Autonomous obstacle avoidance method and system for automatic driving tractor

Abstract

The invention relates to the technical field of autonomous obstacle avoidance, and discloses an autonomous obstacle avoidance method and system for an autonomous driving tractor, and the method comprises the following steps: obtaining surrounding real-time traffic information data in the driving process of the tractor, determining a large-flow region, and determining a selectable path set through searching in combination with the total driving time; the method can help a tractor to recognize in advance and avoid a large-flow area as much as possible, reduces the probability of meeting with obstacles, reduces the complexity of obstacle avoidance, selects a priority path by combining historical traffic information, improves the reasonability of path planning, further optimizes the driving path through path splicing operation, reduces the road sections passing through the large-flow area, and improves the efficiency of path planning. The driving safety and efficiency are improved, and the optimal driving path is determined by comprehensively considering the total path driving time, so that the tractor can arrive at the destination more quickly.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of autonomous obstacle avoidance, in particular to an automatic driving tractor autonomous obstacle avoidance method and system. BACKGROUND

[0002] The automatic driving tractor is an intelligent vehicle that integrates advanced technology and performs transportation tasks in specific scenarios, has the ability of environment perception, intelligent decision-making and automatic control, and is becoming a key equipment in the logistics and industrial fields. In the application scenarios of the automatic driving tractor, such as logistics parks and port terminals, the tractor needs to complete the transportation task in a complex traffic environment. The existing path planning method often only relies on static map information and does not fully consider real-time traffic conditions. In actual operation, dynamic factors such as traffic flow, congestion and traffic accidents change all the time, which makes the pre-planned path not the optimal choice, and even causes the tractor to be trapped in a congested section, greatly increasing the travel time and reducing the transportation efficiency. SUMMARY

[0003] The purpose of the present application is to provide an automatic driving tractor autonomous obstacle avoidance method and system to solve the problem that the existing path planning method often only relies on static map information and does not fully consider real-time traffic conditions. In actual operation, dynamic factors such as traffic flow, congestion and traffic accidents change all the time, which makes the pre-planned path not the optimal choice, and even causes the tractor to be trapped in a congested section, greatly increasing the travel time and reducing the transportation efficiency.

[0004] In a first aspect, the present application provides an automatic driving tractor autonomous obstacle avoidance method, comprising the following steps: Obtain the surrounding real-time traffic information data of the tractor driving process, determine the high-flow area, and determine the selectable path set by searching and combining the total travel time; Based on the selectable path set, first calculate and process the historical traffic situation data of the selectable path to obtain a priority selection value, identify the priority selection path, and then perform path splicing to obtain an effective splicing path set; The traffic situation data includes traffic congestion data and traffic accident data. According to the priority selection path set and the effective splicing path set, combine the total path travel time for comparison and analysis to obtain the best travel path.

[0005] In a second aspect, the present application provides an automatic driving tractor autonomous obstacle avoidance system, which comprises: The selectable path acquisition module acquires surrounding real-time traffic information data of the tractor driving process, determines a heavy traffic area, and determines a selectable path set through searching combined with total driving time; The priority selection path acquisition module: based on the selectable path set, combined with historical traffic situation data of the selectable path, obtains a priority selection value through calculation and processing, and identifies a priority selection path; The traffic information data includes traffic congestion data and traffic accident data. The path splicing module: based on the priority selection path set, splices the paths to obtain an effective spliced path. The best path selection module: according to the priority selection path set and the effective spliced path set, combined with total path driving time, analyzes to obtain a best driving path.

[0006] The beneficial effects of the present application are: The present application can help the tractor to identify and avoid the heavy traffic area in advance, reduce the probability of encountering obstacles, reduce the complexity of obstacle avoidance, select a priority path by combining historical traffic information, improve the rationality of path planning, further optimize the driving path through path splicing operation, reduce the road section passing through the heavy traffic area, improve the driving safety and efficiency, determine the best driving path by comprehensively considering the total path driving time, and make the tractor reach the destination more quickly. BRIEF DESCRIPTION OF DRAWINGS

[0007] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0008] Figure 1 It is a flow chart of an automatic driving tractor autonomous obstacle avoidance method of the present application; Figure 2 It is a structural schematic diagram of an automatic driving tractor autonomous obstacle avoidance system of the present application; Figure 3 It is a structural schematic diagram of an automatic driving tractor autonomous obstacle avoidance device of the present application.

