Vehicle control methods and devices, storage media and electronic equipment

Abstract

This application provides a vehicle control method and apparatus, storage medium, and electronic device, relating to the fields of smart mines, autonomous driving, and unmanned vehicles. The method includes: fusing the perception results of a first target object acquired by a lidar and the perception results of a second target object acquired by a millimeter-wave radar to obtain a target object perception queue; and fusing the target object perception queue with a first target object tracking queue using a target fusion strategy to obtain a second target object tracking queue. The target fusion strategy includes: for each perception element, if a matching first tracking element exists, determining whether its source includes both lidar and millimeter-wave radar; if both are included, determining the target sensor speed information based on the respective speed information of the lidar and millimeter-wave radar, and then updating the first tracking element to obtain the second tracking element. This application ensures the reliability of target object detection and improves the safety and efficiency of autonomous driving in mines.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical fields of smart mines, automatic driving and unmanned vehicles, and particularly relates to a vehicle control method and device, a storage medium and an electronic device. BACKGROUND

[0002] Mine automatic driving needs to accurately detect target objects (for example, specific obstacles) and measure their speeds to ensure the safe and efficient operation of vehicles. Laser radar can accurately perceive the edge profile of a target object, but cannot detect the other side of the target object, resulting in inaccurate speed measurement; millimeter wave radar can provide position and speed information of a target object, but due to hardware limitations, the lateral distance and position may change greatly, resulting in inaccurate speed measurement. Therefore, in order to improve the speed measurement accuracy, it is necessary to effectively fuse the speeds of different sensors to ensure the safe and smooth operation of automatic driving.

[0003] The current speed measurement method mainly filters the results of different sensors, but does not consider that the sensor characteristics may introduce bias in some scenarios, thereby failing to achieve optimal speed fusion effect. SUMMARY

[0004] Therefore, an embodiment of the present application provides a vehicle control method and device, a storage medium and an electronic device.

[0005] In a first aspect, an embodiment of the present application provides a vehicle control method, comprising: obtaining a perception result of a first target object determined based on a laser radar of a target vehicle; obtaining a perception result of a second target object determined based on a millimeter wave radar of the target vehicle; fusing the perception result of the first target object and the perception result of the second target object to obtain a target object perception queue, the target object perception queue comprising a plurality of perception elements; fusing the target object perception queue and a first target object tracking queue based on a target fusion strategy to obtain a second target object tracking queue, so as to control the target vehicle to move based on the second target object tracking queue, the first target object tracking queue comprising a plurality of first tracking elements, and the second target object tracking queue comprising a plurality of second tracking elements. The target fusion strategy comprises: for each perception element, if there is a first tracking element matching the perception element, determining whether the information source in the perception element includes the laser radar and the millimeter wave radar, if the information source includes the laser radar and the millimeter wave radar, determining target sensor speed information based on the speed information of the laser radar and the speed information of the millimeter wave radar, and updating the first tracking element based on the target sensor speed information to obtain the second tracking element corresponding to the first tracking element.

[0006] In some implementations of the first aspect, based on the speed information of the lidar and the speed information of the millimeter-wave radar, the target sensor speed information is determined, including: if the speed information of the millimeter-wave radar meets a target condition, and the target vehicle is not turning at the moment, the speed information of the millimeter-wave radar is determined as the target sensor speed information; if the speed information of the millimeter-wave radar does not meet the target condition, and / or the target vehicle is turning at the moment, the speed information of the lidar is determined as the target sensor speed information; preferably, the target vehicle includes an autonomous vehicle; preferably, the target sensor speed information is optimal sensor speed information; preferably, the first target object perception result and the second target object perception result include perception results for obstacles.

[0007] In some implementations of the first aspect, the target condition includes: a number of speed information in a speed information queue in which the speed information of the millimeter-wave radar is located is greater than a first target number; a standard deviation between the speed information in the speed information queue is less than a first target difference value; a maximum deviation of the speed information in the speed information queue from a mean value of speed information of the speed information queue is less than a second target difference value; a difference between the latest two time information in a first time information queue corresponding to the speed information of the millimeter-wave radar is less than a third target difference value; preferably, the number of speed information in the speed information queue is less than a second target number.

[0008] In some implementations of the first aspect, the method of determining whether the target vehicle is turning includes: obtaining a current orientation queue of the target vehicle, and a second time information queue corresponding to the current orientation queue; based on the current orientation queue and the second time information queue, using a least squares method to calculate coefficients of a fitting polynomial; based on the coefficients of the fitting polynomial, calculating an angular velocity of the target vehicle; if the angular velocity of the target vehicle is less than an angular velocity threshold, it is determined that the target vehicle is not turning; if the angular velocity of the target vehicle is greater than or equal to the angular velocity threshold, it is determined that the target vehicle is turning.

[0009] In some implementations of the first aspect, based on the speed information of the lidar and the speed information of the millimeter-wave radar, the target sensor speed information is determined, including: if the speed information of the millimeter-wave radar does not meet the target condition, and / or the target vehicle is turning at the moment, a position information queue in which position information of the lidar is located and a third time information queue corresponding to the speed information of the lidar are determined; if a number of position information in the position information queue is greater than a third target number, and a difference between the latest two time information in the third time information queue is less than a fourth target difference value, based on the position information queue and the third time information queue, a target speed information is calculated, and the target speed information is determined as the target sensor speed information.

[0010] In some implementations of the first aspect, the target fusion strategy further includes: if the information source only includes the lidar, determining the speed information of the lidar as the target sensor information; and preferably, if there is no first tracking element matching the perception element, directly adding the perception element to the first target object tracking queue.

[0011] In some implementations of the first aspect, fusing the perception result of the first target object and the perception result of the second target object to obtain the target object perception queue includes: matching the perception result of the first target object and the perception result of the second target object; if the matching is successful, creating a perception element and updating the time information of the target object and the position information of the target object contained in the perception element based on the first target object perception result, wherein the information source of the perception element includes the lidar and the millimeter wave radar; if the matching is unsuccessful, creating a perception element and updating the time information of the target object and the position information of the target object corresponding to the perception element based on the first target object perception result or the second target object perception result, wherein the information source of the perception element is the lidar or the millimeter wave radar; and adding the perception element created when the matching is successful or unsuccessful to the target object perception queue.

