Method for extracting moving track of indoor miniature intelligent vehicle

Abstract

The invention discloses a moving track extraction method for an indoor miniature intelligent vehicle. According to the method, a motion capture system is combined with a reflective ball on the surface of the miniature intelligent vehicle, the motion trail of the intelligent vehicle is accurately captured, the three-dimensional position coordinates of the intelligent vehicle are calculated in real time, the driving strategy of the intelligent vehicle is adjusted in real time through external environment data (such as traffic lights and traffic signs), and the safety and operation efficiency of the intelligent vehicle are further improved. Real-time track data is uploaded to the cloud control system through the vehicle-mounted Wi-Fi module, the cloud control system and the Kafka process and analyze the uploaded data, and efficient operation of the intelligent vehicle in a complex indoor environment is ensured. The method can realize high-precision and high-real-time track extraction in an indoor complex environment, is widely applied to the fields of intelligent vehicle control, logistics distribution, education and the like, and has relatively high intelligence, adaptability and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent vehicles, and more particularly, to a method for extracting the running trajectory of an indoor miniature intelligent vehicle. Background Art

[0002] With the development of intelligent technologies, intelligent vehicles are increasingly widely used in various environments, especially in indoor environments. The application scenarios of indoor intelligent vehicles include, but are not limited to, item delivery, logistics management, entertainment interaction, etc. However, the trajectory extraction and control of indoor intelligent vehicles remain technical challenges. Currently, most indoor intelligent vehicle trajectory extraction methods rely on traditional sensor technologies, such as infrared sensors, lidar, or ultrasonic sensors. These sensors are easily interfered with in complex indoor environments. Especially when the intelligent vehicle performs high-precision movements in a narrow space, the measurement accuracy and reliability of the sensors often cannot meet the actual requirements. For example, although lidar can provide relatively high-precision distance measurements, its performance will be greatly reduced under complex indoor lighting or reflection interference. And infrared sensors are easily affected by factors such as light changes and object occlusion, resulting in inaccurate data and ultimately affecting the running stability and safety of the intelligent vehicle.

[0003] In view of the deficiencies in the prior art, the present invention proposes a novel method for extracting the trajectory of an indoor miniature intelligent vehicle. This method combines motion capture technology, wireless communication, and a cloud control system to efficiently and accurately extract and transmit the running trajectory information of the miniature intelligent vehicle in the indoor environment for real-time monitoring and trajectory adjustment. Summary of the Invention

[0004] The present invention provides a method for extracting the running trajectory of an indoor miniature intelligent vehicle, aiming to improve the running stability and intelligent level of the miniature intelligent vehicle in the indoor environment through high-precision trajectory data collection and real-time monitoring of the cloud control system. This method mainly solves the problems of insufficient accuracy, poor real-time performance, and multi-vehicle cooperative control in traditional technologies, and enhances the system's response ability to environmental changes through the cooperation between the cloud control system and the vehicle.

[0005] In a first aspect, the present invention provides a method for extracting the motion trajectory of a miniature intelligent vehicle using a motion capture system. Specifically, the system arranges multiple high-precision cameras in an indoor environment and establishes a coordinate system and a measurement range. The road network and the initial path traveled by the miniature intelligent vehicle are drawn in three ways: CAD, SUMO, and the cloud control system. The initial road network, path, and speed information are sent through the cloud control system. When the miniature intelligent vehicle moves in the indoor environment, the reflective balls installed on the vehicle body will be tracked in real time by the cameras of the motion capture system. The motion trajectory data of the reflective balls is converted into the three-dimensional position of the vehicle. The system accurately obtains the motion trajectory of the vehicle through real-time collection and analysis of this data. Compared with traditional sensors (such as lidar, ultrasonic sensors, etc.), the motion capture system of the present invention reduces the influence of environmental interference (such as light changes, object occlusion, etc.) on the trajectory accuracy through optical capture technology, improving the stability and reliability of data collection.

[0006] In a second aspect, the present invention provides a method for real-time monitoring and environmental data integration of a miniature intelligent vehicle through a cloud control system. The miniature intelligent vehicle receives coordinates through a WiFi module and transmits them to the cloud control system; the cloud control system mainly monitors the trajectory data of the miniature intelligent vehicle in real time and uploads the relevant data to the cloud for storage and processing. The cloud control system can monitor the running state of the vehicle in real time and provide key external environmental information for the miniature intelligent vehicle. The cloud control system can also obtain the data information of other important devices on the road (such as traffic lights, traffic signs, etc.) in real time and transmit this data to the miniature intelligent vehicle. Based on this environmental data, the miniature intelligent vehicle can make timely responses, such as automatically decelerating or stopping when approaching a traffic light, ensuring the safety and efficient operation of the vehicle. In addition, the cloud control system can also monitor the running conditions of multiple vehicles in real time, providing support for the collaborative work of the vehicle fleet.

