ROS-based driving test robot vehicle end control system

By designing a ROS-based driving test robot vehicle-end control system, the poor maintenance problem caused by tight coupling of modules in the existing technology is solved, and highly loose coupling and multi-adaptation are achieved, which promotes the rapid development and widespread development of driving test robots. use.

CN118938778APending Publication Date: 2024-11-12YIXIAN INTELLIGENCE
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411243909.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-09-05
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

The existing driving test robot software system modules are highly tightly coupled, resulting in poor maintainability, iterativeness and replacement, and low reusability of functional modules, making it difficult to promote the rapid development and widespread use of driving test robots.

Method used

A ROS-based driving test robot vehicle-end control system is designed, including sensor driving layer, positioning layer, coordinate conversion layer, map layer, planning layer and control layer. The modules of each layer are highly loosely coupled, supporting a variety of algorithms and sensors. It can realize distributed computing and multi-programming language support.

Benefits of technology

This system architecture promotes the rapid development and widespread use of driving test robots, and has multiple algorithm adaptations, multiple sensor adaptations, and multiple chassis adaptations, improving the flexibility and scalability of the system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118938778A_ABST
    Figure CN118938778A_ABST
Patent Text Reader

Abstract

The invention discloses an ROS-based driving test robot vehicle end control system. The system comprises a sensor driving layer, a positioning layer, a coordinate conversion layer, a map layer, a planning layer and a control layer from bottom to top. The vehicle end control system has the characteristics of distributed calculation, functional module high loose coupling and multi-programming language support, has the advantages of multi-algorithm adaptation, multi-sensor adaptation and multi-chassis adaptation, and can promote rapid development and wide application of the driving test robot.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving, and in particular to a vehicle-side control system of a driving test robot. Background Art

[0002] With the development of autonomous driving algorithm technology and the improvement of sensor cost-effectiveness, robot technology is gradually being implemented in driving training scenarios. Relying on positioning technology, sensor perception of the surrounding environment, map-based planning and control, and control-based language teaching are the core modules of driving test robots. At present, the driving test robot software systems in the driving training industry are all developed based on Visual Studio. The modules are highly tightly coupled, with poor maintainability, iteration, and replacement, and low reusability of functional modules. Summary of the invention

[0003] In order to solve one of the problems existing in the prior art, the present invention provides a vehicle-side control system of a driving test robot based on ROS, including from bottom to top: a sensor drive layer, a positioning layer, a coordinate conversion layer, a map layer, a planning layer, and a control layer;

[0004] Among them, the sensor driver layer includes several functional modules; the sensor driver layer reads and analyzes the data information of the objects corresponding to each functional module, and publishes the standard message format of ROS or the customized message format;

[0005] The positioning layer receives sensor drive information and static coordinate conversion information, calculates the real-time position and posture of the driving test robot, and publishes the standard message format of ROS;

[0006] The coordinate conversion layer includes a static coordinate conversion module and a dynamic coordinate conversion module. The static coordinate conversion module configures the static coordinate system conversion according to the sensor external parameters; the dynamic coordinate conversion module publishes the real-time dynamic coordinate conversion from the odometer sensor to the Map coordinate system according to the odometer information of the positioning layer, and publishes the real-time speed information of the driving test robot;

[0007] The map layer includes a global grid map module, a local grid map module, a subject map module, and a high-precision point cloud map module; the global grid map module is used for global navigation, the local grid map module is used for obstacle avoidance planning, the subject map module is used for automatic teaching path planning, and the high-precision point cloud map module is used to generate point cloud maps;

[0008] The planning layer includes a path planning module and a speed planning module. The path planning module is used to plan the path. The speed planning module is used to plan and calculate the driving trajectory of the driving test robot body and perform collision detection, calculate how far away the collision occurs in the driving trajectory, and calculate the maximum permitted speed according to the vehicle braking performance;

[0009] The control layer includes a lateral control module and a longitudinal control module. The lateral control module is used to calculate the steering angle of the steering wheel; the longitudinal control module is used to calculate the throttle and brake values; the control layer sends the steering angle, throttle and brake values ​​of the steering wheel to the wire control module for execution.

