Method, system and medium for visually sensing result

Abstract

The invention provides a method, a system and a medium for visually perceiving a result, and a server is developed by using Python and transmits data to a client in a user-defined format through an Ethernet or a CAN (Controller Area Network) bus. And the client uses a visualization tool to receive the self-defined data and perform graph drawing and visualization. The modular design of the server and the client enables data addition and deletion to be flexible, and the server can depend on tools such as Foxglove, so that the attention of bottom layer implementation is reduced, and the application layer development is focused. In addition, through tools such as Wireshark, data can be synchronously recorded, and cross-platform use is supported. Through the separated design of the server and the client, the user-defined data format and transmission protocol, the modular design, the data addition and deletion flexibility, the data security and integrity and the like, the system aims at improving the working efficiency of developers, ensuring the accuracy and integrity of the data, supporting real-time data recording and analysis, and improving the development efficiency of the developers. And powerful support is provided for development and optimization of an automatic driving system.

Description

Technical Field

[0001] The present invention relates to the field of automobile automatic driving, and in particular to a method, system and medium for visualizing perception results. Background Art

[0002] With the rapid development of intelligent and connected technologies, autonomous vehicles have gradually moved from concept to practical application. As a core component of the autonomous driving system, the cockpit domain controller (CDC) plays a vital role. The CDC is the core control unit of the cockpit domain, responsible for integrating and managing multiple subsystems in the cockpit, including but not limited to information display, audio control, communication management, and environmental control. Through centralized management and control, the CDC can achieve a high degree of functional integration and improve the reliability and performance of the cockpit system.

[0003] However, in actual application, CDC and its related perception data face many challenges. The accuracy of perception data directly affects the decision-making effect of the autonomous driving system, while the reliability of CDC determines whether these decisions can be accurately executed. Therefore, ensuring the accuracy of perception data and the reliability of CDC is crucial to the safety and stability of autonomous vehicles.

[0004] To solve these problems, the industry and academia have been exploring various solutions. Data visualization and fault diagnosis technology, as important means, have been widely used in the development and optimization of autonomous driving systems. Through data visualization, developers can more intuitively understand the distribution and change trends of perception data, thereby discovering potential problems. Fault diagnosis technology can help developers quickly locate and resolve errors and faults in CDC.

[0005] At present, in terms of data visualization, some solutions build dedicated visualization platforms to display and analyze the perception data of autonomous driving systems in real time. These platforms usually support multiple data formats and visualization methods, and can customize the display effects according to different needs. Through the visualization platform, developers can intuitively observe the dynamic changes of perception data and discover anomalies and patterns.

[0006] In terms of fault diagnosis, some solutions integrate advanced fault diagnosis systems to monitor and warn the autonomous driving system in real time. These systems can detect and report errors and faults in CDC, helping developers to locate problems and fix them in a timely manner. At the same time, some solutions also provide fault diagnosis algorithms and models to further improve the accuracy and efficiency of fault diagnosis.

[0007] However, although these solutions have achieved certain results in data visualization and fault diagnosis, they still have some limitations. For example, they are too simple in data display and cannot fully display the complexity and diversity of perceived data; they lack accuracy and real-time in fault diagnosis and cannot timely and effectively discover and solve errors and faults in CDC. In addition, rewriting the entire system from the bottom up using general programming languages ​​such as C# or Java leads to slow development and is prone to errors, affecting development efficiency; secondly, directly reusing old visualization tools, although saving time, may cause data verification problems because unified data format processing may cause data distortion; finally, existing tools lack the function of recording data while visualizing, and cannot save real-time data, which increases the difficulty of data collection and limits the depth of subsequent analysis. Summary of the invention

[0008] In view of the defects in the prior art, the purpose of the present invention is to provide a method, system and medium for visualizing perception results, which can visualize the perception data sent by the domain controller, thereby helping developers or technicians to analyze the data more intuitively and accurately find errors in the perception data and CDC.

[0009] In order to achieve the above technical effects, the present invention adopts the following technical solutions:

[0010] According to a first aspect of the present invention, a method for visualizing perception results is provided, which specifically comprises the following steps:

[0011] Step S1. Server development: Use Python to write the server program, and use Ethernet or CAN bus communication to process data reading and parsing; the server reads the original perception data from according to actual needs; converts the original data into structured information through a custom parsing algorithm and packages it into a custom format; uses the network protocol to transmit the data to the client;

[0012] Step S2. Client development: The client receives the custom format data sent by the server, parses it and draws a visualization graph using an image visualization tool; both the server and the client adopt a modular design, support flexible addition and deletion of data modules, and improve system scalability and maintainability;

[0013] Step S3. The client displays the perception data sent by the domain controller in real time, and visualizes and analyzes the data from multiple angles, especially the comparison between the perception data and the control logic output of the cockpit domain controller (CDC); by visually displaying the difference between the perception data and the CDC output, errors can be found and problems can be quickly located;

[0014] Step S4. Use the tool Wireshark to synchronously record the real-time data stream for later analysis and playback;

[0015] During the data transmission process in the above steps, the data is encrypted and integrity checked.

