Control method for continuous operation of unmanned container truck in magnetic storm environment

Abstract

The invention provides a control method for continuous operation of an unmanned container truck in a magnetic storm environment, and the method comprises the steps: 1, carrying out the initialization of a sensor on the unmanned container truck after the unmanned container truck is started, building an initial map coordinate, and obtaining the magnetic field intensity and air pressure value of a current environment; 2, a sensor collects data in real time and preprocesses the data; 3, triggering a magnetic storm mode according to the magnetic field intensity of the current environment, and converting the unmanned container truck into fusion positioning; step 4, in a magnetic storm mode, fusing the preprocessed data by adopting extended Kalman filtering and a parameter adaptive adjustment algorithm to obtain attitude and position estimation; step 5, constructing a real-time map according to attitude and position estimation, marking a static target, identifying and tracking a dynamic target, and updating a motion track of the dynamic target; and step 6, based on the constructed real-time map, searching an optimal path for the unmanned container truck to run.

Description

Technical Field

[0001] This application relates to the field of driverless technology, and particularly to a control method for an unmanned container truck to continuously operate in a magnetic storm environment. Background Art

[0002] With the continuous development of driverless technology, the application of unmanned container trucks in port logistics has become more and more extensive. However, under extreme weather conditions such as magnetic storms and in the working environment where multiple quay cranes work side by side, the positioning accuracy of traditional global navigation satellite systems will drop significantly or even fail, which poses a huge challenge to the environmental perception and path planning of unmanned container trucks. Existing mapping technologies are difficult to ensure the safe and efficient operation of unmanned container trucks in magnetic storm weather. Summary of the Invention

[0003] In view of this, the present invention provides a control method for an unmanned container truck to continuously operate in a magnetic storm environment, so as to solve the technical problem that existing technologies are difficult to ensure the safe and efficient operation of unmanned container trucks in magnetic storm weather.

[0004] The present invention provides a control method for an unmanned container truck to continuously operate in a magnetic storm environment. The method includes: Step 1, after starting the unmanned container truck, initialize the sensors on the unmanned container truck, establish an initial map coordinate, and obtain the current environmental magnetic field intensity and air pressure value; Step 2, the sensors collect data in real time and preprocess the data; Step 3, according to the current environmental magnetic field intensity, trigger the magnetic storm mode and convert the unmanned container truck to fusion positioning; Step 4, in the magnetic storm mode, use the extended Kalman filter and parameter adaptive adjustment algorithm to fuse the preprocessed data to obtain attitude and position estimates; Step 5, construct a real-time map according to the attitude and position estimates, mark static targets, identify and track dynamic targets, and update their motion trajectories; Step 6, based on the constructed real-time map, search for the optimal path for the unmanned container truck to drive and operate.

[0005] Further, the sensors include lidar, camera, inertial measurement unit, magnetometer, barometer.

[0006] Further, Step 2 includes: Step 21, the lidar collects point cloud data in real time, removes ground noise points from the point cloud data, and extracts the obstacle contour; Step 22, the camera synchronously collects image frames and uses image processing algorithms to identify semantic information; Step 23, the inertial measurement unit collects acceleration and angular velocity data in real time, fuses the magnetometer data through complementary filtering, and compensates for the magnetic field interference caused by magnetic storms.

[0007] Further, the semantic information includes road signs and container numbers.

[0008] Further, step 3 includes: step 31, continuously monitoring the change rate of the magnetic field intensity output by the magnetometer, and triggering the magnetic storm mode when the magnetic field fluctuation exceeds a preset threshold; step 32, the driverless container truck switches from the global navigation satellite system-inertial measurement unit integrated navigation to the camera-light detection and ranging-inertial measurement unit fusion positioning; step 33, constructing a geomagnetic interference model based on historical magnetic storm data to dynamically correct the outputs of the inertial measurement unit and the magnetometer.

[0009] Further, step 4 includes: step 41, using the extended Kalman filter and the parameter adaptive adjustment algorithm to fuse the light detection and ranging point cloud and the inertial measurement unit data, and outputting attitude and position estimations; step 42, matching the static features identified in the image frame with the light detection and ranging point cloud to optimize the positioning accuracy; step 43, continuously resampling with newly acquired data, and eliminating the cumulative error through graph optimization.

[0010] Further, the parameter adaptive algorithm is the least mean square error algorithm, which realizes the perception data fusion by minimizing the error.

[0011] Further, step 5 includes: step 51, converting the light detection and ranging point cloud into a grid map; step 52, marking static targets; step 53, based on the motion analysis of consecutive frame point clouds, identifying and tracking dynamic targets and updating their motion trajectories.