[0010] Furthermore, the several functional modules of the sensor driving layer are IMU driving module, RTK driving module, Lidar driving module, Radar driving module and wire control module;

[0011] The IMU driver module reads and analyzes the data information of the corresponding object through the serial port or CAN, and publishes the standard message format of ROS;

[0012] The RTK driver module reads the data information of the corresponding object through the serial port or network port, and publishes the standard message format of ROS;

[0013] The Lidar driver module reads the data information of its corresponding object through the network and publishes the standard message format of ROS;

[0014] The Radar driver module reads the sensor data of the corresponding object through CAN and publishes customized millimeter-wave radar target data, which includes horizontal and vertical coordinates, horizontal and vertical speeds, RCS, and confidence.

[0015] The wire control module reads one or more of the vehicle steering, vehicle speed, gear information, braking depth, and throttle depth through the CAN module, and receives one or more of the steering wheel steering angle, throttle, braking value, and gear control instructions and sends them to the actuator.

[0016] Furthermore, the global grid map module in the map layer generates a pgm file using an external electronic fence file, and uses the map_server module to load and publish the message format of the ROS standard.

[0017] Furthermore, the local grid map module in the map layer subscribes to radar sensor and odometer information to generate grid map data in a body coordinate system.

[0018] Furthermore, the subject map module in the map layer utilizes an external subject map file to parse and publish a customized ROS message.

[0019] Furthermore, the high-precision point cloud map module in the map layer generates a point cloud map by using RTK odometer information, lidar, and IMU through SLAM.

[0020] Furthermore, the path planning module in the planning layer includes a global path planning module and a local path planning module;

[0021] The global path planning module subscribes to the global grid map, odometer information and target location information, and calculates the path from the current location to the target location;

[0022] The local path planning module subscribes to the global path, the local grid map, the current position and the coordinate system transformation to calculate a trajectory to avoid obstacles.

[0023] Furthermore, the speed planning module calculates the maximum permitted speed based on the laser radar, millimeter wave radar, vehicle status, and coordinate system conversion information.

[0024] Furthermore, the lateral control module in the control layer subscribes to local path planning information, odometer information, and vehicle information, and uses pure tracking / MPC / LQR to calculate the steering angle of the steering wheel.

[0025] Furthermore, the longitudinal control module in the control layer performs PID control and calculates throttle and brake values ​​according to the maximum permissible speed of the longitudinal speed planning and the actual speed of the vehicle.

[0026] The vehicle-side control system provided by the present invention has the characteristics of distributed computing, highly loose coupling of functional modules, and support for multiple programming languages. It has the advantages of multiple algorithm adaptation, multiple sensor adaptation, and multiple chassis adaptation, and can promote the rapid development and widespread use of driving test robots. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions in the specific implementation manner of the present invention, the drawings required for use in the specific implementation manner or the description of the prior art will be briefly introduced below.

[0028] Figure 1 It is a schematic diagram of the system disclosed in the embodiment of the first aspect of the present invention.

[0029] Figure 2 It is a schematic diagram of the architecture of the positioning layer in the system disclosed in the embodiment of the first aspect of the present invention.

[0030] Figure 3 It is a schematic diagram of the architecture of the coordinate conversion layer in the system disclosed in the embodiment of the first aspect of the present invention.

[0031] Figure 4 It is a schematic diagram of the architecture of the local grid map module in the system disclosed in the embodiment of the first aspect of the present invention.

[0032] Figure 5 It is a schematic diagram of the architecture of the global path planning module in the system disclosed in the embodiment of the first aspect of the present invention.

[0033] Figure 6It is a schematic diagram of the architecture of the local path planning module in the system disclosed in the embodiment of the first aspect of the present invention.

[0034] Figure 7 It is a schematic diagram of the architecture of the speed planning module in the system disclosed in the embodiment of the first aspect of the present invention.

[0035] Figure 8 It is a schematic diagram of the architecture of the lateral control module in the system disclosed in the embodiment of the first aspect of the present invention.