[0016] Preferably, the sensor in step S1 includes a camera, a radar, or a lidar.

[0017] Preferably, it is characterized in that the network protocol in step S1 includes TCP / IP or UDP.

[0018] Preferably, the image visualization tool in step S2 has a data analysis function and supports data screening, statistics and trend analysis; the image visualization includes 2D / 3D image and animation display modes.

[0019] Preferably, the visualization tool in step 2 comprises Foxglove.

[0020] Preferably, the server and the client can both run under different operating systems, including Windows and Ubuntu.

[0021] According to a second aspect of the present invention, a system for visualizing perception results is provided, which is used to implement the above-mentioned method for visualizing perception results.

[0022] According to a third aspect of the present invention, there is provided a computer-readable storage medium having a computer program stored thereon, the program being executed by a processor to implement the above-mentioned method for visualizing perception results.

[0023] Compared with the prior art, the present invention has the following beneficial effects:

[0024] 1. In the method for visualizing perception results provided by the present invention, by using Python for server-side development, the perception data can be quickly read and parsed, and the data can be sent to the client through a customized transmission protocol to ensure the accuracy and completeness of the data.

[0025] 2. The server in the method for visualizing perception results provided by the present invention adopts a modular design, and can flexibly add or delete data modules according to needs, thereby improving the scalability and maintenance efficiency of the system.

[0026] 3. The client-side integration of tools such as Foxglove in the method for visualizing perception results provided by the present invention can display the perception data in real time in multiple forms (2D / 3D, etc.), making the data more intuitive and easy to understand.

[0027] 4. The method for visualizing perception results provided by the present invention supports cross-platform operation and can be run on multiple operating systems such as Windows and Ubuntu.

[0028] 5. The method for visualizing perception results provided by the present invention performs data encryption and verification mechanisms during data transmission to ensure data security and stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments made with reference to the following drawings:

[0030] Figure 1 This is a flowchart of the steps of the method for visualizing perception results described in the first embodiment. DETAILED DESCRIPTION

[0031] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations.

[0032] Therefore, the following detailed description of the embodiments of the present application provided in the accompanying drawings is not intended to limit the scope of the present application for which protection is sought, but merely represents selected embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0033] First Embodiment

[0034] like Figure 1 As shown, this embodiment provides a method for visualizing perception results. By developing the server and the client separately, combined with data processing, transmission, visualization and analysis tools, an efficient, flexible and safe method for sensing data and CDC error detection of autonomous driving systems is provided. The specific steps are as follows:

[0035] Step S1. Server development: The server is responsible for reading, parsing and transmitting data. This part is developed based on Python language and adopts modular design to ensure that the system can be developed quickly and adapt to the needs of different scenarios.

[0036] S1.1 Language selection: Use Python as the server-side development language. Its simplicity, readability and rich library resources can quickly realize data reading and parsing.

[0037] S1.2 Data reading and analysis: The server reads the raw perception data from various sensors (such as cameras, radars, lidars, etc.) in real time or quasi-real time according to actual needs through various communication methods such as Ethernet and CAN bus, and converts the data into structured information through customized parsing algorithms.

[0038] S1.3 Data transmission: The server encapsulates the parsed data in a custom format and sends it to the client via a network protocol (such as TCP / IP or UDP). The custom format should contain enough information so that the client can parse and display it correctly.

[0039] S1.4 Modular design: The server-side framework adopts modular design, which makes the addition and deletion of data flexible. Developers can add or delete data modules according to their needs without making a lot of modifications to the entire system. This design method not only improves the development efficiency of the system, but also makes subsequent upgrades and maintenance easier.

[0040] Step S2. Client development: The main task of the client is to receive data from the server and visualize it. The client uses visualization tools such as Foxglove and analyzes and displays data through a graphical interface.

[0041] S2.1 Selection of visualization tools: The client uses visualization tools such as Foxglove, which usually provide rich graphics drawing and interactive functions and can meet various visualization needs.

[0042] S2.2 Data reception and analysis: The client receives the custom format data sent by the server and analyzes it. The analyzed data can be directly used to draw graphics.

[0043] S2.3 Graph drawing and visualization: Using Foxglove's basic template, the client can draw corresponding graphs based on the received data and perform real-time visualization. This can include multiple chart types such as line charts, bar charts, scatter charts, etc. By visually displaying the differences between the perceived data and the CDC output, it is easy to find errors and quickly locate problems. This integration and customization method makes the visualization effect more in line with actual needs and improves the readability and comprehensibility of the data.