[0007] Through the innovations in the above two aspects, the present invention realizes high-precision trajectory data collection and efficient external environment integration. This method can not only ensure the stable operation of the miniature intelligent vehicle in a complex environment, but also improve the intelligent level of the system, enabling the vehicle to make timely and accurate responses according to environmental changes and external signals, significantly improving the operation efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 The overall physical logic framework diagram of the present invention;

[0009] Figure 2 Schematic diagram of initial path drawing based on CAD;

[0010] Figure 3 Schematic diagram of initial path drawing based on SUMO;

[0011] Figure 4Schematic diagram of initial path drawing based on cloud control system;

[0012] Figure 5 Schematic diagram of road network information distribution;

[0013] Figure 6 Schematic diagram of initial path distribution;

[0014] Figure 7 Schematic diagram of initial speed distribution;

[0015] Figure 8 Schematic diagram of vehicle information inspection;

[0016] Figure 9 Schematic diagram of real-time data transmission situation;

[0017] Figure 10 Schematic diagram of traffic light configuration. Specific implementation method

[0018] The indoor micro-scale intelligent vehicle operation trajectory extraction method provided by the present invention, based on the deep collaborative work of the motion capture system and the cloud control system, can accurately and stably extract the operation trajectory of the micro-scale intelligent vehicle, and realize real-time monitoring and dynamic adjustment of the entire vehicle life cycle. This method integrates high-precision spatial positioning technology, real-time data stream processing technology and multi-device collaborative control technology, providing a systematic and intelligent solution for the operation of micro-scale intelligent vehicles in complex indoor environments. The overall physical logic framework is as Figure 1 shown, and its specific implementation method is as follows:

[0019] First, arrange the motion capture system and the virtual road network projection system in the laboratory environment. The motion capture system consists of several high-precision cameras. Through a scientifically designed layout strategy, it can cover the key areas of the entire experimental scene to ensure capturing the full trajectory of the micro-scale intelligent vehicle. Reflective balls are installed on the surface of the micro-scale intelligent vehicle as motion markers. Through multi-angle real-time capture by the cameras of the motion capture system and combined with an advanced optical calculation model, the real-time coordinates of the reflective balls in three-dimensional space are accurately obtained, forming the core data source of the micro-scale intelligent vehicle movement. The virtual road network projection provides a highly simulated traffic environment for the experiment and supports experimental requirements through diversified scene construction.

[0020] After that, the initial path of the micro-scale intelligent vehicle needs to be planned. The present invention proposes three flexible and efficient implementation methods to meet the experimental requirements of multiple scenarios.

[0021] The first method uses CAD software to draw the path: First, it is necessary to draw a road network map. Considering the range of the motion capture system and the available indoor area of 4m * 4m, an accurate road network structure of 4000mm * 4000mm is drawn in CAD. Then, for the custom path information, the high-density path point coordinates are obtained through the array export method to generate an initial path with high-precision characteristics and complex geometric shapes. This method can accurately control the geometric parameters of the path, such as the corner radius, curvature, etc., and is an optimal solution for high-precision experiments, as shown in Figure 2 shown below.

[0022] The second method uses SUMO to draw the path: First, it is necessary to draw a virtual road network of 1:20, that is, 80m * 80m, in the virtual traffic simulation platform SUMO. Then, place a vehicle that can follow a custom path in the virtual environment, adjust the simulation step length step-length value = 0.05, and through the Traci interface, call traci.vehicle.getPosition to obtain the trajectory coordinate data of the virtual vehicle's travel, and batch generate the initial path. The advantage of this method is high efficiency, which is suitable for the requirements of batch experimental path planning, as shown in Figure 3 shown below.

[0023] The third method is based on the interactive interface of the cloud control system. By manually drawing a path line by the user, the system automatically captures the path point coordinates and generates an initial path. Although the path accuracy of this method is slightly inferior, the operation is intuitive and fast, and it can directly provide a runnable path, which is suitable for the scenario of rapid verification experiments, as shown in Figure 4 shown below.

[0024] Next, the motion capture system and the cloud control system should be started to ensure that the micro-scale intelligent vehicle can be captured by the motion system. The cloud control system, as the global control center, is responsible for scheduling and managing the entire life cycle of the experiment. The specific operations are as follows: First, send the road network information to the micro-scale intelligent vehicle (as shown in Figure 5 shown below), and the corresponding optional paths will be automatically adjusted to the path set of the corresponding road network. Then, select any initial path and the initial speed of the micro-scale intelligent vehicle under this set, check the path upload situation (as shown in Figure 6 , 7 and Figure 8 shown below) and send the start command. The initial path defines the running trajectory of the vehicle, the initial speed is the preset value when the vehicle starts, and the start command instructs the vehicle to enter the preset running state. At the same time, the cloud control system establishes a stable connection with the micro-scale intelligent vehicle through wireless communication to ensure low-latency and high-reliability transmission of subsequent data and instructions.

[0025] After the vehicle starts running, the motion capture system captures the motion trajectory of the miniature intelligent vehicle in real time and transmits the three-dimensional coordinate data to the vehicle's Wi-Fi module. The Wi-Fi module uses a high-bandwidth and anti-interference communication protocol to ensure seamless data transmission in a complex indoor environment. The miniature intelligent vehicle preprocesses the received data and uploads it to the cloud control system through a wireless network. By subscribing to and publishing specific topics in the Kafka data center, the cloud control system further transmits the data to the Kafka data center to store, process, and distribute the real-time trajectory data. The real-time data is as Figure 9 shown. As a distributed high-throughput message processing platform, Kafka can process massive data streams with millisecond-level latency, thus ensuring the efficient parsing and real-time feedback of vehicle trajectory information.

