Unmanned motorcade motion cooperative control method based on regional vision relative positioning

Abstract

The invention discloses an unmanned motorcade motion cooperative control method based on regional vision relative positioning, and belongs to the technical field of intelligent control, and the method comprises the steps: collecting the visual information of the surrounding environment corresponding to any unmanned vehicle in real time, carrying out the regional vision relative positioning, and obtaining the relative position and motion state of any unmanned vehicle in a motorcade; transmitting relative positions and motion states corresponding to all unmanned vehicles in the motorcade to a control module based on a communication sharing mode; generating a cooperative control strategy based on the relative position design, adjusting the cooperative control strategy based on the motion state, and generating an overall motion path of the motorcade; the motion state of any unmanned vehicle is monitored, and a motion instruction of any unmanned vehicle is generated in real time based on the overall motion path and the visual information; and any unmanned vehicle receives the motion instruction based on the communication sharing mode and adjusts the motion state to complete motion cooperative control of the motorcade. According to the invention, the accuracy of unmanned motorcade motion cooperative control can be improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent control technology, and in particular relates to a method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning. Background Art

[0002] In recent years, with the development of computer science and artificial intelligence, unmanned vehicles have been studied more and more widely. Unmanned vehicle fleets based on unmanned vehicles have also been widely studied. Cooperative control is a problem that unmanned vehicles must solve. Unmanned vehicle fleets also face huge challenges in cooperative control, which can be divided into the following aspects: in terms of information cognition, the incompleteness and time-varying nature of vehicle states; in terms of control, the control constraints brought by complex environments and actuator constraints.

[0003] As the core problem that unmanned vehicle fleets need to solve, collaborative control is mainly divided into distributed and centralized. In the distributed multi-vehicle collaborative algorithm, vehicles transmit and exchange information through V2V (Vehicle to Vehicle) communication to complete driving decisions. However, V2V communication often has communication delays and information loss, so the stability and robustness of the distributed algorithm need to be improved. The centralized multi-vehicle collaborative algorithm collects the information of all vehicles to the central processor, completes centralized processing, and then transmits the information to each vehicle. Its stability and robustness are far greater than the distributed one; at the same time, in the centralized collaborative algorithm, multiple vehicles can collaborate to complete perception, decision-making and planning functions, improving the vehicle's adaptability to the environment.

[0004] Therefore, in actual situations, it is necessary to improve the positioning accuracy of the unmanned vehicle itself and accurately complete the motion coordinated control of the unmanned vehicle fleet. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning to solve the problems in the prior art.

[0006] In order to achieve the above-mentioned invention object, the present invention proposes a method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning, comprising: S1: Using a camera device to collect visual information of the surrounding environment corresponding to any unmanned vehicle in real time, and combining the on-board sensor data to perform regional visual relative positioning, and obtain the relative position and movement state of any of the unmanned vehicles in the fleet; S2: Setting a communication sharing mode, and transmitting the relative positions and the motion states corresponding to all the unmanned vehicles in the fleet to a control module based on the communication sharing mode; S3: the control module generates a coordinated control strategy based on the relative position design, adjusts the coordinated control strategy based on the motion state, and generates an overall motion path of the fleet; S4: monitoring the motion state of any of the unmanned vehicles, and generating a motion instruction for any of the unmanned vehicles in real time based on the overall motion path and the visual information; S5: Any of the unmanned vehicles receives the motion instruction based on the communication sharing mode, and adjusts the motion state based on the motion instruction to complete the motion coordinated control of the fleet.

[0007] Furthermore, the obtaining of the relative position and motion state of any unmanned vehicle in the vehicle fleet comprises the following steps: Extracting regional features based on the visual information and matching them with the regional map to obtain target features of the preceding vehicle, performing regional visual relative positioning based on the target features, and generating the relative position based on the regional map and the regional visual relative positioning; The driving speed and the driving angle are acquired based on the vehicle-mounted sensor data, and the driving speed and the driving angle are set as the motion state.

