Vehicle-road cooperative unmanned vehicle regulation and control system in roadway

Abstract

The invention relates to the technical field of unmanned driving, in particular to a vehicle-road cooperative unmanned vehicle regulation and control system in a roadway. Comprising a roadside data acquisition unit, a roadside calculation unit, a vehicle end control unit and a cloud management unit, the vehicle-road cooperation system is applied to the environment in the roadway, most of data acquisition and calculation are completed through the roadside data acquisition unit and the roadside calculation unit, the load of the vehicle end control unit is reduced, and the communication efficiency between the unmanned vehicle and the roadside equipment is improved; according to the invention, environmental data acquisition in the roadway and data acquisition of the unmanned vehicle are processed respectively, obstacles in the roadway and possible environmental dangers are evaluated through the roadside data acquisition unit and the roadside calculation unit, and data supplementation is carried out through the vehicle end control unit, so that safe operation of the unmanned vehicle is ensured; and the cloud management unit evaluates the roadway section Bi where the unmanned vehicle is located, and then determines whether to re-plan the route.

Description

Technical Field

[0001] The present invention relates to the field of unmanned driving technology, and in particular to a vehicle-road cooperative unmanned vehicle control system in a lane. Background Art

[0002] As unmanned driving technology continues to mature, it will be used in more and more scenarios, especially in some scenarios that are dangerous and do not particularly require human control of the vehicle. Therefore, the use of unmanned vehicles in mine tunnels has become a trend; there are still many difficulties in applying unmanned vehicle driving technology in mine tunnels. Compared with open roads, the signal transmission in mine tunnels is poor, and the weak light and high dust in mine tunnels also affect the control of unmanned vehicles; therefore, the control of unmanned vehicles is now mostly coordinated with the vehicle-road cooperative system to more accurately control the unmanned vehicles, so that they can avoid obstacles and travel along reasonable routes.

[0003] However, in the existing technology, vehicle-road collaboration mostly deals with the relationship between vehicles and vehicles, vehicles and traffic signal equipment, and vehicles and pedestrians on the ground; while the space in the mine tunnel is relatively small, and various pipes and other necessary equipment will be installed on the inner wall of the tunnel. Therefore, the environment in the tunnel is relatively simple, and the interactive scenes in the vehicle-road collaboration system are less than the scenes on the ground. However, the environment in the tunnel is related to the driving safety of unmanned vehicles, and when controlling unmanned vehicles, it is necessary not only to avoid collisions between unmanned vehicles and obstacles, but also to consider changes in the environment in the tunnel, such as falling gravel, damage and detachment of equipment, accumulation of water, accumulation of debris, etc., which may affect the control of unmanned vehicles.

[0004] In view of the above technical defects, a solution is now proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a vehicle-road cooperative unmanned vehicle control system in a lane to solve the technical defects mentioned above. The present invention applies a vehicle-road cooperative system to the lane environment, and completes most of the data collection and calculation through the roadside data collection unit and the roadside calculation unit, reducing the load of the vehicle-side control unit and improving the communication efficiency between the unmanned vehicle and the roadside equipment; the present invention processes the lane environment data collection and the unmanned vehicle data collection separately, evaluates the obstacles in the lane and the possible environmental hazards through the roadside data collection unit and the roadside calculation unit, and supplements the data through the vehicle-side control unit to ensure the safe operation of the unmanned vehicle; through the roadside warning evaluation value GL and the risk assessment parameter Rs, the cloud management unit evaluates the lane section Bi where the unmanned vehicle is located, and then determines whether to re-plan the route.

[0006] The purpose of the present invention can be achieved through the following technical solutions: A vehicle-road cooperative unmanned vehicle control system in a lane: It includes the roadside, vehicle and cloud ends; the roadside includes the roadside data collection unit and the roadside computing unit; the vehicle includes the vehicle control unit; the cloud includes the cloud management unit; the roadside interacts with the cloud end through a wireless communication network, and the roadside interacts with the vehicle end through V2X.

[0007] Roadside data collection unit, used to collect environmental perception data inside mine tunnels.

[0008] The roadside data collection unit includes a wireless communication network and a roadside environment perception system; the wireless communication network of the roadside data collection unit includes a 4G / 5G network and a WiFi network.

[0009] The roadside environment perception system includes lidar, mining cameras, temperature and humidity sensors, infrared sensors, and UWB base stations; when the infrared sensor collects heat source data, the lidar does not collect data.

[0010] It also includes a roadside computing unit for receiving and storing environmental perception data inside the mine tunnel, and calculating roadside point cloud data, and calculating the roadside warning evaluation value GL within the set time frequency. If the warning evaluation value GL exceeds the threshold GB, a roadside warning signal is generated, and the roadside warning signal is sent to the vehicle-end control unit through the roadside V2X unit, and the roadside warning evaluation value GL is sent to the cloud management unit through the wireless communication network.

[0011] The vehicle-side control unit is used to collect road perception data on the mine tunnel route; the vehicle-side control unit includes a vehicle-side perception system, an on-board V2X unit, an on-board computing host, a wireless communication network, a UWB positioning unit, an inertial measurement unit, and a speed sensor unit; the vehicle-side perception system includes an on-board lidar and an on-board camera, which are used to collect road perception data on the mine tunnel route; the wireless communication network of the vehicle-side control unit includes a 4G / 5G network and a WiFi network.