[0012] In the second aspect, an embodiment of the present application provides a control device of a vehicle, including: a first acquisition module configured to acquire a first target object perception result determined based on a lidar of a target vehicle; a second acquisition module configured to acquire a second target object perception result determined based on a millimeter wave radar of the target vehicle; a first fusion module configured to fuse the first target object perception result and the second target object perception result to obtain a target object perception queue, the target object perception queue including a plurality of perception elements; and a second fusion module configured to fuse the target object perception queue and a first target object tracking queue based on a target fusion strategy to obtain a second target object tracking queue, so as to control the target vehicle to move based on the second target object tracking queue, the first target object tracking queue including a plurality of first tracking elements, and the second target object tracking queue including a plurality of second tracking elements. The target fusion strategy includes: for each perception element, if there is a first tracking element matching the perception element, determining whether the information source in the perception element includes the lidar and the millimeter wave radar, if the information source includes the lidar and the millimeter wave radar, determining target sensor speed information based on speed information of the lidar and speed information of the millimeter wave radar, and updating the first tracking element based on the target sensor speed information to obtain a second tracking element corresponding to the first tracking element.

[0013] In the third aspect, an embodiment of the present application provides a computer readable storage medium storing a computer program for executing the control method of the vehicle of the first aspect.

[0014] In a fourth aspect, an embodiment of the present application provides an electronic device, comprising: a processor; a memory for storing processor-executable instructions; and the processor is configured to execute the control method of the vehicle according to the first aspect.

[0015] In the mine unmanned driving, when the target object enters the sensing overlap area of the laser radar and the millimeter wave radar, the reliability of target object detection can be ensured, the accuracy and consistency of the sensing result can be improved, and the adaptability and robustness of the autonomous driving system under different environmental conditions can be enhanced through the sensing result of the first target object and the sensing result of the second target object. Then, the target object sensing queue and the first target object tracking queue are fused to generate a more comprehensive and accurate second target object tracking queue. This queue not only contains the latest target sensor speed information, but also integrates historical tracking information, so that the unmanned driving system can more accurately track or avoid the target object, thereby making safer and more effective driving decisions, improving the safety and efficiency of mine autonomous driving, and ensuring the smooth operation of the vehicle in complex environments. BRIEF DESCRIPTION OF DRAWINGS

[0016] The above and other objects, features and advantages of the present application will become more apparent from the following detailed description of embodiments of the present application, taken in conjunction with the accompanying drawings. The drawings provided in the disclosure serve to provide a further understanding of the embodiments of the present application, constitute a part of the specification, and are used to explain the present application together with the embodiments of the present application, but do not constitute a limitation on the present application. In the drawings, the same reference numerals generally represent the same components or steps.

[0017] Figure 1 Fig. 1 shows a flowchart of a control method of a vehicle according to an embodiment of the present application.

[0018] Figure 2 Fig. 2 shows a flowchart of determining target sensor speed information according to an embodiment of the present application.

[0019] Figure 3 Fig. 2 shows a flowchart of determining target sensor speed information according to an embodiment of the present application.

[0020] Figure 4 Fig. 3 shows a flowchart of determining whether the vehicle is turning according to an embodiment of the present application.

[0021] Figure 5 Fig. 4 shows a flowchart of obtaining a target sensing queue according to an embodiment of the present application.

[0022] Figure 6 Fig. 5 shows a structural diagram of a control device of a vehicle according to an embodiment of the present application.

[0023] Figure 7Fig. 1 shows a structural schematic diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0024] The technical solutions in the embodiments of the present application will be clearly and completely described in connection with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the scope of protection of the present application.

[0025] Figure 1 Fig. 2 shows a flowchart of a control method of a vehicle according to an embodiment of the present application. For example, as shown in Fig. 2, the method comprises the following steps. Figure 1

[0026] In step S110, a perception result of a first target object determined based on a laser radar of a target vehicle is obtained.

[0027] For example, the target vehicle is equipped with at least one laser radar, wherein the laser radar is a device for object detection and measurement by using laser technology, and can provide high-precision distance and speed information. During driving of the target vehicle, the laser radar can detect the position, size, timestamp, sensor type and other information of the target object by emitting and receiving laser beams, and the perception result of the first target object is generated after the information is processed by a laser radar perception algorithm. For example, the first target object is a reflector, a temporary obstacle, another vehicle, a pedestrian, etc., the target vehicle is an autonomous vehicle, and the sensor type corresponding to the laser radar is recorded as type=0.

[0028] In step S120, a perception result of a second target object determined based on a millimeter wave radar of the target vehicle is obtained.

[0029] For example, the target vehicle is also equipped with at least one millimeter wave radar, wherein the millimeter wave radar is a device for object detection and measurement by using millimeter wave electromagnetic waves, and can provide effective object detection in adverse weather conditions (such as rain, fog, snow, etc.). During driving of the target vehicle, the millimeter wave radar can detect the position, speed, distance, timestamp, sensor type and other information of the target object by emitting and receiving millimeter wave signals, and the perception result of the second target object is generated after the information is processed by a millimeter wave radar perception algorithm. For example, the sensor type corresponding to the millimeter wave radar is recorded as type=1.

[0030] In step S130, the perception result of the first target object and the perception result of the second target object are fused to obtain a target object perception queue.

[0031] ​Specifically, fusion refers to combining the perception results of the first target object and the perception results of the second target object to form a more accurate and complete overall perception result (i.e., target object perception queue). Specifically, different sensors have their unique advantages and limitations, for example, lidar is very accurate in measuring distance and shape, but its performance will decrease in bad weather conditions; while millimeter wave radar can provide stable detection in bad weather, but it is not as good as lidar in resolution.

[0032] Exemplarily, before fusion, the perception results of the first target object and the perception results of the second target object are first pre-processed, including denoising, filtering and calibration, in order to reduce errors and noise in the original data and improve the accuracy of subsequent processing. Then, the perception results of the first target object and the perception results of the second target object are ensured to be synchronized in time, and the above-mentioned perception results are mapped into the same coordinate system. Then, different perception results are matched in space and time. If the matching is successful, the two kinds of perception results are integrated together, for example, the time stamp, position, speed and other information are combined into a unified data structure. Finally, the fused perception results form a target object perception queue, which contains multiple perception elements, each of which describes the current state of a target object in detail, including the time, position and speed at which it is detected. These information provides comprehensive and consistent environmental perception data for the unmanned system, so that the unmanned system can more accurately understand and predict the surrounding environment, and thus make safer and more effective driving decisions.