[0008] Furthermore, generating the overall motion path of the fleet includes the following steps: The target feature of the preceding vehicle is updated, the regional feature matching the regional map is updated, the updated target feature and the regional feature are marked based on the relative position, an arrangement order of all the unmanned vehicles in the fleet is generated, the motion states corresponding to all the unmanned vehicles are combined based on the arrangement order, and the overall motion path is generated.

[0009] Furthermore, the dynamically adjusting the motion instructions of any one of the unmanned vehicles based on the overall motion path and the visual information comprises the following steps: The relative position and the motion state are collected based on a preset time interval, and a position change sequence and a motion change sequence are generated respectively; a prediction model is constructed based on a neural network, and both the position change sequence and the motion change sequence are input into the prediction model, and the prediction model outputs a predicted position and a predicted speed corresponding to any unmanned vehicle within a prediction time period based on the change amount corresponding to the preset time interval; An estimated trajectory is generated based on the predicted position and the predicted speed, the control module obtains the estimated trajectories corresponding to all the unmanned vehicles, obtains the overlap between the estimated trajectory and the collaborative control strategy based on the arrangement order, adjusts the estimated trajectory of any one of the unmanned vehicles based on the overlap and the overall motion path, generates a standard trajectory, generates an adjustment instruction based on the standard trajectory, and sets the adjustment instruction as the adjusted motion instruction.

[0010] Further, the updating of the target feature of the preceding vehicle comprises the following steps: Acquire basic information of the preceding vehicle based on the target feature, and determine a relative distance, a relative angle, and a relative speed between the preceding vehicle and the unmanned vehicle; Detect target feature points in the target features using the LK optical flow method, match the target feature points after extracting features from the area map using the FAST algorithm, and use the successfully matched map feature points to calculate the position of the unmanned vehicle; A database is constructed, the database is updated using the map feature points, and the updated database is sent to the control module.

[0011] Furthermore, the LK optical flow method matches the unmanned vehicle with the area map corresponding to the front vehicle to generate a matching map. If the matching map exists, the RANSAC algorithm is used to output the matching effect of the matching map. If the matching effect is greater than a first threshold, it is determined to be a map matching feature point, otherwise, it is determined to be a non-matching feature point; if the matching map does not exist, the LK optical flow method is used to extract feature points from the area map of the unmanned vehicle and determine them as the map matching feature points; the map matching feature points are set as the map feature points.

[0012] Furthermore, completing the motion coordination control of the vehicle fleet includes: Calculate the actual position of the vehicle, the position of the preceding vehicle and the travel length of the vehicle in real time, subtract the travel length of the vehicle from the position of the preceding vehicle to obtain the real-time speed of the vehicle, estimate the speed and heading angle of the unmanned vehicle according to the real-time speed of the vehicle, and generate new feature points; The new feature point is sent to the control module, and this step is repeated until the convoy reaches the destination.

[0013] Further, the setting of the communication sharing mode includes: Setting a communication frequency and an information tag, designing a communication technology based on the number of the fleet, establishing a communication topology based on the communication frequency and the communication technology, and transmitting data information corresponding to the information tag based on the communication topology; The transmission performance of the data information is obtained, the communication topology map is optimized and adjusted based on the transmission performance, and the adjusted communication topology map is set as the communication sharing mode.

[0014] Compared with the prior art, the beneficial effects of the present invention are at least as follows: The present invention first obtains the relative position and motion state of the unmanned vehicles, which can quickly generate the overall motion path of the fleet. Then, the motion state of the unmanned vehicles is monitored by a prediction model, which can accurately generate motion instructions in real time. Finally, the motion state of the corresponding unmanned vehicles is adjusted by the motion instructions, which can intelligently complete the motion coordination control of the fleet.

[0015] The present invention also calculates the position change between feature points through regional visual relative positioning, and can accurately calculate the relative position of the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a flow chart of the steps of a method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning according to the present invention; Figure 2 It is a schematic diagram of the communication sharing mode in the present invention. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0018] It is understood that the terms "first", "second", etc. used in this application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish a first element from another element. For example, without departing from the scope of this application, a first xx script may be referred to as a second xx script, and similarly, a second xx script may be referred to as a first xx script.

