A method and system for real-time acquisition of autonomous driving ROS system data based on 5G network cloud platform

Abstract

The present invention relates to a method and system for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform. The method includes M1: after the vehicle is powered on, the 5G module of the vehicle's autonomous driving controller is connected to the tunnel server through the 5G network, and the tunnel client of the vehicle's autonomous driving controller initiates a TCP connection request to the tunnel server, performs relevant authentication and key exchange, and establishes a data transmission tunnel; M2: the cloud platform's Webviz sends a data request to the tunnel server through a websocket, and the tunnel server transmits the data request to the tunnel client through a data transmission tunnel. The present invention not only solves the problem that in a 5G public network environment, the cloud platform cannot actively obtain autonomous driving ROS system data in real time on demand because the on-board terminal has no fixed IP, but also can achieve data communication between services that cannot be directly connected without changing the original service message protocol.

Description

Technical Field

[0001] The present invention relates to the field of autonomous driving technology, and in particular to a method and system for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform. Background Art

[0002] In the field of autonomous driving, the industry generally uses ROS as the foundational technical framework for autonomous driving system development. This framework coordinates data communication and control across multiple vehicle controllers, simplifying system development. Currently, autonomous vehicle systems are primarily developed based on the first-generation version of ROS. This version features a centralized node in the system, the ROS Master. Within the overall network communication architecture, this node acts as the management center, managing each ROS system node. Communication between nodes is also facilitated by the master, allowing point-to-point communication between nodes.

[0003] Although the new generation of ROS is decentralized, its recent release means many manufacturers are still in the observation and verification phase, and it has yet to see widespread adoption. To monitor the status of the ROS system, autonomous driving typically requires sending autonomous driving data to external systems or even cloud platforms for visualization.

[0004] In existing technologies, tools like Rviz or Webviz are often used to visualize autonomous driving monitoring data. However, Rviz is highly dependent on the ROS Master node and cannot run independently of the ROS system. Webviz services usually run in the cloud and need to interact with ROS for data.

[0005] To facilitate data exchange between external systems and ROS, the community provides the ROSBridge tool, which implements a data proxy for the ROS system. External systems can access the ROSBridge service to interact with the ROS system. As a proxy tool, ROSBridge needs to be deployed in the same network domain as the ROS system.

[0006] The latest autonomous driving technologies leverage 5G networks to communicate with cloud platforms and connected vehicles. However, the high construction and maintenance costs of dedicated 5G networks have severely limited their commercial scale. Consequently, most autonomous driving technologies still operate over public 5G networks. In such networks, the IP address of vehicle network terminals cannot be fixed, making it impossible for cloud platforms and connected vehicles to connect to and access the ROSBridge service on the vehicle. Consequently, autonomous driving status monitoring and data querying typically require developers to connect directly to the vehicle controller. This requires extremely high professional skills and completely excludes operators, leaving non-professionals with no effective means of monitoring autonomous driving status.

[0007] In addition, existing technologies limit the monitoring of autonomous driving data to within the vehicle, and the cloud cannot efficiently obtain data from the autonomous driving system and conduct real-time analysis and early warning of the data. Summary of the Invention

[0008] In view of the above shortcomings of the existing technology, the present invention provides a method and system for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform. This method not only solves the problem that the cloud platform cannot actively obtain autonomous driving ROS system data in real time on demand because the on-board terminal has no fixed IP address in the 5G public network environment, but also can achieve data communication between services that cannot be directly connected without changing the original service message protocol.

[0009] To achieve the above and other related objectives, the present invention provides a technical solution as follows: a method for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform, comprising the following steps:

[0010] M1: After the vehicle is powered on, the 5G module of the vehicle's autonomous driving controller connects to the tunnel server through the 5G network. The tunnel client of the vehicle's autonomous driving controller initiates a TCP connection request to the tunnel server, performs relevant authentication and key exchange, and establishes a data transmission tunnel.

[0011] M2: Webviz on the cloud platform sends a data request to the tunnel server via websocket, and the tunnel server transmits the data request to the tunnel client via the data transmission tunnel;

[0012] M3: The tunnel client forwards the data request to the ROSBridge system of the vehicle's autonomous driving controller. The ROSBridge system parses the data request and outputs data request information.

[0013] M4: Based on the data request information, the ROS system of the autonomous driving controller obtains the corresponding data and transmits the data to the tunnel server and the Webviz of the cloud platform.

[0014] Furthermore, the tunnel client sends a login message, the tunnel server receives the login message, parses and extracts login authentication information, identifies the identity of the tunnel client, and after the authentication is successful, the tunnel server returns authentication information to the tunnel client.

[0015] Furthermore, the authentication information includes a communication key for communication encryption.

[0016] Furthermore, the tunnel client receives the authentication information, encrypts the heartbeat message according to an encryption algorithm, and sends the heartbeat information to the tunnel server.