[0012] Further, step 6 further includes: setting a safety redundancy mechanism when searching for the optimal path.

[0013] Further, the safety redundancy mechanism includes: when the positioning error exceeds the threshold, triggering deceleration and repositioning; when an unknown obstacle is detected, immediately stopping the vehicle and alarming through the remote control system; regularly uploading map data to support the collaborative mapping of multiple driverless container trucks.

[0014] The present invention provides a control method for a driverless container truck to continuously operate in a magnetic storm environment. The method fuses sensor data, performs real-time map updates through advanced positioning algorithms to improve the adaptability to magnetic storm weather, and sets a safety mechanism, mainly for solving the technical problem that it is difficult to ensure the safe and efficient operation of a driverless container truck in magnetic storm weather in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 is a schematic flowchart of a control method for a driverless container truck to continuously operate in a magnetic storm environment provided by the present invention; Figure 2 is a schematic flowchart of another control method for a driverless container truck to continuously operate in a magnetic storm environment provided by the present invention; Figure 3 is a schematic flowchart of a method for converting a driverless container truck into a fusion positioning provided by the present invention; Figure 4 It is a schematic flow diagram of the data fusion method provided by the present invention; Figure 5 It is a schematic flow diagram of the method for constructing a real-time map and updating the movement trajectory provided by the present invention. Detailed implementation manners

[0016] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0017] Embodiment 1: The present invention provides a control method for an unmanned container truck to continuously operate in a magnetic storm environment, as Figure 1 shown, the method includes: Step 1, after starting the unmanned container truck, initialize the sensors on the unmanned container truck, establish an initial map coordinate, and obtain the current environmental magnetic field intensity and air pressure value; Step 2, the sensors collect data in real time and preprocess the data; Step 3, according to the current environmental magnetic field intensity, trigger the magnetic storm mode and convert the unmanned container truck to fusion positioning; Step 4, in the magnetic storm mode, use the extended Kalman filter and the parameter adaptive adjustment algorithm to fuse the preprocessed data to obtain the attitude and position estimation; Step 5, construct a real-time map according to the attitude and position estimation, mark static targets, identify and track dynamic targets, and update their movement trajectories; Step 6, based on the constructed real-time map, search for the optimal path for the unmanned container truck to drive and operate.

[0018] The present application provides a control method for an unmanned container truck to continuously operate in a magnetic storm environment. By fusing lidar, camera, IMU and millimeter wave radar data, combining particle filter and graph optimization algorithm, high-precision positioning under magnetic storm conditions is achieved. The magnetic storm level is monitored in real time through a geomagnetic sensor, and the sensor weights and vehicle driving parameters are adaptively adjusted, solving the technical problem that it is difficult to ensure the safe and efficient operation of an unmanned container truck in magnetic storm weather in the prior art.

[0019] Embodiment 2: The present invention provides a control method for an unmanned container truck to continuously operate in a magnetic storm environment, as Figure 2 shown, the method includes the following steps.

[0020] Step 1: After starting the driverless truck, initialize the sensors on the driverless truck, establish the initial map coordinates, and obtain the current environmental magnetic field intensity and air pressure value. The sensors include lidar, camera, inertial measurement unit, magnetometer, and barometer. When establishing the initial map coordinate system, the current environmental magnetic field intensity and air pressure value are obtained through the magnetometer and barometer, which are used as the basis for magnetic storm detection.

[0021] Step 2: The sensors collect data in real time and preprocess the data. In this application, the sensor data is corrected through a preset magnetic storm weather model, that is, preprocessed, to reduce the impact of magnetic storms on the positioning and mapping accuracy. Step 2 includes: Step 21: The lidar collects point cloud data in real time, removes the ground noise points in the point cloud data, and extracts the obstacle contours. This step removes the ground noise points through filtering, such as voxel filtering.

[0022] Step 22: The camera synchronously collects image frames and uses image processing algorithms to identify semantic information. The semantic information includes road signs and container numbers.

[0023] Step 23: The inertial measurement unit collects acceleration and angular velocity data in real time, fuses the magnetometer data through complementary filtering, and compensates for the magnetic field interference caused by magnetic storms. Step 3: According to the current environmental magnetic field intensity, trigger the magnetic storm mode and convert the driverless truck to integrated positioning. Step 4: In the magnetic storm mode, use the extended Kalman filter and parameter adaptive adjustment algorithm to fuse the preprocessed data to obtain the attitude and position estimation. Step 5: Construct a real-time map based on the attitude and position estimation, mark static targets, identify and track dynamic targets, and update their motion trajectories. Step 6: Based on the constructed real-time map, search for the optimal path for the driverless truck to drive and operate.