[0044] The technical solution provided in this embodiment adopts a separate design of the server and the client, so that data processing, transmission and visualization can be performed separately, improving the flexibility and scalability of the system. The server focuses on reading, parsing and transmitting data, while the client is responsible for data visualization and display. This design allows each part to be optimized specifically, thereby improving overall performance.

[0045] At the same time, this embodiment adopts a more modular and configurable development framework to make data addition and deletion flexible. This design allows developers to quickly add or delete data modules according to actual needs without making large-scale modifications to the entire system, thereby improving development efficiency. In addition, this embodiment also provides a wealth of pre-set components and templates, allowing developers to quickly build and customize the required visual interface, further accelerating the development process.

[0046] At the same time, the method described in this embodiment provides a flexible data processing mechanism, allowing developers to customize data formats and parsing rules according to actual needs. The server can encapsulate the read and parsed data in a customized format and send it to the client through a specific transmission protocol. This customized design enables data to be transmitted efficiently and accurately between the server and the client, while avoiding parsing errors caused by data format mismatches. At the same time, the method also provides a data verification function to ensure that the data sent during the visualization process is consistent with the actual needs, ensure the accuracy and integrity of the data, and avoid data format problems caused by reusing old visualization tools.

[0047] Step S3. Data recording and cross-platform support

[0048] S3.1 Data recording: By integrating network analysis tools such as Wireshark, data can be recorded during data transmission, which realizes the function of recording data while visualizing to meet the needs of developers in data analysis and debugging. By integrating the real-time data recording module, key data can be automatically saved during visualization and convenient data playback function can be provided. In this way, developers can not only observe data changes in real time during visualization, but also conduct in-depth analysis of recorded data in subsequent stages to better understand system behavior and performance.

[0049] S3.2 Cross-platform support: This technical solution adopts a cross-platform design concept. Both the server and the client can run on different operating systems such as Windows and Ubuntu. This improves the flexibility and applicability of the solution. Encryption and integrity verification are required during data transmission to ensure the security and reliability of data when used across platforms.

[0050] This technical solution aims to achieve fast reading, parsing, transmission and visualization of data through separate development of the server and the client. The server is developed using Python, which is responsible for reading and parsing data, and transmitting data to the client in a custom format via Ethernet or CAN bus. The client uses visualization tools such as Foxglove to receive custom data and use basic templates for graphics drawing and visualization. The modular design of the server and client makes the addition and deletion of data flexible. At the same time, the server can rely on tools such as Foxglove to reduce the focus on the underlying implementation and focus on application layer development. In addition, through tools such as Wireshark, data can be recorded synchronously to support cross-platform use.

[0051] Second Embodiment

[0052] This embodiment provides a system for visualizing perception results, which is used to implement the method for visualizing perception results described in the first embodiment.

[0053] Embodiment 3

[0054] This embodiment provides a computer medium having a computer program stored thereon, which is executed by a processor to implement the method for visualizing perception results described in the first embodiment.

[0055] The above describes the specific embodiments of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical concept of the present invention.

Claims

1. A method for visualizing perception results, characterized in that: The specific steps include: Step S1. Server development: Use Python to write the server program, and use Ethernet or CAN bus communication to process data reading and parsing; the server reads the original perception data from according to actual needs; converts the original data into structured information through a custom parsing algorithm and packages it into a custom format; Use network protocols to transmit data to the client; Step S2. Client development: The client receives the custom format data sent by the server, parses it and draws a visualization graph using an image visualization tool; The server and client are both modularly designed to support flexible addition and deletion of data modules, thus improving system scalability and maintainability; Step S3. The client displays the perception data sent by the domain controller in real time, and visualizes and analyzes the data from multiple angles, especially the comparison between the perception data and the control logic output of the cockpit domain controller (CDC); by visually displaying the difference between the perception data and the CDC output, errors can be found and problems can be quickly located; Step S4. Use the tool Wireshark to synchronously record the real-time data stream for later analysis and playback; During the data transmission process in the above steps, the data is encrypted and integrity checked.

2. The method for visualizing perception results according to claim 1, characterized in that: The sensors in step S1 include cameras, radars, and lidars.

3. The method for visualizing perception results according to claim 1, characterized in that: The network protocol in step S1 includes TCP / IP or UDP.

4. The method for visualizing perception results according to claim 1, characterized in that: The image visualization tool in step S2 has a data analysis function and supports data screening, statistics and trend analysis; the image visualization includes 2D / 3D image and animation display modes.

5. The method for visualizing perception results according to claim 1, characterized in that: Visualization tools in step 2 include Foxglove.

6. The method for visualizing perception results according to claim 1, characterized in that: The server and the client can both run under different operating systems, including Windows and Ubuntu.

7. A system for visualizing perception results, characterized in that: A method for implementing the visual perception result described in any one of claims 1 to 6.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: The program is executed by a processor to implement the method for visualizing perception results as described in any one of claims 1 to 6.

Images