[0017] Furthermore, the tunnel client periodically sends the heartbeat message to the tunnel server.

[0018] To achieve the above objectives and other related objectives, the present invention also provides a system for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform. The system includes a cloud platform, a 5G signal tower, and a vehicle autonomous driving controller. The cloud platform includes a Webviz system and a tunnel server for sending data requests and obtaining data information.

[0019] The 5G signal tower is communicatively connected to the tunnel server end;

[0020] The vehicle autonomous driving controller includes a tunnel client, a ROSBridge system, a 5G module and a ROS system;

[0021] The tunnel client is connected to the tunnel server for data transmission;

[0022] The ROSBridge system is connected to the tunnel client and is used for parsing data requests and encrypting data information;

[0023] The ROS system is connected to the ROSBridge system for responding to data requests and sending data information;

[0024] The 5G module is communicatively connected to the 5G signal tower.

[0025] Furthermore, the system also includes a self-driving camera for acquiring image data information of the vehicle, which is connected to the vehicle automatic driving controller.

[0026] Furthermore, the system also includes a laser radar for acquiring point cloud data information of the vehicle, which is connected to the vehicle automatic driving controller.

[0027] Furthermore, the vehicle automatic driving controller also includes a lidar module for receiving lidar signal data and filtering point cloud data information.

[0028] Furthermore, the vehicle automatic driving controller also includes an image data processing module for initializing and filtering image data.

[0029] The present invention has the following positive effects:

[0030] 1. The present invention uses a tunnel client program deployed and installed on the autonomous driving controller to actively initiate a tunnel connection, and the on-board terminal actively connects to the cloud platform service, establishing a TCP persistent connection between the vehicle and the cloud platform, and building an encrypted data transmission channel between the vehicle controller and the cloud platform. This solves the problem in the 5G public network environment where the cloud platform cannot actively obtain autonomous driving ROS system data in real time on demand because the on-board terminal has no fixed IP address.

[0031] 2. The two sides of the tunnel of the present invention can encrypt the original data message and encapsulate it into a tunnel transmission message. The two ends extract the complete message in the tunnel based on the message protocol header information, unpack the message according to the agreement, and then send it to their respective downstream services. In this way, data communication can be completed between services that cannot be directly connected without changing the original message protocol of the service.

[0032] 3. The present invention can achieve real-time on-demand acquisition of vehicle autonomous driving ROS system data by the cloud platform in a 5G public network environment without changing any existing protocols and business processes. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 Schematic diagram of the process of the present invention;

[0034] Figure 2 This is a system framework diagram of the present invention;

[0035] Figure 3 Schematic diagram of the data transmission process of the present invention. DETAILED DESCRIPTION

[0036] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0037] Example 1: Figure 1 As shown, a method for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform includes the following steps:

[0038] M1: After the vehicle is powered on, the 5G module of the vehicle's autonomous driving controller connects to the tunnel server through the 5G network. The tunnel client of the vehicle's autonomous driving controller initiates a TCP connection request to the tunnel server, performs relevant authentication and key exchange, and establishes a data transmission tunnel.

[0039] M2: Webviz on the cloud platform sends a data request to the tunnel server via websocket, and the tunnel server transmits the data request to the tunnel client via the data transmission tunnel;

[0040] M3: The tunnel client forwards the data request to the ROSBridge system of the vehicle's autonomous driving controller. The ROSBridge system parses the data request and outputs data request information.

[0041] M4: Based on the data request information, the ROS system of the autonomous driving controller obtains the corresponding data and transmits the data to the tunnel server and the Webviz of the cloud platform.

[0042] The tunnel client sends a login message, the tunnel server receives the login message, parses and extracts login authentication information, identifies the identity of the tunnel client, and after the authentication is successful, the tunnel server returns the authentication information to the tunnel client.

[0043] The authentication information includes a communication key for communication encryption.

[0044] The tunnel client receives the authentication information, encrypts the heartbeat message according to an encryption algorithm, and sends the heartbeat message to the tunnel server.

[0045] The tunnel client periodically sends the heartbeat message to the tunnel server.

[0046] Example 2: Based on the method of obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform in Example 1, the present invention is further described below.

[0047] like Figure 2 As shown, in order to achieve the above-mentioned and other related purposes, the present invention provides a system for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform, the system comprising a cloud platform, a 5G signal tower, and a vehicle autonomous driving controller, the cloud platform comprising a Webviz system and a tunnel server for sending data requests and obtaining data information; the 5G signal tower is communicatively connected to the tunnel server;

[0048] The vehicle autonomous driving controller includes a tunnel client, a ROSBridge system, a 5G module and a ROS system;

[0049] The tunnel client is connected to the tunnel server for data transmission;

[0050] The ROSBridge system is connected to the tunnel client and is used for parsing data requests and encrypting data information;

[0051] The ROS system is connected to the ROSBridge system for responding to data requests and sending data information;

[0052] The 5G module is communicatively connected to the 5G signal tower.