[0012] The vehicle-side control unit evaluates whether there is abnormal data Zi. If there is abnormal data Zi, it generates a vehicle-side warning signal and sends the vehicle-side warning signal and abnormal data Zi to the roadside computing unit through the on-board V2X unit. The roadside computing unit controls the roadside environmental perception system through the wireless communication network to collect environmental perception data inside the mine tunnel, and combines the perception data with the abnormal data Zi for data fusion. The risk assessment parameter Rs is calculated by the roadside computing unit and sent to the cloud management unit through the wireless communication network. The cloud management unit determines whether the unmanned vehicle should re-plan its route based on the risk assessment parameter Rs.

[0013] The cloud management unit is used to store and analyze data and control unmanned vehicles; the roadside computing unit regularly sends its stored data to the cloud management unit via the wireless communication network; The cloud management unit plans the unmanned vehicle route based on the stored historical data, generates route instructions, and sends the route instructions to the roadside computing unit via the wireless communication network. The roadside computing unit sends the instructions to the vehicle-side control unit via the roadside V2X unit, and the vehicle-side control unit controls the operation of the unmanned vehicle; the historical data includes but is not limited to the environmental perception data inside the mine tunnel, roadside point cloud data, abnormal data Zi, roadside warning assessment value GL, and risk assessment parameter Rs.

[0014] Furthermore, in order to better manage the environmental data in the mine tunnels, the tunnels are segmented, and intervals are set for the tunnels and numbered. The data in each tunnel section is collected and stored separately. On the one hand, when a problem occurs in a certain tunnel section, an early warning and updated data can be generated only for that end of the tunnel, avoiding data processing of the entire tunnel; on the other hand, the environment of different sections in the tunnel is different, and segmented data collection is more conducive to reflecting the true situation of the environment in the mine tunnel; the cloud management unit divides the tunnel map data into several tunnel intervals Bi, i=1~n, n is a positive integer; each tunnel interval Bi is respectively equipped with a roadside data collection unit and a roadside calculation unit; the coordinate interval of the tunnel interval Bi is located by multiple groups of UWB base stations installed in the mine tunnel; Among them, the roadside data collection unit is connected to the roadside computing unit through a wireless communication network; the roadside computing unit is connected to the cloud management unit through a wireless communication network.

[0015] In order to evaluate the condition of the inner wall of the roadway and its ancillary equipment, roadside point cloud data is calculated. The calculation of roadside point cloud data can reflect the environmental conditions in the roadway. When some point cloud data in the roadside point cloud data exceeds the preset range, it may be due to fallen rocks, accumulated objects, equipment damage, etc. in the roadway, which in turn affects the passage of unmanned vehicles. The roadside data collection unit and the roadside calculation unit can avoid risks in advance, while minimizing repeated data collection and repeated calculations between the roadside data collection unit and the vehicle-side control unit. The specific steps include: S11. Raw point cloud data acquisition: Several laser radars are installed in each lane section Bi, so that the laser radar scanning range can cover the road, inner wall, and inner wall accessories of the lane section Bi. After the laser radar scans, raw point cloud data is obtained. The raw point cloud data contains the three-dimensional coordinates and timestamp of each point. S12. Perform data preprocessing: Calculate the neighborhood distance mean of each point, remove points exceeding a preset threshold, and then divide the remaining point cloud data into three-dimensional grids. Each three-dimensional grid is represented by a representative point, which is the centroid of the three-dimensional grid. Then, transform the coordinates of the representative points to obtain preprocessed point cloud data. S13, registering the pre-processed point cloud data: aligning the pre-processed point cloud data of different frames using the RANSAC algorithm to obtain coarse point cloud data; S14, registering the coarse point cloud data: accurately aligning the coarse point cloud data using the ICP algorithm to obtain point cloud data; S15. Feature extraction: Calculate the normal vector of the point cloud surface by a normal estimation method to obtain the simulated geometric structure of the road in the lane section Bi and the simulated geometric structure of the inner wall and the inner wall accessories of the lane section Bi; S16. Data storage: The formed point cloud data is stored in the roadside computing unit. The roadside computing unit packages the point cloud data together with the identification data of the lane section Bi where the roadside computing unit is located, and sends the packaged point cloud data to the cloud management unit via the wireless communication network; the identification data of the lane section Bi is the coordinate interval of the lane section Bi.

[0016] To determine whether there are obstacles or obstacle risks in the roadway environment, the roadside warning assessment value GL is calculated using point cloud data. The specific steps include: S21. Calculating point cloud anomaly data: The roadside computing unit acquires point cloud data, extracts point cloud data of the road area, records it as road point cloud data, sets a filtering condition K, counts road point cloud data that meets the condition, and obtains first anomaly data M; the roadside computing unit extracts point cloud data of the inner wall and inner wall accessories, records it as inner wall point cloud data, sets a filtering condition L, counts inner wall point cloud data that meets the condition, and obtains second anomaly data N; S22, calculation parameters :Calculate the ratio of the first abnormal data M to the set threshold m, calculate the ratio of the second abnormal data N to the set threshold n, and calculate the parameter ; S23, calculation parameters :The roadside calculation unit records the number of roadside warning signals generated in the lane section where it is located, P, and calculates the parameters ,in is the historical data weight coefficient; S24, calculation parameters :The roadside calculation unit obtains the temperature data T and humidity data H collected by the roadside data collection unit and calculates ,in Indicates the historical minimum temperature in the lane interval Bi, Indicates the historical maximum temperature in the lane interval Bi, Indicates the historical minimum humidity value within the lane interval Bi, Indicates the historical maximum humidity in the lane interval Bi, is the temperature data weight coefficient, is the humidity data weight coefficient; S25. Calculate the roadside warning evaluation value GL: If the warning evaluation value GL is greater than or equal to the threshold GB, a roadside warning signal is generated, otherwise no roadside warning signal is generated.

