above aspects, this application can also be further combined to provide more implementations. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of the structure of an autonomous driving motion planning control system provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the signal flow when the vehicle motion control system provided by the embodiment of the present application is working;

[0024] Figure 3 A schematic diagram of the structure of a motion planning unit provided in an embodiment of the present application;

[0025] Figure 4 One of the schematic diagrams of path planning in a motion control system provided in an embodiment of the present application;

[0026] Figure 5 This is one of the speed planning schematic diagrams in the motion control system provided in the embodiment of the present application;

[0027] Figure 6 A schematic diagram of path planning and speed planning provided in an embodiment of the present application;

[0028] Figure 7 The second schematic diagram of path planning in the motion control system provided in the embodiment of the present application;

[0029] Figure 8 The third schematic diagram of path planning in the motion control system provided in the embodiment of the present application;

[0030] Fig. 9 The second schematic diagram of speed planning in the motion control system provided in the embodiment of the present application;

[0031] Fig.10The third schematic diagram of speed planning in the motion control system provided in the embodiment of the present application;

[0032] Fig.11 One of the schematic diagrams of the motion control system simulation experiment provided in the embodiment of the present application;

[0033] Fig.12 The second schematic diagram of the motion control system simulation experiment provided by the embodiment of the present application;

[0034] Fig.13 This is one of the schematic diagrams of trajectory tracking results in the embodiment of the present application;

[0035] Fig.14 This is the second schematic diagram of the trajectory tracking result in the embodiment of the present application. DETAILED DESCRIPTION

[0036] The technical solution in this application will be described below in conjunction with the accompanying drawings.

[0037] In the description of the embodiments of the present application, unless otherwise specified, “ / ” means or. For example, A / B can mean A or B. The “and / or” in this article is merely a way to describe the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0038] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this embodiment, unless otherwise specified, "plurality" means two or more.

[0039] In the autonomous driving system, trajectory planning and trajectory control are two crucial components. Trajectory planning refers to generating a driving route from the starting point to the end point for the autonomous driving vehicle based on the known traffic environment information and the target location. This process needs to consider factors such as the geometry of the road, traffic rules, obstacle locations, and the behavior of dynamic traffic participants. The goal of trajectory planning is to generate a smooth, feasible and safe path to ensure that the vehicle can reach the destination safely. Trajectory control refers to the control and adjustment of the vehicle according to the pre-planned trajectory during the actual driving process, so that the vehicle can drive along the planned trajectory as accurately as possible. Trajectory control needs to consider factors such as the vehicle's dynamic characteristics, road conditions, and environmental changes, and ensure that the vehicle drives stably on the planned trajectory by adjusting the vehicle's speed, direction, and acceleration in real time.

[0040] In the related art, the trajectory planning and control technology in the automatic driving system mainly relies on multi-objective optimization, dynamic programming and some basic control algorithms. Although these methods can achieve the requirements of automatic driving in general environments, with the complexity of the automatic driving environment and the improvement of the accuracy requirements of automatic driving, the automatic driving system in the related art has the following technical defects. First, the trajectory planning algorithm in the related art has a large amount of calculation and poor real-time performance when dealing with complex traffic environments, which makes it difficult to meet the actual needs of automatic driving vehicles. Especially in the face of highly dynamic and highly uncertain traffic environments, the computing efficiency and response speed of the automatic driving system in the related art still need to be improved. Second, a high-precision vehicle dynamics model is crucial to the accuracy of trajectory planning and control, but the vehicle dynamics model in the related art is difficult to fully and accurately describe the actual motion state of the vehicle, especially in multiple degrees of freedom and complex road conditions, the accuracy and robustness of the model still need to be improved. Third, the trajectory planning and control methods in the related art have poor adaptability and lack flexibility and generalization ability when facing different traffic environments and road conditions.

[0041] In order to overcome the deficiencies in the above-mentioned related technologies, the present application provides an autonomous driving motion planning control system based on time-space decoupling. Figure 1 For a schematic diagram of the structure of the autonomous driving motion planning control system provided in the embodiment of this application, please refer to Figure 1 As shown, the control system includes: a motion planning unit 10, a control instruction generating unit 20 and a motion control unit 30. The motion planning unit 10 is used to obtain the state information, environmental perception information and behavior prediction data of the vehicle, and plan the motion path and motion speed of the vehicle according to the state information, environmental perception information and behavior prediction data of the vehicle; the control instruction generating unit 20 is used to solve the motion path and motion speed based on the vehicle dynamics model and generate corresponding motion control instructions; the motion control unit 30 is used to control the various actuators of the vehicle according to the motion control instructions to complete the automatic driving of the vehicle.