[0033] Step S140, based on the target fusion strategy, the target object perception queue is fused with the first target object tracking queue to obtain a second target object tracking queue.

[0034] The first target object tracking queue is a data structure for tracking and managing target object information, which includes multiple first tracking elements. Exemplarily, the first tracking element contains attribute information of the target object, such as type, size, position, etc.; also contains motion state such as speed, acceleration, direction, so as to accurately predict the behavior of the target object; also contains a time stamp for recording the update time of the target object information, so as to perform data analysis. Correspondingly, the second target object tracking queue also includes multiple second tracking elements, and the detailed information of the second tracking element corresponds to the first tracking element.

[0035] In some embodiments, the target fusion strategy includes: for each sensing element, if there is a first tracking element that matches the sensing element, then determining whether the information source in the sensing element includes lidar and millimeter-wave radar; if the information source includes lidar and millimeter-wave radar, then determining the target sensor velocity information based on the velocity information of lidar and millimeter-wave radar, and updating the first tracking element based on the target sensor velocity information to obtain the second tracking element corresponding to the first tracking element.

[0036] For example, during the fusion of the target object perception queue and the first target object tracking queue, each perception element in the target object perception queue is examined, and a matching first tracking element is searched in the first target object tracking queue. For example, the matching of the two sets of information is determined based on information such as timestamps, positions, and velocities. Once a match is found, the source of the information in the perception element is further examined, including determining whether the perception element contains data from both LiDAR and millimeter-wave radar. If the perception element contains data from both sensors, the velocity information from both the LiDAR and millimeter-wave radar is combined to determine the target sensor velocity information.

[0037] Furthermore, based on the obtained target sensor velocity information, the matching first tracking element is updated by replacing the velocity information in the first tracking element with the target sensor velocity information. The updated first tracking element is then transformed into a second tracking element and added to the second target tracking queue, so that the target vehicle movement can be controlled based on the second target tracking queue. Ultimately, the second tracking element not only contains the latest velocity information (i.e., target sensor velocity information), but also includes position, timestamp, and other relevant attributes, thus providing the autonomous driving system with a more comprehensive and accurate view of the target's state.

[0038] In autonomous driving systems in mines, when a target object enters the overlapping area of ​​LiDAR and millimeter-wave radar perception, the reliability of target object detection can be ensured by combining the perception results of the first and second target objects. This improves the accuracy and consistency of the perception results, enhancing the adaptability and robustness of the autonomous driving system under different environmental conditions. Then, fusing the target object perception queue with the first target object tracking queue generates a more comprehensive and accurate second target object tracking queue. This queue not only includes the latest target sensor speed information but also integrates historical tracking information, enabling the autonomous driving system to more accurately track or avoid targets, thereby making safer and more effective driving decisions. This improves the safety and efficiency of autonomous driving in mines and ensures the smooth operation of vehicles in complex environments.

[0039] Combination Figure 1In some embodiments of this application, the target fusion strategy further includes: if the information source only includes lidar, then the speed information of lidar is determined as target sensor information.

[0040] LiDAR features high precision and high resolution. When other sensors are unavailable or the data is unreliable, relying on the speed information from LiDAR can ensure that the autonomous driving system can still perform effective target tracking and speed estimation, thereby improving the safety, reliability and adaptability of the autonomous driving system.

[0041] In some embodiments of this application, the target fusion strategy further includes: if the information source only contains millimeter-wave radar, then using the Kalman series filtering algorithm to filter the results in the target perception queue, updating the filtering results, and adding the filtering results to the first target tracking queue.

[0042] Combination Figure 1 In the embodiments shown, in other embodiments of this application, if there is no first tracking element that matches the sensing element, the sensing element is directly added to the first target tracking queue.

[0043] For example, in a dynamically changing traffic environment, objects may suddenly appear or enter the detection range of sensors, while the existing tracking queue may not yet contain information about these new objects, causing a mismatch between the information in the first tracking element and the information in the sensing element. In this case, directly adding these sensing elements to the first object tracking queue allows the autonomous driving system to track and analyze these objects, thereby quickly updating the target vehicle's perception of the surrounding environment.

[0044] Furthermore, target vehicles encounter various complex situations during operation, such as sudden changes in obstacles or temporary sensor malfunctions. In these cases, a mismatch may occur between the perceived elements and the initial tracking elements. Directly incorporating the perceived elements into the tracking system helps maintain continuous and accurate environmental perception, reducing decision-making errors caused by missing or delayed information. By updating the initial tracking queue in a timely manner, the autonomous driving system can develop more reasonable path planning and obstacle avoidance strategies based on the latest target information, improving driving safety and efficiency.

[0045] Figure 2 The diagram shown is a flowchart illustrating the process of determining target sensor velocity information according to an embodiment of this application. Figure 1 Extending from the illustrated embodiment Figure 2 The illustrated embodiment will be described in detail below. Figure 2 The illustrated embodiments and Figure 1 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0046] like Figure 2As shown, in this embodiment, the target sensor velocity information is determined based on the velocity information of the lidar and the velocity information of the millimeter-wave radar, including the following steps.

[0047] Step S210: Determine whether the speed information from the millimeter-wave radar meets the target conditions and whether the target vehicle is turning.

[0048] For example, the target condition refers to stability or continuity, that is, determining whether the velocity information of the millimeter-wave radar meets the stability condition or the continuity condition.

[0049] Understandably, the stability of speed information is crucial for the prediction and control of autonomous driving systems. Unstable speed information may lead the system to make incorrect decisions, increasing the risk of collisions or affecting driving comfort. Therefore, determining the stability of speed information from millimeter-wave radar is a prerequisite for ensuring the provision of reliable speed data. For example, the consistency, standard deviation, and maximum deviation of speed changes can be used to assess whether the speed information from millimeter-wave radar meets the target conditions.