[0017] Furthermore, when a roadside warning signal is generated, the roadside computing unit sends the roadside warning signal to the vehicle-side control unit through the roadside V2X unit. If the vehicle-side control unit receives the roadside warning signal, the vehicle-side control unit controls the unmanned vehicle not to enter the corresponding lane section Bi. The cloud-side management unit records the roadside warning signal of the lane section Bi, and eliminates the lane section Bi to re-plan the route. When the warning evaluation value GL is less than the threshold GB, the cloud-side management unit re-includes the lane section Bi in the planned route; wherein, the vehicle-side control unit determines the coordinates of the unmanned vehicle through the UWB positioning unit and the UWB base station.

[0018] Under normal circumstances, the roadside terminal can determine in advance whether the lane environment is passable. However, due to the periodicity of the roadside terminal's data collection, if the environment changes during the data collection period, the roadside warning signal cannot be generated in time. If the unmanned vehicle has entered or is about to enter the lane section Bi where the environment has changed, it is necessary to conduct a situation analysis in conjunction with the vehicle-side control unit. The specific contents are as follows: When the on-board lidar detects an obstacle on the unmanned vehicle's route and the vehicle-side control unit does not receive a roadside warning signal, the on-board computing host calls the vehicle-side perception system to collect lane image data. The on-board computing host then segments the lane image data according to preset conditions to obtain abnormal data Zi, which contains a timestamp. The on-board computing host generates a vehicle-side warning signal and calls the on-board V2X unit to send the vehicle-side warning signal and abnormal data Zi to the roadside computing unit in the lane section Bi where the unmanned vehicle is located. The roadside computing unit then sends the vehicle-side warning signal and abnormal data Zi to the cloud management unit via a wireless communication network.

[0019] Furthermore, the steps of fusing the mine tunnel internal environment perception data with the abnormal data Zi include: S31. Recalculate parameters :The roadside calculation unit controls the roadside data acquisition unit to reacquire the roadside point cloud data and calculate the parameters , if the parameter If the value is greater than or equal to the threshold E, the roadside point cloud data is fused with the abnormal data Zi for perception data. Otherwise, the roadside point cloud data is not considered, and the on-board computing host determines whether the vehicle can continue driving by analyzing the images collected by the on-board camera. S32, data acquisition and synchronization processing: when the parameter When it is greater than or equal to the threshold E, the roadside computing unit uses the timestamp to align the roadside point cloud data and the abnormal data Zi; S33, feature extraction: The roadside computing unit uses the DBSCAN clustering algorithm to identify obstacle features on the roadside point cloud data and extracts the boundary points of the obstacle. The roadside computing unit uses the YOLO algorithm to identify obstacle features on the abnormal data Zi and obtain the bounding box of the obstacle. S34, data fusion: Match the point data in the roadside point cloud data after feature extraction with the detection results of the abnormal data Zi, verify the match by whether the point falls within the detected abnormal data Zi boundary box, and then fuse the roadside point cloud data and the abnormal data Zi through the Kalman filter method; S35. Calculate the size and relative position of the obstacle: Calculate the minimum bounding box of the obstacle through the boundary points of the obstacle, then calculate the coordinates of the center point of the obstacle, and obtain the coordinates of the unmanned vehicle in the global coordinate system through the UWB positioning unit. Convert the coordinates of the center point of the obstacle to the coordinates in the global coordinate system, and calculate the Euclidean distance D from the center point of the obstacle to the unmanned vehicle.

[0020] In order to determine whether the unmanned vehicle can continue to drive, the risk assessment parameter Rs is calculated. The specific steps are: calculate the product of the length, width and height of the bounding box to obtain the obstacle volume S, obtain the Euclidean distance D and the vehicle speed v, and obtain the parameter , normalize the obstacle volume S, Euclidean distance D, and vehicle speed v, and calculate the risk assessment parameter Rs, , where u1, u2, u3, u4 are weight parameters, and Rs is greater than 0 and less than 1.

[0021] The cloud management unit compares the risk assessment parameter Rs with the risk threshold. Risk threshold T1 is a low-risk threshold, and risk threshold T2 is a high-risk threshold. If Rs is less than T1, the vehicle can pass safely. If Rs is greater than or equal to T1 and less than T2, the cloud management unit generates a low-speed travel instruction and sends it to the roadside computing unit through the wireless communication network. The roadside computing unit sends the low-speed travel instruction to the on-board computing host through the roadside V2X unit, thereby controlling the speed of the unmanned vehicle. If Rs is greater than T2, the cloud management unit replans the route.