[0042] Figure 2 For a schematic diagram of the signal flow of the vehicle motion control system provided in the embodiment of the present application, please refer to Figure 2 As shown, the motion planning unit 10 is mainly used for motion planning of autonomous driving. The motion planning unit 10 first receives the environmental perception information and behavior prediction data collected by the environmental perception unit; at the same time, the motion planning unit 10 also receives the vehicle state information output by the vehicle dynamics system in real time. The vehicle state information specifically refers to the vehicle's current position, speed, acceleration and other information. Then, the vehicle's motion path and motion speed are planned according to the vehicle's state information, environmental perception information and behavior prediction data.

[0043] Furthermore, the motion planning unit 10 is mainly used to generate automatic driving motion control instructions. Specifically, the motion planning unit 10 sends the planned motion path and motion speed to the control instruction generation unit 20, and the control instruction generation unit 20 solves the motion path and motion speed based on the constructed vehicle dynamics model, generates corresponding motion control instructions, and sends the generated motion control instructions to the motion control unit 30.

[0044] Finally, the motion control unit 30 is mainly used to control each power system to execute the various motion control instructions generated by the control instruction generation unit 20 to achieve automatic driving control. Specifically, the motion control unit 30 distributes the generated motion control instructions to the corresponding motion actuators, and then controls each actuator to perform corresponding actions to complete the vehicle automatic driving.

[0045] There are two main ways to generate motion control instructions: one is model-based generation, and the other is model-free and data-based generation. Model-based generation uses the method in control theory to first build a vehicle dynamics kinematic model, and then treat the vehicle as a system and control it through MPC, LQR, PID and other methods. In this scheme, the vehicle model is the basis, the model input is the expected trajectory, and the output is the control sequence; model-free data-driven does not require the construction of a vehicle model. The model contains data training and generation of control sequence labels, and then the trained model is used to generate control instructions for the new expected trajectory.

[0046] In some embodiments, the motion control system also includes an environmental perception unit; the environmental perception unit is used to obtain environmental perception information of the current vehicle's surrounding environment; and then obtain the speed, acceleration and motion trajectory information of the target object in the environmental perception information; the behavior prediction data includes the speed, acceleration and motion trajectory information of the target object.

[0047] Among them, the environmental perception unit can be understood as an environmental perception system. For example, the environmental perception unit includes sensors such as laser radar, high-definition camera, millimeter-wave radar, etc., which can collect point cloud information of objects in the surrounding environment in real time. According to the collected point cloud information, the surrounding road structure, road conditions, obstacles and other traffic participants can be analyzed. Among them, traffic participants mainly include pedestrians in vehicles, and vehicles can include various types of vehicles. In other words, environmental perception information includes point cloud information of surrounding objects and information such as the speed, acceleration and trajectory of surrounding pedestrians and vehicles.

[0048] Furthermore, the environment perception unit further processes the acquired environment perception information to obtain behavior prediction data. Specifically, the environment perception information can be first converted into semantic information, and then semantic analysis can be performed on each semantic information to obtain information such as the moving speed, acceleration, and trajectory of pedestrians and vehicles in the environment perception information to form the behavior prediction data of the target object (i.e., pedestrians and vehicles).

[0049] in, Figure 3 For a schematic diagram of the structure of the motion planning unit provided in the embodiment of the present application, see Figure 3 As shown, the motion planning unit 10 in this embodiment includes a path planning module 101 and a speed planning module 102. The path planning module 101 is used to plan multiple initial paths for the vehicle's movement based on the vehicle's state information, environmental perception information, and behavior prediction data using a dynamic planning method; and then use a quadratic planning method to determine the optimal path from the multiple initial paths as the vehicle's movement path. The speed planning module 102 is used to plan the vehicle's optimal speed curve based on the vehicle's state information and the vehicle's movement path, and the speed curve is used to characterize the vehicle's movement speed.