[0009] In the figure: 3, computer equipment; 301, processor; 302, memory; 303, computer program; DETAILED DESCRIPTION

[0010] In the following, the technical solutions in the embodiments of the present application will be described clearly and completely in conjunction with the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work should fall within the protection scope of the present application.

[0011] Embodiment one:

[0012] Figure 1 A flowchart of an autonomous obstacle avoidance method of an automatic driving tractor is provided in the embodiment one of the present application. The embodiment of the present application can be applicable to a case of autonomously avoiding obstacles and selecting a path with a better obstacle avoidance effect. The autonomous obstacle avoidance method of the automatic driving tractor can be executed by an autonomous obstacle avoidance system of the automatic driving tractor. The autonomous obstacle avoidance system of the automatic driving tractor can be realized by software and / or hardware. The autonomous obstacle avoidance system of the automatic driving tractor can be configured in an autonomous obstacle avoidance device of the automatic driving tractor. Optionally, the autonomous obstacle avoidance device of the automatic driving tractor can be an electronic device, which can be a notebook, a desktop computer, a smart tablet and the like. The embodiment of the present application does not limit this.

[0013] The autonomous obstacle avoidance method of the automatic driving tractor provided in the embodiment of the present application specifically includes the following steps. Step one: In the process of automatic driving, the tractor acquires real-time traffic information data around the tractor and analyzes the data to search and determine a set of selectable paths. The traffic information data includes pedestrian flow data and vehicle flow data. In some embodiments, sensors are installed at different positions of the tractor. The sensors include but are not limited to a laser radar. A monitoring period is set. The three-dimensional point cloud data generated by the laser radar is processed by the laser radar. A point cloud segmentation algorithm is used to divide the point cloud into different analysis regions. The pedestrian flow and the vehicle flow are obtained based on the density and distribution of the point cloud of each region. The regions with large flow and the regions with small flow are identified. It needs to be explained that the reason for identifying the large flow area and the small flow area is that the large flow area means that there are more pedestrians and vehicles, which are potential obstacles for the towing vehicle. The towing vehicle can preferentially select the small flow area when planning the path to avoid the large flow area as much as possible, thereby reducing the probability of encountering obstacles and the complexity of obstacle avoidance. In the large flow area, the movement of pedestrians and vehicles can be more complex and disordered, and the towing vehicle needs to consider more factors to make obstacle avoidance decisions. Therefore, identifying the large flow area before path planning and avoiding these areas when planning the path can reduce the difficulty of autonomous obstacle avoidance for the towing vehicle. Based on any one analysis area, the point cloud quantity of pedestrians and the point cloud quantity of vehicles are obtained respectively, and are summed to obtain the total point cloud quantity. The total point cloud quantity is compared with the total area of the region to obtain the point cloud density value. The point cloud distribution coefficient is calculated by the DBSCAN algorithm. The specific process is as follows: Set the neighborhood radius and the minimum point number. For all point clouds in the analysis area, check whether the number of points in the neighborhood radius is greater than or equal to the minimum point number. If yes, the point is a core point, and a cluster is formed with the points in its neighborhood. If the number of points in the neighborhood of a point is less than the minimum point number, but it has an intersection with the neighborhood of a core point, the point is a boundary point and belongs to the cluster of the core point. Otherwise, it is a noise point. For each point cloud i, the average distance Ai between it and other point clouds in the same cluster is calculated, and the average distance Bi between it and all point clouds in other clusters is calculated. Substitute the formula to calculate the contour coefficient Si. It needs to be explained that represents the maximum value of Ai and Bi. When Si is close to 1, it indicates that the point cloud is very compact in