[0050] In practical applications, if the result of step S210 is that the speed information of the millimeter-wave radar meets the target conditions and the target vehicle does not turn, then step S220 is executed; otherwise, step S230 is executed.

[0051] Step S220: The velocity information of the millimeter-wave radar is determined as the velocity information of the target sensor.

[0052] Specifically, if the speed information from the millimeter-wave radar is stable or continuous, and the target vehicle does not steer (i.e., the vehicle's direction and speed change little), then the speed information from the millimeter-wave radar is identified as the target sensor's speed information. In this case, the speed information from the millimeter-wave radar can provide reliable speed data for the autonomous driving system, supporting autonomous driving decisions.

[0053] Understandably, millimeter-wave radar typically exhibits high stability when providing speed information. Furthermore, when the target vehicle is not turning, its motion is relatively simple, allowing millimeter-wave radar to provide continuous and stable measurement data. Therefore, the speed information from millimeter-wave radar is used as the target sensor's speed information.

[0054] Step S230: The velocity information of the lidar is determined as the velocity information of the target sensor.

[0055] During a turn, the target vehicle's direction and speed change significantly, affecting the measurement accuracy of sensors such as millimeter-wave radar. However, lidar can provide accurate edge contour and distance information, as well as reliable and stable speed data, in dynamically changing environments, thereby improving the responsiveness and overall safety of autonomous driving systems. Therefore, when the speed information from millimeter-wave radar does not meet the target conditions, and / or when the target vehicle is turning, the speed information from lidar is used as the target sensor's speed information.

[0056] In some embodiments, the target sensor velocity information is the optimal sensor velocity information. Specifically, in autonomous driving systems, multiple sensors (such as LiDAR, millimeter-wave radar, cameras, etc.) are used to acquire environmental information around the target vehicle. During the fusion process, the velocity information provided by all sensors is comprehensively considered, and an optimal velocity estimate is calculated using a specific algorithm (such as Kalman filtering, particle filtering, etc.). This optimal velocity estimate is the optimal sensor velocity information, which reflects the actual motion state of the target object while taking into account the measurement errors and uncertainties of each sensor. In addition, the optimal sensor velocity information is not only required to be close to the true value numerically, but also to remain stable over a period of time. This means that even when sensor data fluctuates, the optimal sensor velocity information can still provide a reliable velocity estimate, thus providing accurate input to the autonomous driving system.

[0057] In some embodiments, the first and second object perception results include perception results for obstacles. Specifically, in mining autonomous driving systems, accurately perceiving and processing object information is crucial for ensuring safety and improving efficiency. This solution comprehensively utilizes the advantages of LiDAR and millimeter-wave radar, significantly improving the accuracy, robustness, and response speed of object detection in mining autonomous driving systems, providing strong support for achieving safer and more efficient autonomous driving.

[0058] In this embodiment, the speed information from the millimeter-wave radar is first evaluated to determine if it meets preset target conditions, such as stability and continuity. If these conditions are met, and the target vehicle is not currently turning, the speed information from the millimeter-wave radar is relied upon. However, if the speed information from the millimeter-wave radar does not meet the target conditions, or if the target vehicle is turning, the speed information from the lidar is used instead. LiDAR has advantages in providing high-precision obstacle edge contours and distance information, especially in turning or complex environments, where it can provide more reliable speed estimates. In this way, the target sensor speed information can be dynamically selected based on the dynamic state of the target vehicle and environmental conditions, improving the safety and efficiency of the entire autonomous driving system.

[0059] CombinationFigure 2 In the embodiments shown, and in other embodiments of this application, if the result of step S210 is that the speed information of the millimeter-wave radar does not meet the target conditions, and / or the target vehicle is turning, further steps may be performed. Figure 3 The solution shown in the embodiment.

[0060] Specifically, Figure 3 The diagram shown is a flowchart illustrating the process of determining target sensor velocity information according to an embodiment of this application. Figure 3 As shown, the method includes the following steps.

[0061] Step S310: Determine the location information queue containing the lidar's location information and the third time information queue corresponding to the lidar's velocity information.

[0062] The location information queue is a data structure that stores the location information of targets detected by the LiDAR at continuous time points. Each location information typically includes the target's specific coordinates (e.g., x and y coordinates) in the vehicle coordinate system, reflecting the target's position relative to the vehicle. Corresponding to the location information queue is a third time information queue, which records the exact time the location information was acquired. This queue ensures that the location data is correlated with the actual time of occurrence, thus allowing analysis of the target's dynamic changes at different time points.

[0063] Step S320: Determine whether the number of location information items in the location information queue is greater than the number of third targets, and whether the difference between the two latest time information items in the third time information queue is less than the difference between the fourth targets.

[0064] Specifically, the third target quantity ensures sufficient location data for accurate velocity calculation, and the fourth target difference ensures a sufficiently high frequency of location information acquisition to capture dynamic changes in the target. For example, if the result of step S320 is yes, then step S330 is further executed.

[0065] Step S330: Based on the location information queue and the third time information queue, calculate the target velocity information and determine the target velocity information as the target sensor velocity information.

[0066] For example, based on the location information queue and the third time information queue, a quadratic polynomial p = d × t is fitted using the least squares method. 2 +e×t+g, where p represents the position of the target object, t represents time, and d, e, and g are coefficients that need to be solved.

[0067] The formula for calculating velocity is v = 2d × t + e, where v represents the rate of change of the target object's position per unit time. Furthermore, the calculated velocity v is determined as the target sensor's velocity information.

[0068] In this embodiment, the combination of the location information queue and the third time information queue enables the autonomous driving system to capture the target's position data changing over time, providing crucial information for target speed tracking in dynamic environments. By determining the number of data points in the location information queue and the time difference in the third time information queue, speed estimation errors caused by insufficient data or low collection frequency are effectively avoided. Finally, based on the location information queue and the third time information queue, target speed information is calculated, resulting in more accurate and comprehensive speed estimation. The solution in this embodiment further ensures that the autonomous driving system can obtain accurate, reliable, and real-time speed information in various complex and dynamic driving environments, thereby improving overall safety and efficiency.