[0050] Figure 4 This is one of the path planning diagrams in the motion control system provided in the embodiment of the present application. The diagram describes how to construct the SL diagram based on the real scene. Specifically, it can be obtained by projecting other background vehicles onto the center line S of the road where the vehicle is traveling. Figure 7 The second schematic diagram of path planning in the motion control system provided in the embodiment of the present application is as follows: Figure 7 This is a schematic process of path planning by sampling in the SL graph according to the method in the patent. The planning is mainly divided into three steps: discretization of the drivable space -> dynamic programming to seek a rough solution -> quadratic programming to seek the final solution; Figure 8 The third schematic diagram of path planning in the motion control system provided in the embodiment of the present application is as follows: Figure 8 The middle shaded area is the optimized solution space obtained after dynamic programming, where the optimal solution can be further sought; the quadratic programming optimization process will be carried out in this area; Figure 5 This is one of the speed planning diagrams in the motion control system provided in the embodiment of the present application. The diagram illustrates how to generate an ST diagram. Specifically, it is generated when the driving path of the vehicle overlaps with that of other vehicles. The vertical axis S indicates that a certain section of the center line is occupied, and the horizontal axis T indicates the occupied time period. Fig. 9 This is the second schematic diagram of speed planning in the motion control system provided in the embodiment of the present application. Fig. 9The schematic diagram of speed planning in the figure is roughly consistent with the path planning. It is worth noting that speed planning does not need to be planned using a quintic polynomial. This is because the time interval during the planning process is very small, so there is no need to use a polynomial curve for smooth connection. The piecewise linear connection itself has good smoothness. Fig.10 This is the third schematic diagram of speed planning in the motion control system provided in the embodiment of the present application.

[0051] See also Figure 4 and Figure 5 As shown, specifically, the path planning module 101 in this embodiment maps the vehicle trajectory to a reference line in the SL coordinate system (also called the Frenet coordinate system), converts the trajectory planning problem into the shortest path search problem of the graph, generates a preliminary path through a dynamic programming method, and then finds the optimal path through a quadratic programming method to obtain the vehicle's motion path. Specifically, the speed planning unit 102 in this embodiment performs speed planning on the basis of path planning, and also uses a dynamic programming method to obtain a preliminary solution, and then uses a quadratic programming method to obtain a final solution, and generates an optimal speed curve based on the final solution obtained, thereby obtaining the vehicle's motion speed. Among them, in the specific path planning and speed planning process, path planning and speed planning are implemented iteratively.

[0052] Fig.11 One of the schematic diagrams of the motion control system simulation experiment provided in the embodiment of the present application; Fig.12 The second schematic diagram of the motion control system simulation experiment provided by the embodiment of the present application; Fig.13 This is one of the schematic diagrams of trajectory tracking results in the embodiment of this application. Fig.13 In the figure, the solid line represents the optimal reference trajectory solved by the trajectory planning algorithm, and the dotted line represents the trajectory tracking point obtained after execution by the MPC controller. The obstacle avoidance measure taken by the tested autonomous driving car for the static obstacle scene at the intersection is to change lanes to the right, make a detour, and then change lanes to drive along the initial lane. Fig.14 This is the second schematic diagram of the trajectory tracking result in the embodiment of this application. Fig.14 In the figure, the solid line represents the evaluation reference speed trajectory solved by the trajectory planning algorithm for the autonomous driving car, and the dotted line represents the driving trajectory points of the car after execution by the MPC controller. The experiment shows that the MPC algorithm can better track the reference speed trajectory, thereby completing the avoidance of collision conflicts caused by dynamic traffic participants in the engineering test scenario.

[0053] Figure 6 A schematic diagram of path planning and speed planning provided in an embodiment of the present application, Figure 6 For the constructed virtual scene, see Figure 6 As shown, Figure 6In , A is the driving trajectory of the vehicle under test (i.e., the autonomous driving vehicle), and B, C, D, and E are the running trajectories of different participating vehicles. Assume that when the traffic participating vehicle B enters the perception range of the autonomous driving vehicle, the path planning will be performed first to obtain the position information of the traffic participating vehicle B relative to the autonomous driving vehicle. The motion planning unit 10 of the autonomous driving will perform Lattice sampling under the Frenet coordinate system representation, and plan an optimal driving path according to the requirements of trajectory smoothness, etc., wherein the Frenet coordinate system is also called the SL coordinate system, which means: S represents the driving distance of the autonomous driving vehicle along the center line of the lane, and L represents the offset of the autonomous driving vehicle in the direction perpendicular to the center line of the lane. Furthermore, the motion planning unit 10 will first convert the path planning problem into the shortest path problem of the graph, and then solve the preliminary solution through dynamic planning, and then optimize the solution obtained by dynamic planning through secondary planning to obtain the final driving path.

