Multi-client automatic driving teaching system

Abstract

The invention relates to the technical field of automatic driving, in particular to a multi-client-side automatic driving teaching system which comprises a carla platform and a server side, the carla platform and the server side can be uniformly understood as the server side and both run in the same high-performance server computer, and the client sides run in common computers. The server side and the client side communicate through a network, the client side carries out automatic driving theory teaching and experiment teaching through communication with the server side and resource acquisition, automatic driving teaching can effectively support multi-client-side automatic driving teaching, the cost is low, teaching scenes are diversified, the simultaneous learning requirements of multiple students can be met at the same time, and the teaching efficiency is improved. And the efficiency of automatic driving teaching is improved.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a multi-client autonomous driving teaching system. Background Art

[0002] Traditional autonomous driving teaching methods have problems such as high cost, limited scenarios, and difficulty in meeting the simultaneous learning needs of multiple students. Carla is an open source simulator for autonomous driving research. Carla was developed from scratch to support the development, training, and verification of autonomous driving systems. In addition to open source code and protocols, Carla also provides open digital assets (city layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specifications for sensor suites and environmental conditions. Carla is an open source simulator for autonomous driving research. Carla was developed from scratch to support the development, training, and verification of autonomous driving systems. In addition to open source code and protocols, Carla also provides open digital assets (city layouts, buildings, vehicles) that were created for this purpose and can be used freely. The simulation platform supports flexible specifications for sensor suites and environmental conditions. As a powerful autonomous driving simulation software, Carla provides new possibilities for autonomous driving teaching.

[0003] However, there is currently a lack of systems that effectively support multi-client autonomous driving teaching. Therefore, a multi-client autonomous driving teaching system is proposed. Summary of the invention

[0004] The purpose of the present invention is to provide a multi-client autonomous driving teaching system to solve the problems raised in the above background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: A multi-client autonomous driving teaching system, the system includes a carla platform and a server, the carla platform and the server can be uniformly understood as the server, both run on the same high-performance server computer, the client runs on an ordinary computer, the server and the client communicate through the network, and the client performs autonomous driving theory teaching and experimental teaching by communicating with the server and acquiring resources; The steps of the controlled teaching method include: S1. Start the server and start the teaching theory module according to the teaching progress. The teaching theory module includes a basic sensor module, a deep learning module, a sensor fusion module, a global path planning module, a vehicle longitudinal control module and a vehicle lateral control module. Students can click on any module for systematic learning or single learning. S2. After the server obtains the theoretical teaching module request from the client, it pushes the resource document in the background and displays it on the client; S3. Based on the theoretical module, start the simulation experiment. According to the content of the experiment, switch different maps in the carla platform module, set the twin vehicles according to the number of clients, and the server program module obtains the status of the carla platform module. According to the parameter settings of the server, the carla platform module is communicated for parameter settings, including but not limited to map changes, vehicle generation, and sensor generation. S4, the carla platform module receives the parameter data of the server program module and uses the GPU graphics card of the server host to render and generate the image; S5. After S4 is completed, the client sets the server IP and port to be accessed through the script program. By setting the server port, the client can communicate with the server normally and complete all data interactions through the node function of ROS. S6. After completing S5, execute the subsequent steps. Here, all experimental simulation routines are collectively referred to as client simulation modules. The client simulation module is executed by roslaunch, requesting the server's RGB_VIEW image and vehicle information for real-time display on the client. At the same time, the client issues an action request to the carla platform module for rendering update. S7. When the client module makes a data request, the carla platform module sends the corresponding data to the client module. For the action request of the client module, the carla platform module updates the rendering of the vehicle.

[0006] Preferably, the basic sensor module includes a lidar, a camera, and an Imu, and the deep learning module includes environment construction, yolov5 training, and yolov5 deployment.

[0007] Preferably, the sensor fusion module includes the introduction of robot_pos_ekf, the principle of extended Kalman filtering, and the fusion positioning of imu and odometer, and the global path planning module includes the principle of A* algorithm.

[0008] Preferably, the vehicle longitudinal control module includes longitudinal control logic, PID introduction, and vehicle throttle control, and the vehicle lateral control module includes kinematic model introduction and the principle of Pure Pursuit algorithm.

[0009] Compared with the prior art, the present invention has the following beneficial effects: By running carla and the server on the same high-performance server computer, and the client on an ordinary computer, the server and the client communicate through the network, and the client conducts autonomous driving theory teaching and experimental teaching by communicating with the server and acquiring resources, so that the autonomous driving teaching can effectively support multi-client autonomous driving teaching, with low cost and diversified teaching scenarios, which can meet the learning needs of multiple students at the same time and improve the efficiency of autonomous driving teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 is an architecture diagram of the system of the present invention; Figure 2 A schematic diagram of a system simulation scenario of a server of the present invention; Figure 3 This is a schematic diagram of a laser radar module of the present invention; Figure 4 This is a schematic diagram of the deep learning module of the present invention; Figure 5 This is a schematic diagram of the sensor fusion module of the present invention; Figure 6 This is a schematic diagram of the global path planning of the present invention; Figure 7 This is a schematic diagram of the longitudinal control of the vehicle of the present invention; Figure 8 This is a schematic diagram of the lateral control of the vehicle of the present invention; Fig. 9 Schematic diagram for server port settings; Fig.10 A schematic diagram showing real-time display of vehicle information. DETAILED DESCRIPTION

[0011] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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 are within the scope of protection of the present invention.