[0069] Combination Figure 2 In the embodiments shown, in other embodiments of this application, the target conditions include: (1) the number of velocity information in the velocity information queue where the velocity information of the millimeter-wave radar is located is greater than the number of first targets; (2) the standard deviation between the velocity information in the velocity information queue is less than the difference of the first target; (3) the maximum deviation between the velocity information in the velocity information queue and the mean of the velocity information in the velocity information queue is less than the difference of the second target; (4) the difference between the latest two time information in the first time information queue corresponding to the velocity information of the millimeter-wave radar is less than the difference of the third target.

[0070] Regarding the target condition (1), in detail, the speed information queue stores speed information detected by the millimeter-wave radar at multiple consecutive time points; "the number is greater than the number of the first target" means that there must be a certain number of speed information points in the speed information queue, which exceeds the preset "number of the first target". Through this target condition, it can be ensured that the speed data provided by the millimeter-wave radar is continuous, rather than a few isolated data points, which helps the autonomous driving system to understand the motion state of the obstacle more accurately. In addition, more speed data points can provide more comprehensive information on the speed changes of the target, reduce the influence of random errors, and help the autonomous driving system make more accurate speed estimates and predictions.

[0071] Understandably, in a dynamically changing mining environment, the speed of an object can change rapidly. By collecting a certain amount of speed data, the autonomous driving system can better adapt to these changes and update the speed estimate of the object in a timely manner.

[0072] Furthermore, in some embodiments, the number of speed information points in the speed information queue is less than the number of second targets. By limiting the number of data points in the speed information queue, excessive data processing can be avoided, reducing the computational burden and improving the response speed of autonomous driving, especially in situations requiring rapid obstacle avoidance decisions. Additionally, in dynamic environments, limiting the length of the speed information queue ensures that the latest speed data is used, avoiding decisions based on outdated information.

[0073] Regarding condition (2) in the target conditions, its significance lies in ensuring the stability and reliability of speed measurements. The data in the speed information queue reflects the speed changes of the target object over a period of time. By setting a first target difference, the consistency and fluctuation range of these speed measurements can be evaluated. It is understandable that a smaller standard deviation indicates that the speed measurement values ​​do not change much, that is, the speed information is stable. This helps the autonomous driving system to more accurately predict the motion trend of the target object and make more reliable obstacle avoidance decisions, reducing the risk of misjudgment caused by sensor errors or external interference, thereby achieving safer and more efficient vehicle control in complex and ever-changing autonomous driving scenarios in mines.

[0074] The objective condition (3) aims to ensure the consistency and reliability of target speed measurements in the autonomous driving system. In multi-sensor fusion (two sensors in this application), different sensors may produce speed differences due to their respective measurement errors. By limiting the maximum deviation of speed information, abnormal speed readings caused by random errors or sensor malfunctions can be identified, thereby avoiding the impact of these outliers on the overall speed estimation. Therefore, this objective condition helps reduce fluctuations in speed estimation, improves the stability of speed information, and enables the autonomous driving system to rely on smoother and more reliable speed data when making path planning and obstacle avoidance decisions. In addition, a smaller maximum deviation also means that the speed measurements are more concentrated around the mean, which helps to further optimize the accuracy of speed estimation.

[0075] Regarding condition (4) in the objective, the aim is to ensure the temporal continuity and real-time nature of speed measurement. The first-time information queue records the speed changes of the target object at consecutive time points, which is key data for dynamic tracking and prediction. By limiting the difference between the two most recent time information points to a certain range, the frequency and temporal resolution of speed measurement can be guaranteed, thereby better capturing and responding to the dynamic changes of the target object. In addition, this close temporal continuity also helps to reduce prediction errors that may be introduced due to excessively long time intervals, improving prediction accuracy and reaction speed. Furthermore, it enables the autonomous driving system to process and utilize sensor data more effectively, enhancing its perception of the surrounding environment, thereby achieving safer and more reliable autonomous driving operations in complex and ever-changing driving environments.

[0076] Figure 4 The diagram shown is a flowchart illustrating a process for determining whether a vehicle is turning, according to an embodiment of this application. Figure 2 Extending from the illustrated embodiment Figure 4 The illustrated embodiment will be described in detail below. Figure 4 The illustrated embodiments and Figure 2 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0077] like Figure 4 As shown in this embodiment, the method for determining whether the target vehicle is turning includes the following steps.

[0078] Step S410: Obtain the current orientation queue of the target vehicle and the second time information queue corresponding to the current orientation queue.

[0079] Specifically, the current orientation queue records the orientation information of the target vehicle at consecutive time points. Orientation refers to the angle of the target vehicle's direction of travel; for example, it can be the angle relative to a reference direction. Corresponding to the current orientation queue is the second time information queue, which records the exact time point at which the orientation information was acquired. This queue ensures that the orientation data is correlated with the actual time of occurrence, thus allowing analysis of the dynamic changes of the target vehicle at different time points.

[0080] Step S420: Based on the current orientation queue and the second time information queue, calculate the coefficients of the fitted polynomial using the least squares method.

[0081] For example, the forward orientation queue is: t1: 0 degrees; t2: 5 degrees; t3: 15 degrees; t4: 30 degrees. The second time information queue is: t1: 0 seconds; t2: 1 second; t3: 2 seconds; t4: 4 seconds.

[0082] Based on the above information, firstly, we take the time point as the independent variable (x) and the orientation angle as the dependent variable (y). Next, according to the characteristics of the data and the required fitting accuracy, we choose an appropriate polynomial order. For example, we assume we choose a quadratic polynomial (i.e., one containing x...). 2 item).

[0083] The goal of least squares is to minimize the sum of the squared differences between the predicted and actual values. For example, the quadratic polynomial is y = a × x. 2 In this embodiment, the polynomial +b×x+c is intended to minimize the fitting error between all data points (t1,0), (t2,5), (t3,15), and (t4,30) and the polynomial. Finally, the coefficients a, b, and c are solved through mathematical calculations or statistical software. These coefficients are used to describe the change in the target vehicle's orientation over time.

[0084] Step S430: Calculate the angular velocity of the target vehicle based on the coefficients of the fitted polynomial.