[0054] After the above path planning, the motion planning unit 10 plans the speed of the automatic driving along the path through speed planning, and the speed planning is also carried out in the ST coordinate system. Figure 6 As shown, when the traffic participant E enters the perception range of the autonomous driving vehicle, according to the path planning results, the speed planning module will plan the driving speed along the path planning. According to the position and speed information of the traffic participant vehicle E relative to the autonomous driving vehicle, the autonomous driving motion planning system will perform Lattice sampling under the ST coordinate system representation, and plan an optimal driving path according to the requirements of trajectory smoothness, etc., where the ST coordinate system means: S represents the driving distance of the autonomous driving vehicle along the planned path, and T represents the driving time. Further, the motion planning unit 10 will first convert the speed planning problem into the shortest path problem of the graph, and then solve the preliminary solution through dynamic planning, and then optimize the solution obtained by dynamic planning through secondary planning to obtain the final driving speed. After the speed planning is completed, the motion planning unit 10 will enter a new round of path planning according to the driving state of the autonomous driving vehicle. The new path planning will correct the original path according to the driving state and environmental information, and then continue the speed planning, and repeat this cycle until the vehicle reaches the final position.

[0055] Among them, the path planning module 101 and the speed planning unit 102 need to comprehensively consider various factors such as path smoothness, curvature, curvature change rate, acceleration smoothness and jump smoothness during the process of path planning and speed planning. Through the multi-objective optimization method, it is possible to effectively balance safety, comfort and fuel economy and generate the optimal driving path and driving speed curve.

[0056] It can be seen that the autonomous driving motion planning control system provided in this embodiment decomposes the trajectory planning problem into two sub-problems of path planning and speed planning, and transforms the two sub-problems into the Frenet coordinate system for discretization processing in combination with the vehicle dynamics model, and obtains motion control instructions by combining dynamic programming and quadratic programming, which greatly improves the computing efficiency and real-time performance, and can quickly respond to changes in complex traffic environments.

[0057] In addition, the autonomous driving motion planning control system of this embodiment includes an environmental perception unit, through which the data of the perception system is converted into a Frenet coordinate system description. Combined with dynamic programming and model predictive control methods, it can flexibly respond to different traffic environments and road conditions, thereby improving the environmental adaptability and flexibility of the system.

[0058] Please continue to see Figure 2 As shown, the dynamic system of the autonomous driving vehicle in this embodiment mainly includes vehicle air resistance, vehicle steering mechanism, longitudinal dynamics, suspension dynamics, wheel spin motion and longitudinal angular dynamics, so when constructing the dynamic model of the autonomous driving vehicle, it is necessary to focus on the output of each of the above systems. Then, the vehicle dynamic model is constructed based on the output parameters of each system.

[0059] It is understandable that the vehicle dynamics model is constructed layer by layer. The vehicle dynamics model adopts a multi-degree-of-freedom dynamics model, including a vehicle air resistance model, a steering mechanism model, a tire model, a suspension system model and a body dynamics model, which fully and accurately describes the actual motion state of the vehicle. Specifically, in this embodiment, the control instruction generation unit 20 also includes a vehicle air resistance module, a vehicle steering mechanism module, a longitudinal dynamics module, a suspension dynamics module, a vehicle spin motion module and a longitudinal angle dynamics module. These modules first construct corresponding sub-models. For example, the vehicle air resistance module is used to construct a vehicle air resistance model, and the input of the vehicle air resistance model is environmental factors such as wind resistance and gravity, and its output is some intermediate parameter information, such as the output can be information such as speed or acceleration. For example, the vehicle steering mechanism module is used to construct a vehicle steering mechanism model.

[0060] It can be seen that this embodiment adopts a multi-degree-of-freedom dynamic model, including multiple sub-models such as vehicle air resistance, steering mechanism, tire model, suspension system and body dynamics, which can comprehensively and accurately describe the actual motion state of the vehicle and significantly improve the accuracy and robustness of trajectory planning and control.

[0061] After the control instruction generation unit 20 obtains the planned motion path and motion speed, the control instruction generation unit 20 will use the MPC (Model Predictive Control) method to generate control instructions for each moment based on the established vehicle dynamics model, and the automatic driving motion execution module will execute the corresponding actions and finally complete the local trajectory driving.

[0062] Among them, the control instruction generation unit 20 is specifically used to obtain multiple parameter information output by the vehicle air resistance module, the vehicle steering mechanism module, the longitudinal dynamics module, the suspension dynamics module, the vehicle spin motion module and the longitudinal angle dynamics module, and construct a vehicle dynamics model according to the multiple parameter information. In other words, the multiple modules in the control instruction generation unit 20 first construct corresponding sub-models, and then construct the final vehicle dynamics model according to the output of each sub-model. Further, the control instruction generation unit 20 linearizes and discretizes the constructed vehicle dynamics model, and then combines the state quantity and control quantity weighted matrix to generate motion control instructions through quadratic programming.