the cluster and is well separated from other clusters. When Si is close to -1, it means that the point cloud may be misclassified. When Si is close to 0, it indicates that the point cloud is at the boundary of the cluster. Sum all the contour coefficients of the point clouds to obtain the mean value of the contour coefficients, which is the point cloud distribution coefficient. Multiply the point cloud density value and the point cloud distribution coefficient to obtain the flow degree evaluation value. Set the flow degree evaluation threshold. The analysis area corresponding to the flow degree evaluation value greater than the flow degree evaluation threshold is marked as the large flow area, and the analysis area corresponding to the flow degree evaluation value less than or equal to the flow degree evaluation threshold is marked as the small flow area. Obtain a high-precision map containing the driving area of the towing vehicle, which includes but is not limited to the topological structure of the road. Integrate the identified traffic large area information with the high-precision map to determine the specific position and range of the traffic large area on the map; Use the Dijkstra algorithm to search for selectable paths, and the specific process is as follows: Set the current position of the tractor as the starting point and the destination to be reached as the target point to obtain a plurality of drivable paths; Based on any drivable path, divide it into a plurality of calculation road segments to obtain the driving time of each calculation road segment; It should be noted that the driving time is summarized and set by a person skilled in the art according to historical driving speed; Multiply the driving time of the calculation road segment passing through the traffic large area by the risk coefficient to obtain a high driving time, and mark the driving time of the calculation road segment not passing through the traffic large area as a normal driving time; The risk coefficient takes a value greater than 1, which is summarized and set by a person skilled in the art according to the specific characteristics of the traffic large area and combined with historical driving speed, and its value is to reflect that due to the large flow of pedestrians or vehicles on the calculation road segment, the driving time will be increased; Sum all the high driving times and normal driving times to obtain the total path driving time; Set a path driving time threshold, and keep the drivable paths corresponding to the path driving time less than the path driving time threshold, and mark them as selectable paths, and mark the remaining drivable paths as non-selectable paths; Obtain all selectable paths and mark them as a selectable path set; Step 2: Based on the selectable path set, combine the historical traffic situation data of the selectable paths to identify the priority selection path; In some embodiments, the selectable path set is obtained based on any selectable path; Based on the current driving time and the sum of the total path driving time, the driving end time is obtained, the period from the current driving time to the driving end time is marked as the analysis period, and the traffic situation data in the analysis period of each day in the historical data is obtained; The traffic situation data includes traffic congestion data and traffic accident data; The traffic congestion data includes path congestion duration and congestion length, and the traffic accident data includes traffic accident frequency and accident handling duration; Sum the path congestion duration in the historical data to obtain the average path congestion duration, and perform ratio processing on the average path congestion duration and the analysis period of the selectable path to obtain the congestion duration ratio value; Summing up the path congestion length in the historical data to obtain a path congestion length average value, and performing ratio processing on the path congestion length average value and the total path length of the selectable path to obtain a congestion length ratio value; Performing product calculation on the congestion time ratio value and the congestion length ratio value to obtain a congestion representation value; The role of calculating the congestion representation value is: firstly, it intuitively and comprehensively reflects the congestion severity of a certain selectable path in a specific analysis period; secondly, as an important quantitative index, the congestion representation value improves the accuracy and rationality of path planning in the process of identifying the priority selection path; thirdly, in the automatic driving process of the towing vehicle, the calculated congestion representation