[0053] Among them, the system also includes a self-driving camera, which is used to obtain the vehicle's image data information and is connected to the vehicle's automatic driving controller; the system also includes a lidar, which is used to obtain the vehicle's point cloud data information and is connected to the vehicle's automatic driving controller; the vehicle's automatic driving controller also includes a lidar module, which is used to receive lidar signal data and filter point cloud data information; the vehicle's automatic driving controller also includes an image data processing module, which is used to initialize and filter image data.

[0054] Specifically, if Figure 3 As shown in the figure, before the tunnel transmits data, the original data needs to be packaged and a protocol header needs to be added. Before the tunnel end receives the data and hands it over to other services, it needs to unpack the transmitted data. When packaging, the programs at both ends of the tunnel will encrypt and decrypt the message payload according to the key agreed upon in the login message to ensure the security of data transmission in the tunnel.

[0055] In summary, the present invention not only solves the problem in the 5G public network environment where the cloud platform cannot actively obtain autonomous driving ROS system data in real time on demand because the on-board terminal has no fixed IP, but also can achieve data communication between services that cannot be directly connected without changing the original message protocol of the service.

[0056] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for obtaining autonomous driving ROS system data in real time based on a 5G network cloud platform, characterized in that: The following steps are involved: M1: After the vehicle is powered on, the 5G module of the vehicle's autonomous driving controller connects to the tunnel server through the 5G network. The tunnel client of the vehicle's autonomous driving controller initiates a TCP connection request to the tunnel server, performs relevant authentication and key exchange, and establishes a data transmission tunnel. M2: Webviz on the cloud platform sends a data request to the tunnel server via websocket, and the tunnel server transmits the data request to the tunnel client via the data transmission tunnel; M3: The tunnel client forwards the data request to the ROSBridge system of the vehicle's autonomous driving controller. The ROSBridge system parses the data request and outputs data request information. M4: Based on the data request information, the ROS system of the autonomous driving controller obtains the corresponding data and transmits the data to the tunnel server and the Webviz of the cloud platform.

2. The method for obtaining real-time autonomous driving ROS system data based on a 5G network cloud platform according to claim 1 is characterized in that: The tunnel client sends a login message, the tunnel server receives the login message, parses and extracts login authentication information, identifies the identity of the tunnel client, and after the authentication is successful, the tunnel server returns the authentication information to the tunnel client.

3. The method for obtaining real-time autonomous driving ROS system data based on a 5G network cloud platform according to claim 2 is characterized in that: The authentication information includes a communication key for communication encryption.

4. The method for obtaining real-time autonomous driving ROS system data based on a 5G network cloud platform according to claim 2, characterized in that: The tunnel client receives the authentication information, encrypts the heartbeat message according to an encryption algorithm, and sends the heartbeat information to the tunnel server.

5. The method for obtaining real-time autonomous driving ROS system data based on a 5G network cloud platform according to claim 4 is characterized in that: The tunnel client periodically sends the heartbeat message to the tunnel server.

6. A system for acquiring autonomous driving ROS system data in real time based on a 5G network cloud platform, the system comprising a cloud platform, a 5G signal tower, and an autonomous driving vehicle controller, characterized by: The cloud platform includes a Webviz system and a tunnel server for sending data requests and obtaining data information; The 5G signal tower is communicatively connected to the tunnel server end; The vehicle autonomous driving controller includes a tunnel client, a ROSBridge system, a 5G module and a ROS system; The tunnel client is connected to the tunnel server for data transmission; The ROSBridge system is connected to the tunnel client and is used for parsing data requests and encrypting data information; The ROS system is connected to the ROSBridge system for responding to data requests and sending data information; The 5G module is communicatively connected to the 5G signal tower.

7. The system for acquiring autonomous driving ROS system data in real time based on a 5G network cloud platform according to claim 6, characterized in that: The system also includes a self-driving camera for acquiring image data information of the vehicle and connected to the vehicle automatic driving controller.

8. The system for acquiring autonomous driving ROS system data in real time based on a 5G network cloud platform according to claim 6, characterized in that: The system also includes a laser radar for acquiring point cloud data information of the vehicle, which is connected to the vehicle automatic driving controller.

9. The system for acquiring autonomous driving ROS system data in real time based on a 5G network cloud platform according to claim 8, characterized in that: The vehicle automatic driving controller also includes a lidar module for receiving lidar signal data and filtering point cloud data information.

10. The system for acquiring autonomous driving ROS system data in real time based on a 5G network cloud platform according to claim 9, characterized in that: The vehicle automatic driving controller also includes an image data processing module for initializing and filtering image data.

Images