[0085] For example, by differentiating the fitted polynomial, we obtain 2ax + b. Then, we select one or more specific time points x, substitute these time values ​​into the derivative equation, and obtain the corresponding derivative value. This derivative value is the angular velocity at the corresponding time point. For example, we can select the current time point to calculate the current angular velocity, or we can select multiple time points to analyze the trend of angular velocity over time.

[0086] In step S440, if the angular velocity of the target vehicle is less than the angular velocity threshold, it is determined that the target vehicle has not turned.

[0087] Step S450: If the angular velocity of the target vehicle is greater than or equal to the angular velocity threshold, then it is determined that the target vehicle is turning.

[0088] Angular velocity represents the rate of change of the target vehicle's orientation angle per unit time, while the absolute value of the angular velocity indicates the speed of steering. Based on the calculated angular velocity magnitude and a preset angular velocity threshold, it can be determined whether the vehicle is performing a steering operation. For example, with an acceleration threshold of 0.5, if the absolute value of the angular velocity is less than 0.5, the target vehicle is considered not to be making a significant steering; if the absolute value of the angular velocity is greater than or equal to 0.5, the target vehicle is considered to be steering.

[0089] In this embodiment, by acquiring the target vehicle's current orientation queue and corresponding time information queue, orientation data of the target vehicle at continuous time points can be collected. Using this data, the coefficients of a fitting polynomial are calculated using the least squares method. This polynomial describes the pattern of the target vehicle's orientation change over time. Furthermore, based on the coefficients of this fitting polynomial, the angular velocity of the target vehicle, i.e., the change in orientation angle per unit time, is calculated. This provides the autonomous driving system with a quantitative indicator to determine the vehicle's steering state, enabling the autonomous driving system to make timely control decisions, such as adjusting speed, changing path, or issuing warnings, to ensure the safety and stability of the target vehicle under various driving conditions. In addition, this data-driven steering judgment method enhances the predictive ability and adaptability of the autonomous driving system, enabling it to respond more flexibly to the dynamic changes of the target vehicle in complex and ever-changing mining environments, thereby improving the overall intelligence level of the autonomous driving system and the driving experience.

[0090] Figure 5 The diagram shown is a schematic representation of the process for obtaining a target perception queue according to an embodiment of this application. Figure 1 Extending from the illustrated embodiment Figure 5 The illustrated embodiment will be described in detail below. Figure 5 The illustrated embodiments andFigure 1 The differences between the embodiments shown are not repeated here, and the similarities are not repeated here.

[0091] like Figure 5 As shown, in this embodiment, the perception results of the first target object and the perception results of the second target object are fused to obtain the target object perception queue, including the following steps.

[0092] Step S510: Match the perception results of the first target object with the perception results of the second target object.

[0093] The matching process is based on multiple factors, such as timestamps, location coordinates, and speed. For example, an autonomous driving system compares these parameters to determine whether two sensors have detected the same obstacle.

[0094] Step S520: If the matching is successful, a sensing element is created, and the time information and location information of the target object contained in the sensing element are updated based on the sensing result of the first target object.

[0095] For example, once a match is successful, a new sensing element is created. This sensing element will contain the time and location information of the target object, which is updated based on the sensing results of the first target object. In some embodiments, if a match is successful, the lidar velocity information contained in the sensing element is updated using the sensing results of the first target object, and the millimeter-wave radar velocity information contained in the sensing element is updated using the sensing results of the second target object. Furthermore, since the matching is based on data from two sensors, the information sources of the sensing element will include both lidar and millimeter-wave radar, increasing the reliability and comprehensiveness of the data. For example, in this case, type = 2.

[0096] In step S530, if the matching fails, a sensing element is created, and the time information and location information of the target object corresponding to the sensing element are updated based on the sensing result of the first target object or the sensing result of the second target object.

[0097] A failed match means that the detection results from the LiDAR and millimeter-wave radar are not sufficiently consistent to confirm that they are the same target. In this case, separate sensing elements are created for the target detected by the LiDAR and millimeter-wave radar, respectively. These sensing elements will update the target's temporal and positional information based on the detection results from their respective sensors. For example, if the obstacle's location detected by the LiDAR is more accurate, this data will be used to update the positional information of the sensing elements; similarly, if the velocity information provided by the millimeter-wave radar is more reliable, this data will also be used to update the velocity information of the sensing elements. Simultaneously, the information source of these sensing elements will be labeled as a single sensor, i.e., LiDAR or millimeter-wave radar, indicating that the data comes from only one sensor.

[0098] Step S540: Add the sensing element created when the match is successful or unsuccessful to the target object sensing queue.

[0099] Specifically, both successfully matched and unmatched perception elements are processed uniformly and added to the target object perception queue. This queue is a crucial data structure for the autonomous driving system's environmental understanding and decision support, maintaining the latest perception information for all currently detected targets. Furthermore, the perception elements contain the target's time, location, and velocity information, and are tagged with the information source: LiDAR, millimeter-wave radar, or a fusion of both.

[0100] In this embodiment, a matching algorithm compares perception results from different sensors to identify and associate multiple perception data representing the same target object. When a match is successful, the perception result of the first target object is used to update the time and location information of the perception element, ensuring that the perception element contains the latest target object state. Furthermore, by integrating information from LiDAR and millimeter-wave radar, the reliability and comprehensiveness of the data are enhanced, improving the obstacle recognition accuracy of the autonomous driving system. If a match is unsuccessful, a separate perception element is created for each unmatched perception result, updating the time, speed, and location information based on either the LiDAR or millimeter-wave radar perception results. This ensures that even when sensor data fails to match, tracking and monitoring of all detected targets can be maintained, preventing any targets that might affect driving safety from being overlooked. Finally, regardless of whether a match is successful or unmatched, all targets are added to the target object perception queue, ensuring the integrity and real-time nature of the perception queue and providing a comprehensive and continuous environmental model for the autonomous driving system. By maintaining a real-time updated perception queue, the system can better respond to environmental changes and adjust driving strategies in a timely manner, thereby improving the safety and efficiency of the entire autonomous driving system.