value can be combined with other traffic information to plan a driving route that avoids congested sections in advance; Summing up the number of traffic accidents in the historical data to obtain a total number of accidents, and performing ratio calculation on the total number of accidents and the total number of days in the historical data to obtain an accident frequency value; Summing up the traffic accident handling time in the historical data to obtain an accident handling time average value, and performing ratio processing on the accident handling time average value and the analysis period to obtain an accident handling time ratio value; Performing product calculation on the accident frequency value and the accident handling time ratio value to obtain a traffic mutation value; The role of calculating the traffic mutation is: firstly, it quantifies the impact of traffic accidents on traffic conditions and intuitively reflects the degree of interference of a certain path in a specific period; secondly, the traffic mutation value is used as an important index to calculate the priority selection value when determining the priority selection path; thirdly, selecting a path with a low traffic mutation value means that the towing vehicle has a relatively low risk of encountering traffic accidents during driving, which can effectively reduce situations such as parking and detouring caused by traffic accidents; Performing weighted sum calculation on the congestion representation value, the traffic mutation value, and the total driving time to obtain a priority selection value; Obtaining the priority selection values of all selectable paths, and extracting the maximum value xd as the maximum priority selection value; Setting an interval step c to identify the number of priority selection values within the interval [xd-c, xd]; The interval step c is used to determine whether there is a value close to the maximum value xd in the priority selection values corresponding to the selectable paths, and the interval step c is set by the implementer according to the characteristics of the data; If the number is one, it means that only the maximum value xd is within the interval [xd-c, xd], and the selectable path corresponding to the maximum value xd is the priority selection path; If the number is not one, it indicates that there is a value close to the maximum value xd, which will correspond to the selectable path, marked as the priority selection path set; The technical scheme of the embodiment is: in the automatic driving process of the towing vehicle, real-time traffic information data is acquired through a sensor, a point cloud data processing technology is used to identify a large-flow area, a Dijkstra algorithm is used to search a drivable path in combination with a high-precision map, a total path driving time is calculated according to a driving time and a risk coefficient of a road section passing through the large-flow area, a threshold value is set to determine a selectable path set, a priority selection value is obtained based on the selectable path set, in combination with historical traffic information data to calculate congestion representation values, traffic mutation values and the like, and then a priority selection path is identified; The effect of the embodiment is that: first, the towing vehicle can avoid potential pedestrian and vehicle motion areas when planning a path, reduce the probability of encountering obstacles, reduce the complexity of obstacle avoidance decision-making, and significantly improve the safety and reliability of obstacle avoidance; Second, in combination with real-time traffic data and a high-precision map, a Dijkstra algorithm is used to search a drivable path, and the driving time and risk coefficient of a road section passing through a large-flow area are considered, the total path driving time is comprehensively calculated, a threshold value is set to filter out a selectable path set, and the traffic conditions of different road sections are considered, so that the planned path is more reasonable, the driving in congested or dangerous areas is reduced, and the driving efficiency is improved; Third, based on the selectable path set, a current driving time is determined to analyze a time period, historical traffic information data of the time period is acquired, a priority selection value is obtained by calculating congestion representation values, traffic mutation values and the like and performing weighted summation, a priority selection path is identified, the evaluation method of historical data considers the traffic risks of different paths in similar time periods, improves the scientificity and accuracy of path selection, and improves the smoothness of driving.