[0063] It can be seen that the vehicle dynamics model in this embodiment adopts a multi-degree-of-freedom dynamics model, which includes multiple subsystems such as vehicle air resistance, steering mechanism, tire model, suspension system and body dynamics, which comprehensively and accurately describes the actual motion state of the vehicle and significantly improves the accuracy and robustness of trajectory planning and control.

[0064] In some embodiments, the motion control instructions include: direction control instructions, gear control instructions, acceleration control instructions, braking control instructions, and light control instructions. The motion control unit 30 can control the driving direction of the autonomous driving vehicle according to the direction control instruction; the motion control unit 30 can control the driving speed of the autonomous driving vehicle according to the gear control instruction; the motion control unit 30 can control the acceleration of the autonomous driving vehicle during driving according to the acceleration control instruction; the motion control unit 30 can control the braking system of the autonomous driving vehicle according to the braking control instruction; the motion control unit 30 can control the lighting system of the autonomous driving vehicle during driving according to the light control instruction.

[0065] Furthermore, this embodiment also provides an autonomous driving vehicle, which includes the autonomous driving motion planning control system as described above.

[0066] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid state drive (SSD).

[0067] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the embodiments of the present application.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0069] In the several embodiments provided in the embodiments of the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0070] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0071] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0072] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a memory (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), random access memory (RandomAccess Memory, RAM), disk or optical disk and other media that can store program code.

[0073] The above is only a specific implementation of the embodiment of the present application, but the protection scope of the embodiment of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or replacements within the technical scope disclosed in the embodiment of the present application, which should be included in the protection scope of the embodiment of the present application. Therefore, the protection scope of the embodiment of the present application should be based on the protection scope of the claims.

Claims

1. An automatic driving motion planning control system based on time-space decoupling, characterized in that: include: Motion planning unit, control instruction generation unit and motion control unit; The motion planning unit is used to obtain the vehicle's state information, environmental perception information and behavior prediction data, and plan the vehicle's motion path and motion speed according to the vehicle's state information, environmental perception information and behavior prediction data; The control instruction generating unit is used to solve the motion path and motion speed based on the vehicle dynamics model to generate corresponding motion control instructions; The motion control unit is used to perform corresponding control on each actuator of the vehicle according to the motion control instruction to complete the automatic driving of the vehicle.

2. The automatic driving motion planning control system according to claim 1, characterized in that: The motion planning unit includes a path planning module and a speed planning module; The path planning module is used to plan multiple initial paths for the vehicle's movement based on the vehicle's state information, environmental perception information, and behavior prediction data using a dynamic planning method; and then use a quadratic planning method to determine the optimal path from the multiple initial paths as the vehicle's movement path; The speed planning module is used to plan an optimal speed curve of the vehicle according to the state information of the vehicle and the movement path of the vehicle, and the speed curve is used to represent the movement speed of the vehicle.

3. The automatic driving motion planning control system according to claim 1 or 2, characterized in that: The step of solving the motion path and motion speed based on the vehicle dynamics model and generating corresponding motion control instructions includes: The vehicle dynamics model is linearized and discretized to construct a prediction model, and the prediction model is used to generate corresponding motion control instructions according to the motion path and motion speed.

4. The automatic driving motion planning control system according to claim 1 or 2, characterized in that: The motion control instructions include: direction control instructions, gear control instructions, acceleration control instructions, braking control instructions and lighting control instructions.

5. The automatic driving motion planning control system according to claim 1 or 2, characterized in that: The control instruction generating unit also includes a vehicle air resistance module, a vehicle steering mechanism module, a longitudinal dynamics module, a suspension dynamics module, a vehicle spin motion module and a longitudinal angle dynamics module.

6. The automatic driving motion planning control system according to claim 5, characterized in that: The control instruction generation unit is also used to obtain multiple parameter information output by the vehicle air resistance module, vehicle steering mechanism module, longitudinal dynamics module, suspension dynamics module, vehicle spin motion module and longitudinal angle dynamics module, and construct the vehicle dynamics model based on the multiple parameter information.

7. The automatic driving motion planning control system according to claim 1 or 2, characterized in that: The motion control system also includes an environment perception unit; the environment perception unit is used to obtain environment perception information of the current vehicle surrounding environment.

8. The automatic driving motion planning control system according to claim 7, characterized in that: The environment perception unit is also used to obtain the speed, acceleration and motion trajectory information of the target object in the environment perception information; the behavior prediction data includes the speed, acceleration and motion trajectory information of the target object.

9. An autonomous driving vehicle, characterized in that: Comprising an autonomous driving motion planning control system as described in any one of claims 1-8.

Images