[0101] The above text combined Figures 1 to 5 The present application describes in detail the vehicle control method embodiments, which are illustrated below in conjunction with... Figure 6 This application describes in detail the vehicle control device embodiments. It should be understood that the descriptions of the vehicle control method embodiments correspond to the descriptions of the vehicle control device embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0102] Figure 6 The diagram shown is a structural schematic of a vehicle control device according to an embodiment of this application. Figure 6 As shown, the vehicle control device 60 provided in this embodiment includes:

[0103] The first acquisition module 610 is used to acquire the first target object perception result determined by the lidar of the target vehicle;

[0104] The second acquisition module 620 is used to acquire the second target object perception result determined by the millimeter-wave radar of the target vehicle;

[0105] The first fusion module 630 is used to fuse the first target object perception result and the second target object perception result to obtain a target object perception queue, which includes multiple perception elements.

[0106] The second fusion module 640 is used to fuse the target object perception queue and the first target object tracking queue based on the target fusion strategy to obtain the second target object tracking queue, so as to control the movement of the target vehicle based on the second target object tracking queue. The first target object tracking queue includes multiple first tracking elements, and the second target object tracking queue includes multiple second tracking elements.

[0107] The target fusion strategy includes: for each sensing element, if there is a first tracking element that matches the sensing element, then determine whether the information source in the sensing element includes LiDAR and millimeter-wave radar. If the information source includes LiDAR and millimeter-wave radar, then determine the target sensor velocity information based on the velocity information of LiDAR and millimeter-wave radar, and update the first tracking element based on the target sensor velocity information to obtain the second tracking element corresponding to the first tracking element.

[0108] In one embodiment of this application, the second fusion module 640 is further configured to: if the speed information of the millimeter-wave radar meets the target conditions, and the target vehicle is not turning at this moment, then determine the speed information of the millimeter-wave radar as the target sensor speed information; if the speed information of the millimeter-wave radar does not meet the target conditions, and / or the target vehicle is turning at this moment, then determine the speed information of the lidar as the target sensor speed information; preferably, the target vehicle includes an autonomous vehicle; preferably, the target sensor speed information is the optimal sensor speed information; preferably, the first target object perception result and the second target object perception result include the perception result for obstacles.

[0109] In one embodiment of this application, the target conditions include: the number of velocity information items in the velocity information queue where the velocity information of the millimeter-wave radar is located is greater than the number of first targets; the standard deviation between the velocity information items in the velocity information queue is less than the difference between the first targets; the maximum deviation between the velocity information items in the velocity information queue and the mean of the velocity information items in the velocity information queue is less than the difference between the second targets; the difference between the latest two time information items in the first time information queue corresponding to the velocity information of the millimeter-wave radar is less than the difference between the third targets; preferably, the number of velocity information items in the velocity information queue is less than the number of second targets.

[0110] In one embodiment of this application, the second fusion module 640 is further configured to: obtain the current orientation queue of the target vehicle and the second time information queue corresponding to the current orientation queue; calculate the coefficients of the fitting polynomial using the least squares method based on the current orientation queue and the second time information queue; calculate the angular velocity of the target vehicle based on the coefficients of the fitting polynomial; if the angular velocity of the target vehicle is less than the angular velocity threshold, it is determined that the target vehicle has not turned; if the angular velocity of the target vehicle is greater than or equal to the angular velocity threshold, it is determined that the target vehicle is turning.

[0111] In one embodiment of this application, the second fusion module 640 is further configured to: if the speed information of the millimeter-wave radar does not meet the target conditions, and / or the target vehicle is turning at this moment, determine the location information queue where the laser radar's location information is located and the third time information queue corresponding to the laser radar's speed information; if the number of location information in the location information queue is greater than the number of third targets, and the difference between the latest two time information in the third time information queue is less than the difference of the fourth target, calculate the target speed information based on the location information queue and the third time information queue, and determine the target speed information as the target sensor speed information.

[0112] In one embodiment of this application, the target fusion strategy further includes: if the information source only includes lidar, then the speed information of lidar is determined as target sensor information; preferably, if there is no first tracking element that matches the sensing element, then the sensing element is directly added to the first target tracking queue.

[0113] In one embodiment of this application, the first fusion module 630 is further configured to: match the perception results of the first target object and the perception results of the second target object; if the match is successful, create a perception element and update the time information and location information of the target object contained in the perception element based on the perception results of the first target object, wherein the information source of the perception element includes lidar and millimeter-wave radar; if the match is unsuccessful, create a perception element and update the time information and location information of the target object corresponding to the perception element based on the perception results of the first or second target object, wherein the information source of the perception element is lidar or millimeter-wave radar; and add the perception element created when the match is successful or unsuccessful to the target object perception queue.

[0114] Below, for reference Figure 7 This describes an electronic device according to embodiments of the present application. Figure 7 The diagram shown is a structural schematic of an electronic device provided in an exemplary embodiment of this application.

[0115] like Figure 7 As shown, the electronic device 70 includes one or more processors 701 and memory 702.

[0116] The processor 701 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 70 to perform desired functions.

[0117] The memory 702 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 701 may execute the program instructions to implement the vehicle control methods and / or other desired functions of the various embodiments of this application described above. The computer-readable storage medium may also store various contents such as the perception results of a first target, the perception results of a second target, a target perception queue, perception elements, a first tracking element, a second tracking element, etc.

[0118] In one example, the electronic device 70 may also include an input device 703 and an output device 704, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0119] The input device 703 may include, for example, a keyboard, a mouse, etc.

[0120] The output device 704 can output various information to the outside, including the perception results of the first target, the perception results of the second target, the target perception object queue, perception elements, the first tracking element, the second tracking element, etc. The output device 704 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0121] Of course, for the sake of simplicity, Figure 7 Only some of the components of the electronic device 70 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 70 may include any other suitable components depending on the specific application.

[0122] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps in the vehicle control methods according to various embodiments of this application described above.

[0123] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0124] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions thereon, which, when executed by a processor, cause the processor to perform the steps in the vehicle control methods according to various embodiments of this application described above.