[0022] The beneficial effects of the present invention are as follows: (1) The present invention divides the mine tunnel into several sections. The roadside data acquisition unit and the roadside computing unit provided in each section collect and process the tunnel environment data within the section. This allows for more accurate determination and prediction of whether the tunnel environment is suitable for unmanned vehicles, providing a basis for route planning. (2) The present invention determines and predicts the lane environment in advance, reducing the amount of data calculation of the vehicle-side control unit and being more conducive to the regulation of the unmanned vehicle; the vehicle-side control unit can assist the roadside computing unit in more timely determining the driving environment in the lane, and ensure the timeliness of the operation of the unmanned vehicle through the determination of the cloud management unit, thereby reducing unnecessary route changes and avoiding the impact on production activities. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] The present invention will be further described below with reference to the accompanying drawings; Figure 1 This is a flow chart of the system of the present invention;. DETAILED DESCRIPTION

[0024] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0025] Example 1: The present invention is a vehicle-road cooperative unmanned vehicle control system in a lane: It includes a roadside data acquisition unit for collecting environmental perception data inside the mine tunnel.

[0026] The roadside data collection unit includes a wireless communication network and a roadside environment perception system; the wireless communication network of the roadside data collection unit includes a 4G / 5G network and a WiFi network.

[0027] The roadside environment perception system includes lidar, mining cameras, temperature and humidity sensors, infrared sensors, and UWB base stations. When the infrared sensor collects heat source data, the lidar does not collect data unless it receives other instructions, preventing the collection of personnel data and causing it to be mistakenly identified as an obstacle.

[0028] The system also includes a roadside computing unit for receiving and storing environmental perception data from the interior of the mine tunnel, calculating roadside point cloud data, and obtaining a roadside warning assessment value GL within a set time frequency. In this embodiment, the time frequency set is to collect data every 6 hours. If the warning evaluation value GL exceeds the threshold GB, a roadside warning signal is generated, and the roadside warning signal is sent to the vehicle-side control unit through the roadside V2X unit, and the roadside warning evaluation value GL is sent to the cloud management unit through the wireless communication network.

[0029] The vehicle-side control unit is used to collect road perception data on the mine tunnel route; the vehicle-side control unit includes a vehicle-side perception system, an on-board V2X unit, an on-board computing host, a wireless communication network, a UWB positioning unit, an inertial measurement unit, and a speed sensor unit; the vehicle-side perception system includes an on-board lidar and an on-board camera, which are used to collect road perception data on the mine tunnel route; the wireless communication network of the vehicle-side control unit includes a 4G / 5G network and a WiFi network.

[0030] The vehicle-side control unit evaluates whether there is abnormal data Zi. If there is abnormal data Zi, it generates a vehicle-side warning signal and sends the vehicle-side warning signal and abnormal data Zi to the roadside computing unit through the on-board V2X unit. The roadside computing unit controls the roadside environmental perception system through the wireless communication network to collect environmental perception data inside the mine tunnel, and combines the perception data with the abnormal data Zi for data fusion. The risk assessment parameter Rs is calculated by the roadside computing unit and sent to the cloud management unit through the wireless communication network. The cloud management unit determines whether the unmanned vehicle should re-plan its route based on the risk assessment parameter Rs.

[0031] The cloud management unit is used to store and analyze data and control unmanned vehicles; the roadside computing unit regularly sends its stored data to the cloud management unit via the wireless communication network; The cloud management unit plans the unmanned vehicle route based on the stored historical data, generates route instructions, and sends the route instructions to the roadside computing unit via the wireless communication network. The roadside computing unit sends the instructions to the vehicle-side control unit via the roadside V2X unit, and the vehicle-side control unit controls the operation of the unmanned vehicle; the historical data includes but is not limited to the environmental perception data inside the mine tunnel, roadside point cloud data, abnormal data Zi, roadside warning assessment value GL, and risk assessment parameter Rs.

[0032] The cloud management unit divides the tunnel map data into several tunnel intervals Bi, i=1~n, n is a positive integer; each tunnel interval Bi is respectively provided with a roadside data collection unit and a roadside calculation unit, and the roadside calculation unit in each tunnel interval Bi is set with a number corresponding to the coordinate of the tunnel interval Bi, such as the roadside calculation unit installed in the tunnel interval B1 is numbered SE001, the roadside calculation unit installed in the tunnel interval B2 is numbered SE002, and so on; the number is set manually, and each roadside calculation unit has a unique number. The number of the roadside calculation unit serves as the basis for the cloud management unit to identify the tunnel interval Bi data and store it. When the roadside calculation unit exchanges data with the cloud management unit, the data contains the number data of the roadside calculation unit. The cloud management unit first identifies the number data and then corresponds to the coordinate interval of the specific tunnel interval Bi; the coordinate interval of the tunnel interval Bi is positioned by multiple sets of UWB base stations installed in the mine tunnel; generally, the UWB base station calculates the precise coordinates through triangulation, and obtains the global coordinate system through the UWB base station.

[0033] The roadside data collection unit is connected to the roadside computing unit via a wireless communication network; the roadside computing unit is connected to the cloud management unit via a wireless communication network.

[0034] In order to evaluate the condition of the tunnel wall and its ancillary equipment, the roadside point cloud data is calculated; The specific steps include: S11. Raw point cloud data acquisition: Several laser radars are installed in each lane section Bi, so that the laser radar scanning range can cover the road, inner wall, and inner wall accessories of the lane section Bi. After the laser radar scans, raw point cloud data is obtained. The raw point cloud data contains the three-dimensional coordinates and timestamp of each point. S12. Data preprocessing: Calculate the mean neighborhood distance of each point, remove points exceeding a preset threshold, and then divide the remaining point cloud data into three-dimensional grids. Each three-dimensional grid is represented by a representative point, which is the centroid of the three-dimensional grid. The centroid calculation formula is: , C is the centroid, n is the number of points in the three-dimensional network, and Xi is the point coordinate; Then the coordinates of the representative points are transformed to obtain the preprocessed point cloud data, where the transformation uses the three-dimensional rotation matrix R and the translation vector t to transform the coordinate system, Xa=RX+t, X is the coordinate of the representative point, Xa is the coordinate of the transformed point cloud data, R is the rotation matrix, and t is the translation vector; for example, the rotation matrix for the angle θ around the z-axis is , the rotation matrix can represent the rotation around the x, y, and z axes.