[0019] like Figure 1 As shown, a method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning includes: S1: Use camera equipment to collect visual information of the surrounding environment corresponding to any unmanned vehicle in real time, and combine it with the on-board sensor data to perform regional visual relative positioning to obtain the relative position and movement status of any unmanned vehicle in the fleet.

[0020] Specifically, when unmanned vehicles move in a coordinated manner in a convoy, it is necessary to analyze the images of the front, back, left, and right directions of the unmanned vehicles, that is, the surrounding environment. In this embodiment, visual information includes but is not limited to video sets or image sets taken by camera equipment, and on-board sensor data includes but is not limited to data collected and generated by speed sensors, direction angle sensors, and positioning sensors. Regional visual relative positioning is a technical means of using visual information to determine the relative position of an object in space. It mainly relies on cameras and other visual sensors to capture image data, extract feature information from it, and then calculate the relative position and posture between objects. Relative position refers to the current spatial position of the unmanned vehicle in the convoy, and the motion state includes but is not limited to state data such as driving speed and steering wheel angle.

[0021] S2: Setting a communication sharing mode, and transmitting the relative positions and motion states of all unmanned vehicles in the fleet to the control module based on the communication sharing mode.

[0022] Specifically, in this embodiment, the control module refers to the remote control terminal, and the communication sharing mode refers to the way in which data is communicated and transmitted, such as Figure 2 As shown, there is a communication connection between any two unmanned vehicles, and all communication connection lines constitute a communication sharing mode H1.

[0023] S3: The control module generates a collaborative control strategy based on the relative position design, adjusts the collaborative control strategy based on the motion state, and generates the overall motion path of the fleet.

[0024] Specifically, in this embodiment, the collaborative control strategy refers to the planning method for the movement coordination of the fleet, such as movement formation and movement following. The purpose of adjusting the collaborative control strategy is to intelligently modify the collaborative control strategy according to the movement status of all unmanned vehicles to avoid a single collaborative control strategy affecting the coordinated movement of the fleet. The overall movement path refers to the route generated by the collaborative control strategy after the path planning of all unmanned vehicles.

[0025] S4: Monitor the motion state of any unmanned vehicle, and generate motion instructions for any unmanned vehicle in real time based on the overall motion path and visual information.

[0026] Specifically, in this embodiment, motion instructions refer to instruction information used to control the movement mode of the unmanned vehicle. The visual information collected in real time is changing, so the position of the unmanned vehicle can be located based on the visual information, and the motion instructions can be generated in a timely manner by comparing the overall motion path.

[0027] S5: Any unmanned vehicle receives a motion command based on the communication sharing mode, and adjusts the motion state based on the motion command to complete the motion coordinated control of the fleet.

[0028] Specifically, in this embodiment, the communication sharing mode can quickly and accurately receive the motion command, avoiding communication interference and the motion command failing to be accurately transmitted to the corresponding unmanned vehicle. Each unmanned vehicle controls the data information corresponding to the motion state by the motion command, so that all unmanned vehicles in the fleet complete the motion cooperative control operation.

[0029] As a preferred technical solution of the present invention, obtaining the relative position and motion state of any unmanned vehicle in the fleet includes the following steps: Regional features are extracted based on visual information and matched with the regional map to obtain the target features of the preceding vehicle. Regional visual relative positioning is performed based on the target features, and the relative position is generated based on the regional map and the regional visual relative positioning.

[0030] The driving speed and the driving angle are obtained based on the vehicle-mounted sensor data, and the driving speed and the driving angle are set as a motion state.

[0031] Specifically, in the present invention, the regional feature refers to the image data captured at the current moment in the visual information, the regional map refers to the spatial image data corresponding to the location of the unmanned vehicle at the current moment, the front vehicle refers to the unmanned vehicle located in front of the current unmanned vehicle, and there may be no target feature of the front vehicle. The target feature refers to the image data belonging to the unmanned vehicle.

[0032] The driving angle refers to the wheel angle controlled by the steering wheel, and the data corresponding to the driving speed and the driving angle are set as data corresponding to the motion state.