[0024] This application provides a control method for a driverless truck to continuously operate in a magnetic storm environment. By fusing lidar, camera, IMU, and millimeter-wave radar data, combining particle filtering and graph optimization algorithms, high-precision positioning under magnetic storm conditions is achieved. The magnetic storm level is real-time monitored through a geomagnetic sensor, and the sensor weights and vehicle driving parameters are adaptively adjusted, solving the technical problem that it is difficult to ensure the safe and efficient operation of a driverless truck in magnetic storm weather in the prior art.

[0025] Embodiment 3: The present invention provides a control method for a driverless truck to continuously operate in a magnetic storm environment, as Figure 1As shown, the method includes the following steps.

[0026] Step 1, after starting the driverless container truck, initialize the sensors on the driverless container truck, establish the initial map coordinates, and obtain the current environmental magnetic field intensity and air pressure value; Step 2, the sensors collect data in real time and preprocess the data; Step 3, according to the current environmental magnetic field intensity, trigger the magnetic storm mode and convert the driverless container truck to integrated positioning; As Figure 3 shown, Step 3 includes: Step 31, monitor the change rate of the magnetic field intensity output by the magnetometer in real time, and trigger the magnetic storm mode when the magnetic field fluctuation exceeds the preset threshold; Step 32, the driverless container truck switches from the global navigation satellite system-inertial measurement unit integrated navigation to the camera-lidar-inertial measurement unit integrated positioning; Step 33, construct a geomagnetic interference model based on historical magnetic storm data and dynamically correct the outputs of the inertial measurement unit and the magnetometer.

[0027] Step 4, in the magnetic storm mode, use the extended Kalman filter and the parameter adaptive adjustment algorithm to fuse the preprocessed data to obtain the attitude and position estimation; As Figure 4 shown, Step 4 includes: Step 41, use the extended Kalman filter and the parameter adaptive adjustment algorithm to fuse the lidar point cloud and the inertial measurement unit data, and output the attitude and position estimation; The parameter adaptive algorithm is the least mean square error algorithm, which realizes the perception data fusion by minimizing the error. The extended Kalman filter and the parameter adaptive adjustment algorithm use the surrounding environment data collected in real time by multiple sensors such as lidar, camera, and inertial measurement unit for data fusion to improve the accuracy and robustness of environmental perception.

[0028] Step 42, match the static features identified in the image frame with the lidar point cloud to optimize the positioning accuracy; Step 43, continuously resample using the newly collected data, and eliminate the cumulative error through graph optimization.

[0029] This application combines advanced positioning algorithms such as particle filter and graph optimization to process the fused sensor data, and realizes high-precision positioning and environmental map construction.

[0030] Step 5, construct a real-time map according to the attitude and position estimation, mark the static targets, identify and track the dynamic targets, and update their motion trajectories; This application uses a sliding window technique to update the map of the environment where the driverless container truck is located in real time, ensuring the timeliness and accuracy of the map information. As Figure 5 shown, step 5 includes the following steps.

[0031] Step 51, convert the lidar point cloud into a grid map; Step 52, mark static targets; Step 53, based on the motion analysis of consecutive frame point clouds, identify and track dynamic targets and update their motion trajectories.

[0032] Step 6, based on the constructed real-time map, search for the optimal path for the driverless container truck to drive and run, and at the same time set up a safety redundancy mechanism.

[0033] The technical solution provided by this application also sets up a multiple safety detection mechanism, that is, a safety redundancy mechanism, to monitor the running state of the driverless container truck in real time. Once an abnormality is detected, corresponding measures are immediately taken to ensure the safe operation of the driverless container truck. The safety redundancy mechanism includes: when the positioning error exceeds the threshold, trigger deceleration and repositioning; when an unknown obstacle is detected, stop immediately and alarm through the remote control system; regularly upload map data to support the collaborative mapping of multiple driverless container trucks.

[0034] This application provides a control method for a driverless container truck to continuously operate in a magnetic storm environment. By fusing lidar, camera, IMU, and millimeter-wave radar data, and combining particle filtering and graph optimization algorithms, high-precision positioning under magnetic storm conditions is achieved. The magnetic storm level is monitored in real time through a geomagnetic sensor, and the sensor weights and vehicle driving parameters are adaptively adjusted, solving the technical problem that it is difficult for the existing technology to ensure the safe and efficient operation of the driverless container truck in magnetic storm weather.