[0014] Embodiment two:

[0015] Based on the above embodiment, as Figure 1 shown, the automatic driving towing vehicle autonomous obstacle avoidance method provided by the embodiment of the application specifically includes the following steps: Step three: based on the priority selection path set, a path is spliced to obtain an effective spliced path; In some embodiments, the priority selection path set is acquired, and any one of the priority selection paths is based on; The calculation road section passing through the large-flow area on the priority selection path is acquired, and the distance deviation value of the priority selection path adjacent to the starting point of the calculation road section is calculated; The calculation method of the distance deviation value includes but is not limited to: Euclidean distance formula; It should be noted that when the distance deviation value of the adjacent priority selection path is calculated, the path of the corresponding small-flow area needs to be selected; Set a distance deviation threshold, and keep the distance deviation values less than the distance deviation threshold to correspond to the selectable path as a spliced path, and splice it with the original preferred selection path; Repeat the identification to complete all possible splicing processes to obtain a spliced path; It should be noted that if there are multiple distance deviation values, the minimum value is taken; Based on any one spliced path, obtain all distance deviation values in the splicing operation process, and sum them up to obtain a total distance deviation value; Set a total distance deviation threshold, keep the total distance deviation values greater than the total distance deviation threshold to correspond to the spliced path, and mark it as an effective path, and mark the remaining spliced paths as invalid paths; Obtain all effective spliced paths and mark them as an effective spliced path set; The above path splicing function is: there may be some large traffic areas in the preferred selection path, and there are many pedestrians and vehicles in these areas, which will increase the difficulty of avoiding obstacles for the towing vehicle. By splicing the path adjacent to the small traffic area in the original preferred selection path through the large traffic area, the path through the large traffic area can be effectively avoided or reduced, thereby reducing the probability of meeting obstacles for the towing vehicle, reducing the complexity of avoiding obstacles, and improving the safety and efficiency of driving; In the path splicing process, the distance deviation value and the total distance deviation value are considered to filter out effective spliced paths. These effective spliced paths are smoother in the driving process, can reduce unnecessary detours, thereby optimizing the driving time, and enable the towing vehicle to reach the destination more quickly; Step four: based on the preferred selection path set and the effective spliced path set, analyze the total path driving time to obtain the best driving path; In some embodiments, the effective spliced path set is obtained based on any one effective spliced path; Calculate the total path driving time of the effective spliced path, and obtain the total path driving time of the preferred selection path; It should be noted that the total path driving time of the spliced path is calculated in the same way as the total path driving time in step one, and will not be repeated here; Extract the corresponding paths in the effective spliced path set and the preferred selection path set and mark them as to-be-compared paths; Extract the minimum value of the total path driving time in the to-be-compared path, and mark the to-be-compared path corresponding to the minimum value of the total path driving time as the best driving path; The reason for taking the minimum value of the total driving time of the corresponding paths in the effective splicing path set and the priority path set is that long driving time means that the tractor stays on the road for a long time, the possibility of encountering obstacles increases, and the risk of obstacle avoidance increases. The path with the shortest total driving time can reduce the residence time in a complex traffic environment and reduce the probability of encountering unexpected traffic conditions. The technical scheme of the embodiment is as follows: obtaining a priority path set, calculating the distance deviation value of the road section passing through the heavy traffic area and the adjacent priority path, setting a threshold value for path splicing, and then selecting the effective splicing path according to the total distance deviation value. Finally, the path corresponding to the minimum value of the total driving time of the priority path set and the effective splicing path set is selected as the best driving path. The effect of this embodiment is that, first, for the heavy traffic area that may exist in the priority path, the distance deviation value is calculated to splice the road section passing through the heavy traffic area with the adjacent path in the small traffic area, thereby reducing the road section passing through the heavy traffic area and reducing the probability of the tractor encountering obstacles, reducing the complexity in the obstacle avoidance process, and improving the safety of driving. Second, in the path splicing process, the distance deviation threshold and the total distance deviation threshold are set to filter the splicing paths and retain the effective splicing paths. The effective splicing paths are smoother in the driving process, reducing unnecessary detours, optimizing the driving time, enabling the tractor to reach the destination more quickly, and improving the overall driving efficiency. Third, based on the priority path set and the effective splicing path set, the total driving time of each path is calculated, and the path corresponding to the minimum value is extracted as the best driving path from a global perspective, considering the driving time under different path planning methods, so that the path selected by the tractor is the optimal path under the current traffic conditions, further improving the driving performance.

[0016] Embodiment three

[0017] Based on the above embodiments, as shown in Figure 2 The automatic driving tractor autonomous obstacle avoidance system provided by the embodiment of the present application specifically comprises: The selectable path acquisition module: in the process of automatic driving of the tractor, real-time traffic information data around the tractor is acquired and analyzed to search and determine a set of selectable paths. The traffic information data includes pedestrian flow data and vehicle flow data. The priority path acquisition module: based on the set of selectable paths, the historical traffic information data of the selectable paths is combined to identify a priority path. The path splicing module: based on the set of priority paths, path splicing is performed to obtain splicing paths. The optimal path selection module: based on the selectable path set and the spliced path set, the total driving time of the path is analyzed to obtain the optimal driving path.

[0018] Embodiment four:

[0019] As Figure 3 shown, the embodiment of the present application further provides a computer device 3, comprising a memory 302 and a processor 301 and a computer program 303 stored in the memory 302, when the computer program 303 is executed on the processor 301, an automatic driving tractor autonomous obstacle avoidance method is realized.