[0033] As a preferred technical solution of the present invention, generating the overall motion path of the fleet includes the following steps: The target features of the preceding vehicle are updated, and the regional features of the matching regional map are updated. The updated target features and regional features are arranged based on the regional map to generate an arrangement order for all unmanned vehicles in the fleet. Based on the arrangement order, the corresponding motion states of all unmanned vehicles are combined to generate an overall motion path.

[0034] Specifically, in this embodiment, since all unmanned vehicles in the fleet are moving in real time, it is necessary to update the target features and regional features. The relative positions of the regional features and target features in the regional map can be marked using the technical method corresponding to the regional visual relative positioning. The marked regional features and target features can be sorted by feature point matching, and the arrangement order of all unmanned vehicles can be obtained, where the arrangement order refers to the spatial position distribution of each unmanned vehicle in the fleet. The overall movement path of the fleet can be obtained in real time based on the arrangement order and movement status.

[0035] As a preferred technical solution of the present invention, dynamically adjusting the motion instructions of any unmanned vehicle based on the overall motion path and visual information includes the following steps: Collect relative positions and motion states based on preset time intervals, generate position change sequences and motion change sequences respectively, build a prediction model based on a neural network, input both the position change sequence and the motion change sequence into the prediction model, and the prediction model outputs the predicted position and predicted speed corresponding to any unmanned vehicle within the prediction time based on the change amount corresponding to the preset time interval; An estimated trajectory is generated based on the predicted position and the predicted speed. The control module obtains the estimated trajectories corresponding to all unmanned vehicles, obtains the overlap between the estimated trajectory and the collaborative control strategy based on the arrangement order, adjusts the estimated trajectory of any unmanned vehicle based on the overlap and the overall motion path, generates a standard trajectory, generates an adjustment instruction based on the standard trajectory, and sets the adjustment instruction as the adjusted motion instruction.

[0036] Specifically, in this embodiment, in order to realize the intelligent and timely coordinated control of the fleet movement, a prediction model can be used to predict and analyze the historical movement data of the unmanned vehicle, wherein the position change sequence and the movement change sequence are both historical movement data, and the prediction model can be constructed using an LSTM (Long Short-Term Memory) neural network.

[0037] The degree of deviation between the estimated trajectory of the unmanned vehicle and the path mode set in the cooperative control strategy can be compared by the overlap, where the overlap can be calculated by the Euclidean distance.

[0038] As a preferred technical solution of the present invention, updating the target feature of the preceding vehicle includes the following steps: Based on the target features, the basic information of the leading vehicle is obtained to determine the relative distance, relative angle and relative speed of the leading vehicle relative to the unmanned vehicle.

[0039] The LK optical flow method is used to detect target feature points in the target features, and the FAST algorithm is used to extract features from the regional map and then match the target feature points. The successfully matched map feature points are used to calculate the position of the unmanned vehicle.

[0040] Build a database, update the database using map feature points, and send the updated database to the control module.

[0041] Specifically, in this embodiment, the basic information refers to information composed of the speed change and position change of the target feature of the preceding vehicle, and the relative distance, relative angle and relative speed all refer to the correlation between the current unmanned vehicle and the preceding vehicle. The technical method corresponding to the regional visual relative positioning can be used to calculate and generate the information through the target feature and the time interval.

[0042] LK optical flow (Lucas-Kanade) is a classic computer vision technique that can be used to estimate the motion information of pixels in an image sequence. Target feature points refer to feature points corresponding to the motion information generated by detecting all feature points contained in the target features. FAST (Features from Accelerated Segment Test) is a corner detection algorithm that can be used to extract feature points from an image. Map feature points refer to feature points in a regional map that match target feature points.

[0043] The database refers to the database composed of all map feature points. Since the fleet is moving, the map feature points will update the database in real time.

[0044] As a preferred technical solution of the present invention, the LK optical flow method matches the area map corresponding to the unmanned vehicle and the preceding vehicle to generate a matching map. If a matching map exists, the RANSAC algorithm is used to output the matching effect of the matching map. If the matching effect is greater than a first threshold, it is determined as a map matching feature point, otherwise, it is determined as a non-matching feature point. If a matching map does not exist, the LK optical flow method is used to extract feature points from the area map of the unmanned vehicle and determine them as map matching feature points. The map matching feature points are set as map feature points.