[0035] S13, registering the pre-processed point cloud data: aligning the pre-processed point cloud data of different frames using the RANSAC algorithm to obtain coarse point cloud data; S14. Registration of coarse point cloud data: The coarse point cloud data is accurately aligned using the ICP algorithm to obtain point cloud data. The rotation matrix can be accurately calculated through iterative optimization. S15. Feature extraction: Calculate the normal vector of the point cloud surface by a normal estimation method to obtain the simulated geometric structure of the road in the lane section Bi and the simulated geometric structure of the inner wall and the inner wall accessories of the lane section Bi; S16. Data storage: The formed point cloud data is stored in the roadside computing unit, that is, the point cloud data formed in the lane section B1 is stored in the roadside computing unit of the lane section B1, and so on; the roadside computing unit packages the point cloud data together with the identification data of the lane section Bi where the roadside computing unit is located, and sends the packaged point cloud data to the cloud management unit via the wireless communication network; the identification data of the lane section Bi is the coordinate interval of the lane section Bi.

[0036] To determine whether there are obstacles or obstacle risks in the roadway environment, the roadside warning assessment value GL is calculated using point cloud data. The specific steps include: S21. Calculating abnormal point cloud data: The roadside computing unit acquires point cloud data, extracts point cloud data of the road area, and records it as road point cloud data. A filtering condition K is set, where the filtering condition K is a coordinate value used to filter out extreme values ​​of point cloud coordinate data that are above or below the road surface. The extreme value is set by a technician based on actual conditions. The road point cloud data that meets the condition is counted to obtain first abnormal data M. The roadside computing unit extracts point cloud data of the inner wall and its accessories, and records it as inner wall point cloud data. A filtering condition L is set, where the filtering condition L is a coordinate value used to filter out extreme values ​​of point cloud coordinate data that protrude from the inner wall of the roadway. The extreme value is set by a technician based on actual conditions. The inner wall point cloud data that meets the condition is counted to obtain second abnormal data N. S22, calculation parameters :Calculate the ratio of the first abnormal data M to the set threshold m, calculate the ratio of the second abnormal data N to the set threshold n, and calculate the parameter ; S23, calculation parameters :The roadside calculation unit records the number of roadside warning signals generated by the lane section Bi where it is located, P, and calculates the parameters ,in is the historical data weight coefficient. In this embodiment, is 1.22; S24, calculation parameters :The roadside calculation unit obtains the temperature data T and humidity data H collected by the roadside data collection unit and calculates ,in Indicates the historical minimum temperature in the lane interval Bi, Indicates the historical maximum temperature in the lane interval Bi, Indicates the historical minimum humidity value within the lane interval Bi, Indicates the historical maximum humidity in the lane interval Bi, is the temperature data weight coefficient, is the humidity data weight coefficient. In this embodiment, Take 1.02, Take 1.36; S25. Calculate the roadside warning evaluation value GL: If the warning evaluation value GL is greater than or equal to the threshold GB, a roadside warning signal is generated, otherwise no roadside warning signal is generated. In this embodiment, the value of GB is 11.56.

[0037] If the warning evaluation value GL is less than the threshold GB, no roadside warning signal is generated and the unmanned vehicle continues to travel along the original route; If the warning evaluation value GL is greater than or equal to the threshold GB, a roadside warning signal is generated; when the roadside warning signal is generated, the roadside computing unit sends the roadside warning signal to the vehicle-side control unit through the roadside V2X unit. If the vehicle-side control unit receives the roadside warning signal, the vehicle-side control unit controls the unmanned vehicle to no longer enter the corresponding lane section Bi. The cloud-side management unit records the roadside warning signal of the lane section Bi, and eliminates the lane section Bi and replans the route until the warning evaluation value GL is less than the threshold GB. The cloud-side management unit re-includes the lane section Bi in the planned route. Among them, the vehicle-side control unit determines the coordinates of the unmanned vehicle through the UWB positioning unit and the UWB base station.

[0038] This embodiment divides the mine tunnels into several sections. The roadside data collection unit and roadside computing unit set in each section collect and process the tunnel environment data in the section, which can more accurately determine and predict whether the tunnel environment is suitable for unmanned vehicles to pass through, providing a basis for route planning; judging and predicting the tunnel environment in advance reduces the data calculation amount of the vehicle-side control unit, which is more conducive to the regulation of unmanned vehicles.

[0039] Example 2: The difference between this embodiment and the first embodiment is that: if the warning evaluation value GL is less than the threshold GB, no roadside warning signal is generated, and the unmanned vehicle continues to travel along the original route. When the unmanned vehicle approaches or enters a certain lane section Bi, the vehicle-side control unit of the unmanned vehicle detects abnormal data.