[0125] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0126] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0127] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0128] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0129] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0130] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A control method of a vehicle, characterized by, The method comprises: obtaining a first target object perception result determined based on a laser radar of a target vehicle; obtaining a second target object perception result determined based on a millimeter wave radar of the target vehicle; fusing the first target object perception result and the second target object perception result to obtain a target object perception queue, the target object perception queue comprising a plurality of perception elements; fusing the target object perception queue and a first target object tracking queue based on a target fusion strategy to obtain a second target object tracking queue, the first target object tracking queue comprising a plurality of first tracking elements, the second target object tracking queue comprising a plurality of second tracking elements, and the target vehicle being controlled to move based on the second target object tracking queue; wherein the target fusion strategy comprises: for each perception element, if there is a first tracking element matching the perception element, determining whether information sources in the perception element include the laser radar and the millimeter wave radar, if the information sources include the laser radar and the millimeter wave radar, determining target sensor speed information based on speed information of the laser radar and speed information of the millimeter wave radar, and updating the first tracking element based on the target sensor speed information to obtain a second tracking element corresponding to the first tracking element; the target sensor speed information being determined according to whether the speed information of the millimeter wave radar meets a target condition and / or whether the target vehicle is turning, and the target condition representing stability or continuity of the speed information of the millimeter wave radar.

2. The control method of a vehicle according to claim 1, characterized by The determination of the target sensor speed information based on the speed information of the laser radar and the speed information of the millimeter wave radar comprises: if the speed information of the millimeter wave radar meets the target condition and the target vehicle is not turning at this moment, determining the speed information of the millimeter wave radar as the target sensor speed information; if the speed information of the millimeter wave radar does not meet the target condition and / or the target vehicle is turning at this moment, determining the speed information of the laser radar as the target sensor speed information.

3. The control method of a vehicle according to claim 1, characterized by The target vehicle comprises an autonomous vehicle.

4. The control method of a vehicle according to claim 1, characterized by The target sensor speed information is optimal sensor speed information.

5. The control method of a vehicle according to claim 1, characterized by The first target object perception result and the second target object perception result comprise perception results for obstacles.

6. The control method of a vehicle according to claim 1, characterized by The target condition comprises: a number of speed information in a speed information queue in which the speed information of the millimeter wave radar is greater than a first target number; a standard deviation between the speed information in the speed information queue is less than a first target difference value; a maximum deviation of the speed information in the speed information queue from a mean value of speed information of the speed information queue is less than a second target difference value; a difference between the latest two time information in a first time information queue corresponding to the speed information of the millimeter wave radar is less than a third target difference value.

7. The control method of a vehicle according to claim 6, characterized by a number of speed information in the speed information queue is less than a second target number.

8. The control method of a vehicle according to claim 1, characterized by The method for determining whether the target vehicle is turning comprises: obtain a current orientation queue of the target vehicle and a second time information queue corresponding to the current orientation queue; calculate coefficients of a fitting polynomial based on the current orientation queue and the second time information queue by using a least square method; calculate an angular velocity of the target vehicle based on the coefficients of the fitting polynomial; if the angular velocity of the target vehicle is less than an angular velocity threshold, determine that the target vehicle is not turning; if the angular velocity of the target vehicle is greater than or equal to the angular velocity threshold, determine that the target vehicle is turning.

9. The control method of a vehicle according to any one of claims 1 to 8, characterized by, The determining the target sensor velocity information based on the velocity information of the lidar and the velocity information of the millimeter wave radar comprises: if the velocity information of the millimeter wave radar does not satisfy a target condition and / or the target vehicle is turning at the moment, determine a position information queue in which position information of the position information of the lidar is located and a third time information queue corresponding to the velocity information of the lidar; if a number of the position information in the position information queue is greater than a third target number and a difference between the latest two time information in the third time information queue is less than a fourth target difference, calculate target velocity information based on the position information queue and the third time information queue, and determine the target velocity information as the target sensor velocity information.

10. The control method of a vehicle according to any one of claims 1 to 8, characterized by The target fusion strategy further comprises: if the information source only comprises the lidar, determine the velocity information of the lidar as the target sensor velocity information.

11. The control method of a vehicle according to any one of claims 1 to 8, characterized by if there is no first tracking element matching the perception element, directly add the perception element to the first target object tracking queue.

12. The control method of a vehicle according to any one of claims 1 to 8, characterized by The fusing the perception result of the first target object and the perception result of the second target object to obtain a target object perception queue comprises: matching the perception result of the first target object and the perception result of the second target object; if the matching is successful, creating a perception element and updating time information of a target object and position information of the target object contained in the perception element based on the first target object perception result, wherein the information source of the perception element comprises the lidar and the millimeter wave radar; if the matching is unsuccessful, creating a perception element and updating time information of a target object and position information of the target object corresponding to the perception element based on the first target object perception result or the second target object perception result, wherein the information source of the perception element is the lidar or the millimeter wave radar; adding the perception element created when the matching is successful or the matching is unsuccessful to the target object perception queue.

13. A control device of a vehicle characterized by comprising: comprise: a first obtaining module configured to obtain a first target object perception result determined based on a lidar of a target vehicle; a second obtaining module configured to obtain a second target object perception result determined based on a millimeter wave radar of the target vehicle; a first fusion module configured to fuse the first target object perception result and the second target object perception result to obtain a target object perception queue, the target object perception queue comprising a plurality of perception elements; a second fusion module configured to fuse the target object perception queue and a first target object tracking queue based on a target fusion strategy to obtain a second target object tracking queue, so as to control movement of the target vehicle based on the second target object tracking queue, the first target object tracking queue including a plurality of first tracking elements, and the second target object tracking queue including a plurality of second tracking elements; wherein the target fusion strategy includes: for each of the perception elements, if there is a first tracking element matching the perception element, determining whether information sources in the perception element include the lidar and the millimeter wave radar, if the information sources include the lidar and the millimeter wave radar, determining target sensor speed information based on speed information of the lidar and speed information of the millimeter wave radar, and updating the first tracking element based on the target sensor speed information to obtain a second tracking element corresponding to the first tracking element; the target sensor speed information being determined according to whether the speed information of the millimeter wave radar satisfies a target condition and / or whether the target vehicle is turning, the target condition representing stability or continuity of the speed information of the millimeter wave radar.

14. A computer-readable storage medium, characterized in that, The storage medium stores a computer program for executing the control method of the vehicle of any one of claims 1 to 12.

15. An electronic device, comprising: comprising: a processor; a memory for storing instructions executable by the processor; the processor configured to execute the control method of the vehicle of any one of claims 1 to 12.

Images