[0036] Fig. 9 It is a schematic diagram of the architecture of the longitudinal control module in the system disclosed in the embodiment of the first aspect of the present invention. DETAILED DESCRIPTION

[0037] The structure and operation of the present invention will be further described in detail below in conjunction with the accompanying drawings. Obviously, the accompanying drawings are provided only for a better understanding of the present invention and should not be construed as limiting the present invention. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] In the description of the present invention, it should be noted that, if the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. appear, the orientation or position relationship indicated is based on the orientation or position relationship shown in the drawings, which is only for the convenience of describing the present invention and simplifying the description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, if the terms "first" and "second" appear, they are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0039] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0040] Example 1

[0041] like Figure 1As shown, the present invention discloses a vehicle-side control system of a driving test robot based on ROS, including from bottom to top: sensor drive layer, positioning layer, coordinate conversion layer, map layer, planning layer, and control layer. ROS (Robot Operating System) is an open source robot operating system framework that can provide support for various functional modules, software algorithms, etc. The present invention is specifically a vehicle-side system architecture built on ROS1.

[0042] In a specific embodiment, the sensor driver layer includes several functional modules; the sensor driver layer reads and analyzes the data information of the objects corresponding to each functional module, and publishes the standard message format of ROS or the customized message format;

[0043] The positioning layer receives sensor drive information and static coordinate conversion information, calculates the real-time position and posture of the driving test robot, and publishes the standard message format of ROS; see the architecture diagram of the positioning layer Figure 2 .

[0044] The coordinate conversion layer includes a static coordinate conversion module and a dynamic coordinate conversion module. The static coordinate conversion module configures the static coordinate system conversion according to the sensor external parameters; the dynamic coordinate conversion module publishes the real-time dynamic coordinate conversion from the odometer sensor to the Map coordinate system according to the odometer information of the positioning layer, and publishes the real-time speed information of the driving test robot; the architecture diagram of the coordinate conversion layer can be found in Figure 3 The map coordinate system refers to the map coordinate system, which is a reference frame that describes the position and direction of various elements (such as roads, landmarks, obstacles, etc.) in the map. The map coordinate system in this embodiment is a geographic coordinate system based on longitude and latitude or a customized local coordinate system.

[0045] The map layer includes a global grid map module, a local grid map module, a subject map module, and a high-precision point cloud map module; the global grid map module is used for global navigation, the local grid map module is used for obstacle avoidance planning, the subject map module is used for automatic teaching path planning, and the high-precision point cloud map module is used to generate point cloud maps;

[0046] The planning layer includes a path planning module and a speed planning module. The path planning module is used to plan the path. The speed planning module is used to plan and calculate the driving trajectory of the driving test robot body and perform collision detection, calculate how far away the collision occurs in the driving trajectory, and calculate the maximum permitted speed according to the vehicle braking performance;

[0047] The control layer includes a lateral control module and a longitudinal control module. The lateral control module is used to calculate the steering angle of the steering wheel; the longitudinal control module is used to calculate the throttle and brake values; the control layer sends the steering angle, throttle and brake values ​​of the steering wheel to the wire control module for execution.

[0048] Specifically, the several functional modules of the sensor driving layer are IMU driving module, RTK driving module, Lidar driving module, Radar driving module and wire control module;

[0049] The IMU driver module reads and parses the data information of the corresponding object through the serial port or CAN, and publishes the standard message format of ROS; in the specific embodiment, the standard message format of ROS is the sensor_msgs / Imu message format, which mainly includes frame_id, angular velocity, acceleration and other information; IMU is the abbreviation of Inertial Measurement Unit, which is usually used to measure the angular velocity, acceleration and other parameters of the object, and is widely used in aerospace, robotics, automobile and other fields.

[0050] The RTK driver module reads the data information of the corresponding object through the serial port or the network port, and publishes the standard message format of ROS; in the specific embodiment, the standard information format of ROS is the nmea_msgs / Sentence message format; RTK is the abbreviation of Real Time Key , which refers to the real-time dynamic carrier phase difference technology.

[0051] The Lidar driver module reads the data information of the corresponding object through the network and publishes the standard message format of ROS; the standard message format of ROS is the message format of sensor_msgs / PointCloud; Lidar is Light Detection and Ranging, which is a sensor that obtains the precise distance and shape information of the surrounding environment by emitting a laser beam and measuring the time it takes for the laser to return, thereby generating a high-resolution three-dimensional point cloud map.