[0040] Under normal circumstances, the roadside terminal can determine in advance whether the lane environment is passable. However, due to the periodicity of the roadside terminal's data collection, if the environment changes during the data collection period, the roadside warning signal cannot be generated in time. If the unmanned vehicle has entered or is about to enter the lane section Bi where the environment has changed, it is necessary to conduct a situation analysis in conjunction with the vehicle-side control unit. The specific contents are as follows: When the on-board lidar detects an obstacle on the unmanned vehicle's route and the vehicle-side control unit does not receive a roadside warning signal, the on-board computing host calls the vehicle-side perception system to collect lane image data. The on-board computing host then cuts the lane image data according to preset conditions to obtain abnormal data Zi, which contains a timestamp. The on-board computing host cuts the inner wall of the lane and its ancillary equipment in the lane image data by training the YOLO algorithm, and the remaining lane image data is used as abnormal data Zi.

[0041] The on-board computing host generates a vehicle-side warning signal and calls the on-board V2X unit to send the vehicle-side warning signal and abnormal data Zi to the roadside computing unit in the lane section Bi where the unmanned vehicle is located. The roadside computing unit sends the vehicle-side warning signal and abnormal data Zi to the cloud management unit via the wireless communication network.

[0042] The steps for fusing the mine tunnel internal environment perception data with the abnormal data Zi include: S31. Recalculate parameters : When an unmanned vehicle follows a set route, the coordinates of the unmanned vehicle are determined by the on-board UWB positioning unit and the UWB base station, and then the lane section Bi in which the unmanned vehicle is located can be determined; when the cloud management unit receives the vehicle-side warning signal and abnormal data Zi, it sends a roadside point cloud data collection instruction via the wireless communication network to the roadside computing unit in the lane section Bi where the unmanned vehicle is located and the roadside computing unit in the next lane section Bi in the direction of the unmanned vehicle's route.

[0043] For example, the preset driving route of the unmanned vehicle is to pass through lane section B1 to lane section B5 in sequence. When the unmanned vehicle enters lane section B2, the on-board laser radar detects that there is an obstacle on the unmanned vehicle's route, and the vehicle-side control unit does not receive the roadside warning signal. The on-board computing host generates a vehicle-side warning signal and calls the on-board V2X unit to send the vehicle-side warning signal and abnormal data Zi to the roadside computing unit in lane section B2 where the unmanned vehicle is located. The roadside computing unit in lane section B2 sends the vehicle-side warning signal and abnormal data Zi to the cloud management unit through the wireless communication network. After the cloud management unit receives the vehicle-side warning signal and abnormal data Zi, it sends the roadside point cloud data collection instruction to the roadside computing unit in lane section B2 and the roadside computing unit in lane section B3 through the wireless communication network, and collects the roadside point cloud data respectively, and then calculates the parameters respectively. .

[0044] The roadside calculation unit controls the roadside data acquisition unit to reacquire the roadside point cloud data and calculate the parameters , if the parameter If the threshold value E is greater than or equal to the threshold value E, which is 1.43 in this embodiment, the roadside point cloud data is fused with the abnormal data Zi. Otherwise, the roadside point cloud data is not considered, and the vehicle computing host determines whether the vehicle can continue driving by analyzing the images collected by the vehicle camera. S32, data acquisition and synchronization processing: when the parameter When it is greater than or equal to the threshold E, the roadside computing unit uses the timestamp to align the roadside point cloud data and the abnormal data Zi; S33, feature extraction: The roadside computing unit uses the DBSCAN clustering algorithm to identify obstacle features on the roadside point cloud data and extracts the boundary points of the obstacle. The roadside computing unit uses the YOLO algorithm to identify obstacle features on the abnormal data Zi and obtain the bounding box of the obstacle. S34, data fusion: Match the point data in the roadside point cloud data after feature extraction with the detection results of the abnormal data Zi, verify the match by whether the point falls within the detected abnormal data Zi boundary box, and then fuse the roadside point cloud data and the abnormal data Zi through the Kalman filter method; S35. Calculate the size and relative position of the obstacle: Calculate the minimum bounding box of the obstacle using the boundary points of the obstacle, then calculate the coordinates of the center point of the obstacle. Obtain the coordinates of the unmanned vehicle in the global coordinate system using the UWB positioning unit. Convert the coordinates of the center point of the obstacle to coordinates in the global coordinate system, and calculate the Euclidean distance D from the center point of the obstacle to the unmanned vehicle. The global coordinate system is constructed by arranging multiple UWB base stations (anchor points) at known fixed locations, and the origin and axis of the global coordinate system are defined by the positions of the UWB base stations. The coordinates of the unmanned vehicle in the global coordinate system (Xr, Yr, Zr) obtained by UWB positioning, the point cloud coordinates of the obstacle in the lidar coordinate system (Xa, Ya, Za), the position and deflection angle in the known lane interval Bi , we can get the coordinates of the lidar in the global coordinate system (Xb, Yb, Zb), transform the point cloud coordinates (Xa, Ya, Za) into global coordinates (Xg, Yg, Zg), and calculate the rotation transformation (assuming only rotation around the Z axis): , and then perform a translation transformation: ; Calculate Euclidean distance .

[0045] In order to determine whether the unmanned vehicle can continue to drive, the risk assessment parameter Rs is calculated. The specific steps are as follows: the product of the length, width and height of the bounding box is calculated to obtain the obstacle volume S, and the Euclidean distance D and vehicle speed v are obtained. The vehicle speed is obtained through the speed sensor unit.

[0046] Get Parameters , normalize the obstacle volume S, Euclidean distance D, and vehicle speed v, and calculate the risk assessment parameter Rs, , where u1, u2, u3, u4 are weight parameters, and Rs is greater than 0 and less than 1.