[0012] like Figure 1-10 As shown, a multi-client autonomous driving teaching system includes a carla platform and a server. The carla platform and the server can be uniformly understood as the server, both running on the same high-performance server computer, and the client running on an ordinary computer. The server and the client communicate through the network, and the client conducts autonomous driving theory teaching and experimental teaching by communicating with the server and acquiring resources; The steps of the controlled teaching method include: S1. Start the server and start the teaching theory module according to the teaching progress. The teaching theory module includes basic sensor module, deep learning module, sensor fusion module, global path planning module, vehicle longitudinal control module and vehicle lateral control module. Students can click on any module for systematic learning or single learning; S2. After the server obtains the theoretical teaching module request from the client, it pushes the resource document in the background and displays it on the client; S3. Based on the theoretical module, start the simulation experiment. According to the content of the experiment, switch different maps in the carla platform module, set the twin vehicles according to the number of clients, and the server program module obtains the status of the carla platform module. According to the parameter settings of the server, the carla platform module is communicated for parameter settings, including but not limited to map changes, vehicle generation, and sensor generation. S4, the carla platform module receives the parameter data of the server program module and uses the GPU graphics card of the server host to render and generate the image; S5. After S4 is completed, the client sets the server IP and port to be accessed through the script program. By setting the server port, the client can communicate with the server normally and complete all data interactions through the node function of ROS. S6. After completing S5, execute the subsequent steps. Here, all experimental simulation routines are collectively referred to as client simulation modules. The client simulation module is executed by roslaunch, requesting the server's RGB_VIEW image and vehicle information for real-time display on the client. At the same time, the client issues an action request to the carla platform module for rendering update. S7. When the client module makes a data request, the carla platform module sends the corresponding data to the client module. For the action request of the client module, the carla platform module updates the rendering of the vehicle.

[0013] The basic sensor modules include lidar, camera, and Imu. The deep learning module includes environment construction, yolov5 training, and yolov5 deployment.

[0014] The sensor fusion module includes the introduction of robot_pos_ekf, the principle of extended Kalman filter, the fusion positioning of imu and odometer, and the global path planning module includes the principle of A* algorithm.

[0015] The vehicle longitudinal control module includes longitudinal control logic, PID introduction, and vehicle throttle control. The vehicle lateral control module includes kinematic model introduction and the principle of Pure Pursuit algorithm.

[0016] By running carla and the server on the same high-performance server computer, and the client on an ordinary computer, the server and the client communicate through the network, and the client conducts autonomous driving theory teaching and experimental teaching by communicating with the server and acquiring resources, so that the autonomous driving teaching can effectively support multi-client autonomous driving teaching, with low cost and diversified teaching scenarios, which can meet the learning needs of multiple students at the same time and improve the efficiency of autonomous driving teaching.

[0017] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.

Claims

1. A multi-client autonomous driving teaching system, characterized in that: The system includes a carla platform and a server. The carla platform and the server can be uniformly understood as the server, both running on the same high-performance server computer, and the client running on an ordinary computer. The server and the client communicate through the network. The client conducts autonomous driving theory teaching and experimental teaching by communicating with the server and acquiring resources. The steps of the controlled teaching method include: S1. Start the server and start the teaching theory module according to the teaching progress. The teaching theory module includes a basic sensor module, a deep learning module, a sensor fusion module, a global path planning module, a vehicle longitudinal control module and a vehicle lateral control module. Students can click on any module for systematic learning or single learning. S2. After the server obtains the theoretical teaching module request from the client, it pushes the resource document in the background and displays it on the client; S3. Based on the theoretical module, start the simulation experiment. According to the content of the experiment, switch different maps in the carla platform module, set the twin vehicles according to the number of clients, and the server program module obtains the status of the carla platform module. According to the parameter settings of the server, the carla platform module is communicated for parameter settings, including but not limited to map changes, vehicle generation, and sensor generation. S4, the carla platform module receives the parameter data of the server program module and uses the GPU graphics card of the server host to render and generate the image; S5. After S4 is completed, the client sets the server IP and port to be accessed through the script program. By setting the server port, the client can communicate with the server normally and complete all data interactions through the node function of ROS. S6. After completing S5, execute the subsequent steps. Here, all experimental simulation routines are collectively referred to as client simulation modules. The client simulation module is executed by roslaunch, requesting the server's RGB_VIEW image and vehicle information for real-time display on the client. At the same time, the client issues an action request to the carla platform module for rendering update. S7. When the client module makes a data request, the carla platform module sends the corresponding data to the client module. For the action request of the client module, the carla platform module updates the rendering of the vehicle.

2. The multi-client autonomous driving teaching system according to claim 1, characterized in that: The basic sensor module includes lidar, camera, and Imu, and the deep learning module includes environment construction, yolov5 training, and yolov5 deployment.

3. The multi-client autonomous driving teaching system according to claim 1, characterized in that: The sensor fusion module includes the introduction of robot_pos_ekf, the principle of extended Kalman filtering, and the fusion positioning of imu and odometer. The global path planning module includes the principle of A* algorithm.

4. The multi-client autonomous driving teaching system according to claim 1, characterized in that: The vehicle longitudinal control module includes longitudinal control logic, PID introduction, and vehicle throttle control. The vehicle lateral control module includes kinematic model introduction and the principle of Pure Pursuit algorithm.

Images