[0026] The cloud control system can not only dynamically monitor the current position, speed, and operating status of the miniature intelligent vehicle, but also perform multi-dimensional analysis and decision-making adjustments based on the trajectory data and external environment data. For example, when the vehicle trajectory deviates from the initial path or receives a sudden instruction, the cloud control system can quickly generate a corrective path and send it to the miniature intelligent vehicle in real time to ensure the safety and efficiency of the operation task.

[0027] In addition, the cloud control system can integrate data with other intelligent devices in the indoor environment, such as traffic light signals, traffic signs, and environmental sensor data. These data are transmitted to the miniature intelligent vehicle through the cloud control system to support its dynamic decision-making in complex scenarios. For example, when approaching a traffic light intersection, the miniature intelligent vehicle can adjust its speed in real time or optimize its driving strategy according to traffic sign information, so as to achieve autonomous operation in a highly dynamic indoor environment. The traffic light configuration is as Figure 10 shown.

[0028] Finally, users can subscribe to specific topics in the Kafka data center to obtain the vehicle trajectory data presented in JSON format in real time. These data include detailed information such as three-dimensional coordinates, speed, acceleration, and timestamp, as shown in Table 1. In this way, users can perform visual analysis and secondary development on the experimental data, providing strong support for the operation optimization and algorithm iteration of the miniature intelligent vehicle.

[0029] Table 1

[0030]

[0031] Through the above embodiments, the present invention realizes the precise monitoring and trajectory extraction of the miniature intelligent vehicle in the indoor environment. Through the collaborative work of the motion capture system and the cloud control system, not only can high-precision trajectory extraction and real-time transmission be achieved, but also the adaptability and safety of the intelligent vehicle can be enhanced by integrating external environmental data. This method has a high level of intelligence, can effectively optimize the running trajectory of the miniature intelligent vehicle in a dynamic environment, and ensure that it safely and stably completes the predetermined tasks.

Claims

1. A method for extracting the running trajectory of an indoor miniature intelligent car, characterized in that include: Arrange a motion capture system and a virtual road network projection system in a laboratory environment, wherein the motion capture system includes multiple high-precision cameras covering key areas of the entire experimental scene; A reflective ball is installed on the surface of the miniature smart car as a motion marker, and the motion capture system captures the position of the reflective ball in real time from multiple angles, and combines the optical calculation model to accurately obtain the real-time coordinates of the reflective ball in three-dimensional space, forming a motion data source for the miniature smart car; Using CAD software, SUMO virtual traffic simulation platform, and cloud control system to plan the initial path of the miniature smart car; Start the motion capture system and cloud control system to ensure that the miniature smart car is monitored in real time by the motion capture system. The cloud control system serves as the global control center and is responsible for scheduling and managing the entire life cycle of the experiment. The three-dimensional coordinate data captured by the motion capture system is transmitted to the cloud control system through wireless communication. The cloud control system uses real-time data stream processing technology and high-precision spatial positioning technology to accurately track the position, speed and direction of the miniature smart car, and dynamically adjust the operation strategy of the miniature smart car according to trajectory data and external environment data.

2. The method for extracting the running trajectory of an indoor miniature intelligent car according to claim 1 is characterized in that: The method of drawing a path using CAD software further includes: Draw accurate road network structure in CAD; Obtain high-density path point coordinates through array export; Generates high-precision initial paths with controllable corner radius and curvature.

3. The method for extracting the running trajectory of an indoor miniature intelligent car according to claim 1 is characterized in that: The method of drawing a path using the SUMO virtual traffic simulation platform further includes: Constructing a virtual road network in SUMO; Place virtual vehicles that travel along custom paths in the virtual road network; Adjust the simulation step size, and call traci.vehicle.getPosition through the Traci interface to obtain the trajectory coordinate data of the virtual vehicle, and generate initial paths in batches.

4. The method for extracting the running trajectory of an indoor miniature intelligent car according to claim 1 is characterized in that: The method for manually drawing a path based on the cloud control system further includes: Manually draw path lines through the interactive interface of the cloud control system; The cloud control system automatically captures the coordinates of the path points drawn by the user; Generate initial paths and quickly verify experimental scenarios.

5. The method according to claim 1, characterized in that The wireless communication adopts a high-bandwidth, anti-interference communication protocol to ensure seamless transmission of data in complex indoor environments, and realizes the storage, processing and distribution of real-time trajectory data through the Kafka data center.

6. The method according to claim 1, characterized in that The cloud control system can integrate data with smart devices in indoor environments, supporting the autonomous operation and decision-making adjustments of miniature smart cars in dynamic and complex scenarios.

7. The method according to claim 1, characterized in that Smart devices include signal lights, traffic signs and environmental sensors.

Images