[0045] Specifically, in this embodiment, the RANSAC (RANdom Sample Consensus) algorithm is an iterative method for estimating the parameters of a mathematical model from a set of data containing outliers, which can effectively remove outliers from matching point pairs and estimate a reliable geometric transformation model, which is very important for the positioning and map matching of unmanned vehicles. The matching effect can be set according to the matching accuracy. If the matching effect is greater than the first threshold, the feature point on the matching map is set as the map matching feature point.

[0046] As a preferred technical solution of the present invention, completing the motion coordination control of the fleet includes: Calculate the actual position of the vehicle, the position of the vehicle in front, and the travel length of the vehicle in real time, subtract the travel length of the vehicle from the position of the vehicle in front to get the real-time speed of the vehicle, estimate the speed and heading angle of the unmanned vehicle based on the real-time speed of the vehicle, and generate new feature points; The new feature points are sent to the control module and this step is repeated until the convoy reaches its destination.

[0047] Specifically, in this embodiment, after receiving the movement instruction, the unmanned vehicle will still monitor the actual position of the unmanned vehicle and the position of the vehicle in front. The travel length of the vehicle refers to the length of the vehicle. The position of the vehicle in front will change in real time. The real-time speed of the vehicle can be calculated based on the difference between the real-time change value of the position of the vehicle in front and the travel length of the vehicle, as well as the time interval. The speed estimate and heading angle estimate of the unmanned vehicle can be estimated from the changing orientation of the feature point, and the feature point after real-time change is set as a new feature point and transmitted to the database of the control module until the movement of the fleet ends.

[0048] As a preferred technical solution of the present invention, setting the communication sharing mode includes: Set the communication frequency and information tag, design the communication technology based on the number of fleets, establish a communication topology based on the communication frequency and communication technology, and transmit the data information corresponding to the information tag based on the communication topology; The transmission performance of the data information is obtained, the communication topology is optimized and adjusted based on the transmission performance, and the adjusted communication topology is set as a communication sharing mode.

[0049] Specifically, the communication frequency refers to the transmission frequency, the information tag refers to the tag information corresponding to the type of data to be transmitted, and the communication technology is designed as V2X (Vehicle-to-Everything) communication technology, which can directly exchange status information and control information. The communication topology diagram is a graphical representation of the communication connection method between unmanned vehicles, including but not limited to star topology, mesh topology, etc.

[0050] If the transmission performance is less than the preset value, the communication topology diagram is modified to generate a new communication sharing mode.

[0051] It should be understood that, although each step in the flow chart of each embodiment of the present invention is shown in sequence according to the indication of the arrow, these steps are not necessarily performed in sequence according to the order indicated by the arrow. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be performed in other orders. Moreover, at least a portion of the steps in each embodiment may include a plurality of sub-steps or a plurality of stages, and these sub-steps or stages are not necessarily performed at the same time, but can be performed at different times, and the execution order of these sub-steps or stages is not necessarily performed in sequence, but can be performed in turn or alternately with at least a portion of other steps or sub-steps or stages of other steps.

[0052] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0053] The technical features of the above-mentioned embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0054] The above embodiments only express several implementation methods of the present invention, and the description is relatively specific and detailed, but it cannot be understood as limiting the scope of the present invention. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention.

[0055] The above are only preferred embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for coordinated motion control of an unmanned vehicle fleet based on regional visual relative positioning, characterized in that: The method comprises the following steps: S1: Using a camera device to collect visual information of the surrounding environment corresponding to any unmanned vehicle in real time, and combining the on-board sensor data to perform regional visual relative positioning, and obtain the relative position and movement state of any of the unmanned vehicles in the fleet; S2: Setting a communication sharing mode, and transmitting the relative positions and the motion states corresponding to all the unmanned vehicles in the fleet to a control module based on the communication sharing mode; S3: the control module generates a coordinated control strategy based on the relative position design, adjusts the coordinated control strategy based on the motion state, and generates an overall motion path of the fleet; S4: monitoring the motion state of any of the unmanned vehicles, and generating a motion instruction for any of the unmanned vehicles in real time based on the overall motion path and the visual information; S5: Any of the unmanned vehicles receives the motion instruction based on the communication sharing mode, and adjusts the motion state based on the motion instruction to complete the motion coordinated control of the fleet.