[0035] In summary, the embodiment of the present invention provides a control method for a driverless container truck to continuously operate in a magnetic storm environment. By adopting multi-sensor data fusion and advanced positioning algorithms in port magnetic storm weather, high-precision environment perception and real-time map construction of the driverless container truck are realized, effectively solving the impact of magnetic storm weather on the operation of the driverless container truck, ensuring the safety and attendance rate of the driverless container truck under extreme weather conditions, and improving the vehicle operation efficiency and economic benefits.

[0036] The above are only the preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A control method for an unmanned container truck to continuously operate in a magnetic storm environment, characterized in that, The method includes: Step 1, after starting the driverless container truck, initialize the sensors on the driverless container truck, establish the initial map coordinates, and obtain the current environmental magnetic field intensity and air pressure value; Step 2, the sensors collect data in real time and preprocess the data; Step 3, according to the current environmental magnetic field intensity, trigger the magnetic storm mode and convert the driverless container truck to integrated positioning; Step 4, in the magnetic storm mode, use the extended Kalman filter and parameter adaptive adjustment algorithm to fuse the preprocessed data to obtain the attitude and position estimation; Step 5, construct a real-time map based on the attitude and position estimation, mark static targets, identify and track dynamic targets, and update their motion trajectories; Step 6, based on the constructed real-time map, search for the optimal path for the driverless container truck to drive and operate.

2. The control method for continuous operation of an unmanned container truck in a geomagnetic storm environment according to claim 1, characterized in that, The sensors include lidar, camera, inertial measurement unit, magnetometer, and barometer.

3. The control method for continuous operation of an unmanned container truck in a magnetic storm environment according to claim 2, wherein The Step 2 includes: Step 21, the lidar collects point cloud data in real time, removes the ground noise points in the point cloud data, and extracts the obstacle contours; Step 22, the camera synchronously collects image frames and uses image processing algorithms to identify semantic information; Step 23, the inertial measurement unit collects acceleration and angular velocity data in real time, fuses the magnetometer data through complementary filtering, and compensates for the magnetic field interference caused by magnetic storms.

4. The control method for an unmanned container truck to continuously operate in a magnetic storm environment according to claim 3, characterized in that, The semantic information includes road signs and container numbers.

5. The control method for continuous operation of an unmanned yard truck in a geomagnetic storm environment according to claim 2, wherein The Step 3 includes: Step 31, monitor the change rate of the magnetic field intensity output by the magnetometer in real time, and trigger the magnetic storm mode when the magnetic field fluctuation exceeds the preset threshold; Step 32, the driverless container truck switches from the global navigation satellite system-inertial measurement unit integrated navigation to the camera-lidar-inertial measurement unit integrated positioning; Step 33, construct a geomagnetic interference model based on historical magnetic storm data and dynamically correct the outputs of the inertial measurement unit and the magnetometer.

6. The control method for continuous operation of an unmanned container truck in a magnetic storm environment according to claim 2, wherein The Step 4 includes: Step 41, use the extended Kalman filter and parameter adaptive adjustment algorithm to fuse the lidar point cloud and inertial measurement unit data, and output the attitude and position estimation; Step 42, optimize the positioning accuracy by matching the static features identified in the image frames with the lidar point cloud; Step 43, continuously resample with the newly collected data, and eliminate the cumulative error through graph optimization.

7. The control method for continuous operation of an unmanned container truck in a magnetic storm environment according to claim 6, characterized in that, The parameter adaptive algorithm is the least mean square error algorithm, which realizes the fusion of perception data by minimizing the error.

8. The control method for continuous operation of an unmanned container truck in a geomagnetic storm environment according to claim 2, wherein The Step 5 includes: Step 51, convert the lidar point cloud into a grid map; Step 52, mark static targets; Step 53, based on the motion analysis of consecutive frame point clouds, identify and track dynamic targets, and update their motion trajectories.

9. The control method for an unmanned container truck to continuously operate in a magnetic storm environment according to claim 2, characterized in that, The Step 6 further includes: setting a safety redundancy mechanism when searching for the optimal path.

10. The control method for continuous operation of an unmanned container truck in a magnetic storm environment according to claim 9, wherein, The safety redundancy mechanism includes: when the positioning error exceeds the threshold, trigger deceleration and repositioning; when an unknown obstacle is detected, stop immediately and alarm through the remote control system; regularly upload map data to support the collaborative mapping of multiple driverless container trucks.

Images