[0052] The Radar driver module reads the sensor data of its corresponding object through CAN and publishes customized millimeter-wave radar target data, which includes horizontal and vertical coordinates, horizontal and vertical speeds, RCS, and confidence. Radar is radar.

[0053] The wire control module reads one or more of the vehicle steering, vehicle speed, gear information, brake depth, and throttle depth through the CAN module, and receives one or more of the steering wheel steering angle, throttle, brake value, and gear control instructions and sends them to the actuator. CAN is a serial communication protocol that is widely used in automotive electronic systems to achieve data exchange and communication between various electronic control units (ECUs) in the vehicle.

[0054] In a specific embodiment, the global grid map module in the map layer generates a pgm file using an external electronic fence file, specifically by rtk dot or point cloud map production, and uses the map_server module to load and publish the ROS standard message format, which is specifically the nav_msgs / OccupancyGrid message format. The PGM (Portable GrayMap) format is a file format for storing grayscale images. The map_server module is a built-in functional module of ROS.

[0055] In a specific embodiment, the local grid map module in the map layer subscribes to radar sensor and odometer information to generate grid map data in the body coordinate system, and the message format is nav_msgs / OccupancyGr id. Figure 4 .

[0056] In a specific embodiment, the subject map module in the map layer uses an external subject map file to parse and publish a custom ROS message, which is specifically generated by rtk dot generation or produced by a point cloud map.

[0057] In a specific embodiment, the high-precision point cloud map module in the map layer generates a point cloud map by using RTK odometer information, laser radar, and IMU through SLAM. SLAM (Simultanous Localization and Mapping) is simultaneous positioning and mapping.

[0058] In a specific embodiment, the path planning module in the planning layer includes a global path planning module and a local path planning module;

[0059] The global path planning module subscribes to the global grid map, odometer information and target location information, and calculates the path from the current location to the target location. The specific algorithms used include A* or hybrid A* algorithms. The architecture of the global path planning module can be found in Figure 5 .

[0060] The local path planning module subscribes to the global path, the local grid map, the current position and the coordinate system transformation to calculate a trajectory to avoid obstacles. The specific algorithm includes A* or hybrid A*. The architecture of the local path planning module can be found in Figure 6 .

[0061] In a specific embodiment, the speed planning module calculates the maximum permissible speed based on the laser radar, millimeter wave radar, vehicle status, and coordinate system conversion information. Figure 7 .

[0062] In a specific embodiment, the lateral control module in the control layer subscribes to local path planning information, odometer information, and vehicle information, and uses pure tracking / MPC / LQR to calculate the steering angle of the steering wheel. Figure 8 . MPC (Model Predictive Control) is a control algorithm. It predicts the state of the system in the future based on the system model and determines the current optimal control action through optimization calculation. LQR (Linear Quadratic Regulator) is an optimal control method based on a linear system model. The control input is determined by solving the optimal solution of a specific quadratic performance indicator.

[0063] In a specific embodiment, the longitudinal control module in the control layer performs PID control and calculates throttle and brake values ​​according to the maximum permissible speed of the longitudinal speed planning and the actual speed of the vehicle. Fig. 9 .

[0064] PID is the abbreviation of Proportiona lIntegral-Derivative, which is proportional-integral-derivative controller.

[0065] The present invention can achieve the following technical effects: the system architecture has the characteristics of distributed computing, highly loose coupling of functional modules, and support for multiple programming languages. It has the advantages of multiple algorithm adaptation, multiple sensor adaptation, and multiple chassis adaptation, and can promote the rapid development and widespread use of driving test robots.

[0066] The above embodiments are only used to illustrate the present invention, wherein the structure, connection method and manufacturing process of each component may be changed. Any equivalent transformations and improvements based on this technical solution should not be excluded from the protection scope of the present invention.