[0047] The cloud management unit compares the risk assessment parameter Rs with the risk threshold. Risk threshold T1 is a low-risk threshold, and risk threshold T2 is a high-risk threshold. If Rs is less than T1, it can pass safely. If Rs is greater than or equal to T1 and less than T2, the cloud management unit generates a low-speed travel instruction and sends it to the roadside computing unit through the wireless communication network. The roadside computing unit sends the low-speed travel instruction to the on-board computing host through the roadside V2X unit, thereby controlling the speed and driving position of the unmanned vehicle; if Rs is greater than T2, the cloud management unit replans the route.

[0048] The vehicle-side control unit of this embodiment can assist the roadside computing unit in determining the driving environment in the lane more timely, ensure the timeliness of the unmanned vehicle operation through the determination of the cloud management unit, reduce unnecessary route changes, and thus avoid affecting production activities.

[0049] The threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technicians in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0050] The above formulas are obtained by collecting a large amount of data and performing software simulation, and a formula close to the actual value is selected. The coefficients in the formula are set by those skilled in the art according to actual conditions. The above is only a preferred specific implementation method of the present invention, but the protection scope of the present invention is not limited to this. Any technician familiar with this technical field, within the technical scope disclosed by the present invention, can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A vehicle-road cooperative unmanned vehicle control system in a lane, characterized in that: It includes a roadside data collection unit for collecting environmental perception data inside the mine tunnel; It also includes a roadside computing unit, which is used to receive the environmental perception data inside the mine tunnel, calculate and form roadside point cloud data, calculate and obtain the roadside warning evaluation value GL within a set time frequency, and generate a roadside warning signal if the warning evaluation value GL exceeds the threshold GB, and send the roadside warning signal to the vehicle-side control unit through the roadside V2X unit, and send the roadside warning evaluation value GL to the cloud management unit through the wireless communication network; The vehicle-side control unit is used to collect road perception data on the mine tunnel route and evaluate whether there is abnormal data Zi. If there is abnormal data Zi, a vehicle-side warning signal is generated, and the vehicle-side warning signal and abnormal data Zi are sent to the roadside computing unit through the on-board V2X unit. The roadside computing unit controls the roadside environment perception system through the wireless communication network to collect the inner environment perception data of the mine tunnel, and combines the abnormal data Zi to perform perception data fusion. The risk assessment parameter Rs is calculated by the roadside computing unit, and the risk assessment parameter Rs is sent to the cloud management unit through the wireless communication network. The cloud management unit determines whether the unmanned vehicle should re-plan the route according to the risk assessment parameter Rs; The cloud management unit is used for data storage, analysis, and control of unmanned vehicles; The cloud management unit plans the unmanned vehicle route based on the stored historical data, generates route instructions, and sends the route instructions to the roadside computing unit through the wireless communication network. The roadside computing unit sends the instructions to the vehicle-side control unit through the roadside V2X unit, and the vehicle-side control unit controls the operation of the unmanned vehicle.

2. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 1, characterized in that: The cloud management unit divides the lane map data into a number of lane intervals Bi, each of which is provided with a roadside data collection unit and a roadside calculation unit; The roadside data collection unit includes a wireless communication network and a roadside environment perception system. The roadside environment perception system includes a laser radar, a mining camera, a temperature and humidity sensor, an infrared sensor, and a UWB base station. When the infrared sensor collects heat source data, the laser radar does not collect data. The roadside data collection unit is connected to the roadside computing unit through a wireless communication network; the roadside computing unit is connected to the cloud management unit through a wireless communication network.

3. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 2, characterized in that: The calculation steps of the roadside point cloud data include: S11, original point cloud data acquisition: a plurality of laser radars are installed in each lane section Bi, so that the laser radar scanning range can cover the road, inner wall and inner wall auxiliary equipment of the lane section Bi where it is located; after the laser radar scanning, the original point cloud data is obtained, and the original point cloud data includes the three-dimensional coordinates and timestamp of each point; S12, performing data preprocessing: calculating the neighborhood distance mean of each point, removing points exceeding a preset threshold, and then dividing the remaining point cloud data into three-dimensional grids, each three-dimensional grid is represented by a representative point, and the representative point is the centroid of the three-dimensional grid; then transforming the coordinates of the representative point to obtain preprocessed point cloud data; S13, registering the pre-processed point cloud data: aligning the pre-processed point cloud data of different frames by using the RANSAC algorithm to obtain coarse point cloud data; S14, registering the coarse point cloud data: accurately aligning the coarse point cloud data by using the ICP algorithm to obtain point cloud data; S15, feature extraction: Calculate the normal vector of the point cloud surface by a normal estimation method to obtain the simulated geometric structure of the road, inner wall and inner wall accessories of the lane section Bi; S16. Data storage: The formed point cloud data is stored in a roadside computing unit, which packages the point cloud data together with the identification data of the lane section Bi where the roadside computing unit is located, and sends the packaged point cloud data to a cloud management unit via a wireless communication network.

4. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 3, characterized in that: The calculation steps of the roadside warning evaluation value GL include: S21, calculating point cloud abnormal data: the roadside computing unit acquires point cloud data, extracts point cloud data of the road area, records it as road point cloud data, sets filtering condition K, counts road point cloud data that meet the condition, and obtains first abnormal data M; the roadside computing unit extracts point cloud data of the inner wall and inner wall accessories, records it as inner wall point cloud data, sets filtering condition L, counts inner wall point cloud data that meet the condition, and obtains second abnormal data N; S22, calculation parameters :Calculate the ratio of the first abnormal data M to the set threshold m, calculate the ratio of the second abnormal data N to the set threshold n, and calculate the parameter ; S23, calculation parameters :The roadside calculation unit records the number of roadside warning signals generated in the lane section where it is located, and calculates the parameters ,in is the historical data weight coefficient; S24, calculation parameters :The roadside calculation unit obtains the temperature data T and humidity data H collected by the roadside data collection unit, and calculates ,in Indicates the historical minimum temperature in the lane interval Bi, It represents the maximum historical temperature in the lane interval Bi. Indicates the historical minimum humidity value in the lane interval Bi. It represents the maximum historical humidity in the lane interval Bi. is the temperature data weight coefficient, is the humidity data weight coefficient; S25, calculating the roadside warning evaluation value GL: If the warning evaluation value GL is greater than or equal to the threshold GB, a roadside warning signal is generated, otherwise no roadside warning signal is generated.

5. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 4, characterized in that: The roadside computing unit sends the roadside warning signal to the vehicle-side control unit through the roadside V2X unit. If the vehicle-side control unit receives the roadside warning signal, the vehicle-side control unit controls the unmanned vehicle not to enter the corresponding lane section Bi. The cloud management unit records the roadside warning signal of the lane section Bi, and removes the lane section Bi to re-plan the route. When the warning evaluation value GL is less than the threshold GB, the cloud management unit re-includes the lane section Bi in the planned route.

6. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 2, characterized in that: The vehicle-side control unit includes a vehicle-side perception system, a vehicle-mounted V2X unit, a vehicle-mounted computing host, a wireless communication network, a UWB positioning unit, an inertial measurement unit, and a speed sensor unit; the vehicle-side perception system includes a vehicle-mounted laser radar and a vehicle-mounted camera, which are used to collect road perception data on the route of the mine tunnel.

7. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 6, characterized in that: When the on-board laser radar detects an obstacle on the route of the unmanned vehicle and the vehicle-side control unit does not receive a roadside warning signal, the on-board computing host calls the vehicle-side perception system to collect lane image data, and then the on-board computing host cuts the lane image data according to preset conditions to obtain abnormal data Zi, and the abnormal data Zi contains a timestamp; the on-board computing host generates a vehicle-side warning signal, and calls the on-board V2X unit to send the vehicle-side warning signal and the abnormal data Zi to the roadside computing unit in the lane section Bi where the unmanned vehicle is located.

8. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 7, characterized in that: The step of fusing the inner environment perception data of the mine tunnel with the abnormal data Zi comprises: S31. Recalculate parameters :The roadside computing unit controls the roadside data acquisition unit to reacquire the roadside point cloud data and calculate the parameters , if the parameter If it is greater than or equal to the threshold value E, the roadside point cloud data is fused with the abnormal data Zi for perception data. Otherwise, the roadside point cloud data is not considered. The on-board computing host determines whether the vehicle can continue to drive by analyzing the images collected by the on-board camera. S32, data collection and synchronization processing: when the parameter When it is greater than or equal to the threshold E, the roadside computing unit uses the timestamp to align the roadside point cloud data and the abnormal data Zi; S33, feature extraction: the roadside computing unit uses the DBSCAN clustering algorithm to identify obstacle features from the roadside point cloud data and extracts boundary points of the obstacle; the roadside computing unit uses the YOLO algorithm to identify obstacle features from the abnormal data Zi and obtains the boundary box of the obstacle; S34, data fusion: matching the point data in the roadside point cloud data after feature extraction with the detection results of the abnormal data Zi, verifying the match by whether the point falls within the detected abnormal data Zi boundary box, and then fusing the roadside point cloud data with the abnormal data Zi through the Kalman filtering method; S35. Calculate the size and relative position of the obstacle: calculate the minimum bounding box of the obstacle through the boundary points of the obstacle, then calculate the coordinates of the center point of the obstacle, and obtain the coordinates of the unmanned vehicle in the global coordinate system through the UWB positioning unit, convert the coordinates of the center point of the obstacle into coordinates in the global coordinate system, and calculate the Euclidean distance D from the center point of the obstacle to the unmanned vehicle.

9. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 8, characterized in that: The calculation steps of the risk assessment parameter Rs are: Calculate the product of the length, width, and height of the bounding box to get the obstacle volume S, obtain the Euclidean distance D and the vehicle speed v, and obtain the parameters , normalize the obstacle volume S, Euclidean distance D, and vehicle speed v, and calculate the risk assessment parameter Rs, , where u1, u2, u3, u4 are weight parameters, and Rs is greater than 0 and less than 1.

10. The in-lane vehicle-road cooperative unmanned vehicle control system according to claim 9, characterized in that: The cloud management unit compares the risk assessment parameter Rs with the risk threshold, where risk threshold T1 is a low risk threshold and risk threshold T2 is a high risk threshold. If Rs is less than T1, the vehicle can pass safely. If Rs is greater than or equal to T1 and less than T2, the cloud management unit generates a low-speed travel instruction and sends it to the roadside computing unit via the wireless communication network. The roadside computing unit sends the low-speed travel instruction to the on-board computing host via the roadside V2X unit. If Rs is greater than T2, the cloud management unit re-plans the route.

Images