2. The method according to claim 1, characterized in that The obtaining of the relative position and motion state of any unmanned vehicle in the vehicle fleet comprises the following steps: Extracting regional features based on the visual information and matching them with the regional map to obtain target features of the preceding vehicle, performing regional visual relative positioning based on the target features, and generating the relative position based on the regional map and the regional visual relative positioning; The driving speed and the driving angle are acquired based on the vehicle-mounted sensor data, and the driving speed and the driving angle are set as the motion state.

3. The method according to claim 2, characterized in that Generating the overall motion path of the fleet comprises the following steps: The target feature of the preceding vehicle is updated, the regional feature matching the regional map is updated, the updated target feature and the regional feature are marked based on the relative position, an arrangement order of all the unmanned vehicles in the fleet is generated, the motion states corresponding to all the unmanned vehicles are combined based on the arrangement order, and the overall motion path is generated.

4. The method according to claim 3, characterized in that The dynamically adjusting the motion instructions of any one of the unmanned vehicles based on the overall motion path and the visual information comprises the following steps: The relative position and the motion state are collected based on a preset time interval, and a position change sequence and a motion change sequence are generated respectively; a prediction model is constructed based on a neural network, and both the position change sequence and the motion change sequence are input into the prediction model, and the prediction model outputs a predicted position and a predicted speed corresponding to any unmanned vehicle within a prediction time period based on the change amount corresponding to the preset time interval; An estimated trajectory is generated based on the predicted position and the predicted speed, the control module obtains the estimated trajectories corresponding to all the unmanned vehicles, obtains the overlap between the estimated trajectory and the collaborative control strategy based on the arrangement order, adjusts the estimated trajectory of any one of the unmanned vehicles based on the overlap and the overall motion path, generates a standard trajectory, generates an adjustment instruction based on the standard trajectory, and sets the adjustment instruction as the adjusted motion instruction.

5. The method according to claim 3, characterized in that: The updating of the target feature of the preceding vehicle comprises the following steps: Acquire basic information of the preceding vehicle based on the target feature, and determine a relative distance, a relative angle, and a relative speed between the preceding vehicle and the unmanned vehicle; Detecting target feature points in the target features using the LK optical flow method, matching the target feature points after extracting features from the regional map using the FAST algorithm, and using the successfully matched map feature points to calculate the relative position of the unmanned vehicle; A database is constructed, the database is updated using the map feature points, and the updated database is sent to the control module.

6. The method according to claim 5, characterized in that The LK optical flow method matches the unmanned vehicle with the area map corresponding to the preceding vehicle to generate a matching map. If the matching map exists, the RANSAC algorithm is used to output the matching effect of the matching map. If the matching effect is greater than a first threshold, it is determined as a map matching feature point, otherwise, it is determined as a non-matching feature point. If the matching map does not exist, the LK optical flow method is used to extract feature points from the area map of the unmanned vehicle and determine them as the map matching feature points. The map matching feature point is set as the map feature point.

7. The method according to claim 1, characterized in that The completing the motion coordination control of the fleet includes: Calculate the actual position of the vehicle, the position of the preceding vehicle and the travel length of the vehicle in real time, subtract the travel length of the vehicle from the position of the preceding vehicle to obtain the real-time speed of the vehicle, estimate the speed and heading angle of the unmanned vehicle according to the real-time speed of the vehicle, and generate new feature points; The new feature point is sent to the control module, and this step is repeated until the convoy reaches the destination.

8. The method according to claim 1, characterized in that The communication sharing mode setting includes: Setting a communication frequency and an information tag, designing a communication technology based on the number of the fleet, establishing a communication topology based on the communication frequency and the communication technology, and transmitting data information corresponding to the information tag based on the communication topology; The transmission performance of the data information is obtained, the communication topology map is optimized and adjusted based on the transmission performance, and the adjusted communication topology map is set as the communication sharing mode.

Images