Claims

1. A driving test robot vehicle-side control system based on ROS, characterized in that: It includes from bottom to top: sensor driving layer, positioning layer, coordinate conversion layer, map layer, planning layer, and control layer; Among them, the sensor driver layer includes several functional modules; the sensor driver layer reads and analyzes the data information of the objects corresponding to each functional module, and publishes the standard message format of ROS or the customized message format; The positioning layer receives sensor drive information and static coordinate conversion information, calculates the real-time position and posture of the driving test robot, and publishes the standard message format of ROS; The coordinate conversion layer includes a static coordinate conversion module and a dynamic coordinate conversion module. The static coordinate conversion module configures the static coordinate system conversion according to the sensor external parameters; the dynamic coordinate conversion module publishes the real-time dynamic coordinate conversion from the odometer sensor to the Map coordinate system according to the odometer information of the positioning layer, and publishes the real-time speed information of the driving test robot; The map layer includes a global grid map module, a local grid map module, a subject map module, and a high-precision point cloud map module; the global grid map module is used for global navigation, the local grid map module is used for obstacle avoidance planning, the subject map module is used for automatic teaching path planning, and the high-precision point cloud map module is used to generate point cloud maps; The planning layer includes a path planning module and a speed planning module. The path planning module is used to plan the path. The speed planning module is used to plan and calculate the driving trajectory of the driving test robot body and perform collision detection, calculate how far away the collision occurs in the driving trajectory, and calculate the maximum permitted speed according to the vehicle braking performance; The control layer includes a lateral control module and a longitudinal control module. The lateral control module is used to calculate the steering angle of the steering wheel; the longitudinal control module is used to calculate the throttle and brake values; the control layer sends the steering angle, throttle and brake values ​​of the steering wheel to the wire control module for execution.

2. The system according to claim 1, characterized in that The several functional modules of the sensor driving layer are IMU driving module, RTK driving module, Lidar driving module, Radar driving module and wire control module; The IMU driver module reads and analyzes the data information of the corresponding object through the serial port or CAN, and publishes the standard message format of ROS; The RTK driver module reads the data information of the corresponding object through the serial port or network port, and publishes the standard message format of ROS; The Lidar driver module reads the data information of its corresponding object through the network and publishes the standard message format of ROS; The Radar driver module reads the sensor data of the corresponding object through CAN and publishes customized millimeter-wave radar target data, which includes horizontal and vertical coordinates, horizontal and vertical speeds, RCS, and confidence. The wire control module reads one or more of the vehicle steering, vehicle speed, gear information, braking depth, and throttle depth through the CAN module, and receives one or more of the steering wheel steering angle, throttle, braking value, and gear control instructions and sends them to the actuator.

3. The system according to claim 1, characterized in that: The global grid map module in the map layer generates a pgm file using an external electronic fence file, and uses the map_server module to load and publish the message format of the ROS standard.

4. The system according to claim 1, characterized in that: The local grid map module in the map layer subscribes to radar sensor and odometer information to generate grid map data in a body coordinate system.

5. The system according to claim 1, characterized in that: The subject map module in the map layer utilizes external subject map files to parse and publish custom ROS messages.

6. The system according to claim 1, characterized in that: The high-precision point cloud map module in the map layer generates a point cloud map by using RTK odometer information, lidar, and IMU through SLAM.

7. The system according to claim 1, characterized in that: The path planning module in the planning layer includes a global path planning module and a local path planning module; The global path planning module subscribes to the global grid map, odometer information and target location information, and calculates the path from the current location to the target location; The local path planning module subscribes to the global path, the local grid map, the current position and the coordinate system transformation to calculate a trajectory to avoid obstacles.

8. The system according to claim 1, characterized in that: The speed planning module calculates the maximum permitted speed based on the laser radar, millimeter wave radar, vehicle status, and coordinate system conversion information.

9. The system according to claim 1, characterized in that: The lateral control module in the control layer subscribes to local path planning information, odometer information, and vehicle information, and uses pure tracking / MPC / LQR to calculate the steering angle of the steering wheel.

10. The system according to claim 1, characterized in that: The longitudinal control module in the control layer performs PID control and calculates throttle and brake values ​​according to the maximum permissible speed of the longitudinal speed planning and the actual speed of the vehicle.