[0020] The computer device 3 can be a desktop computer, a notebook, a palm computer and a cloud server and the like. The computer device 3 can include, but is not limited to, a processor 301, a memory 302. Those skilled in the art can understand, Figure 3 The computer device 3 is only an example and does not constitute a limitation on the computer device 3, and can include more or fewer components than those shown, or combine certain components, or different components, for example, it can also include input and output devices, network access devices and the like.

[0021] The processor 301 can be a central processing unit (CPU), and the processor 301 can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0022] The memory 302 may, in some embodiments, be an internal storage unit of the computer device 3, such as a hard disk or a memory of the computer device 3. The memory 302 may, in other embodiments, also be an external storage device of the computer device 3, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, and the like, equipped on the computer device 3. Further, the memory 302 may, in addition, include both an internal storage unit and an external storage device of the computer device 3. The memory 302 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as program codes of the computer program, and the like. The memory 302 may, in addition, be used to temporarily store data that has been output or is to be output.

[0023] Embodiment Five

[0024] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program is run by a processor to implement the automatic driving tractor autonomous obstacle avoidance method in any one of the above methods.

[0025] In the embodiment, the integrated unit, if realized in the form of a software functional unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above embodiment methods can be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program is executed by a processor to implement the steps of the above method embodiments. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or some intermediate forms. The computer readable medium at least includes any entity or device capable of carrying the computer program code to the photographing device / terminal equipment, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. For example, a U disk, a mobile hard disk, a magnetic disk or an optical disk, and the like. In some jurisdictions, according to legislation and patent practice, the computer readable medium cannot be an electrical carrier signal and a telecommunications signal.

[0026] In the above embodiments, the description of each embodiment has its own focus, and the parts not described or recorded in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0027] Those skilled in the art can understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to realize the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0028] In the embodiments disclosed in the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely schematic, for example, the division of the modules or units is merely a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0029] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiments of the present application.

[0030] The above formulas are dimensionless values calculated, and the formulas are obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0031] The above describes one embodiment of the present application in detail, but the content described is only the preferred embodiment of the present application, and cannot be considered to limit the scope of the present application. Any equivalent changes and improvements made within the scope of the present application should still belong to the patent coverage of the present application.

Claims

1. A method for autonomous obstacle avoidance of an automatic driving tractor, characterized in that: The following steps are involved: Obtain real-time traffic information data around the tractor during its driving process, identify areas with high traffic volume, and determine a set of selectable paths by searching and combining the total driving time; Based on the set of selectable paths, the historical traffic situation data of the selectable paths is first calculated and processed to obtain the priority value, identify the priority path, and then perform path splicing to obtain the effective splicing path set; Among them, traffic situation data includes traffic congestion data and traffic accident data; Based on the preferred path set and the effective splicing path set, combined with the total travel time, a comparative analysis is performed to obtain the optimal travel path.

2. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of determining the selectable path set is as follows: Obtain several drivable paths for the tractor from its current location to its destination; Divide each drivable path into several calculation segments and obtain the travel time of each calculation segment; The travel time of the calculated road section passing through the high-traffic area is calculated with the risk coefficient to obtain the high travel time, and the travel time of the calculated road section not passing through the high-traffic area is marked as the normal travel time; Calculate all high travel time and normal travel time to get the total travel time of the route; The drivable paths that are less than the total travel time threshold are recorded as selectable paths, and a selectable path set is constructed.

3. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of obtaining the high-traffic area is as follows: Get point cloud density value and point cloud distribution coefficient; The point cloud density value and the point cloud distribution coefficient are calculated and processed to obtain the flow degree assessment value; The analysis area with a flow rate greater than the assessment threshold is marked as a high flow area.

4. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 3, characterized in that: The method for obtaining the point cloud density value and the point cloud distribution coefficient is: Traffic information data includes pedestrian flow data and vehicle flow data; Obtain 3D point cloud data and use point cloud segmentation algorithm to divide the point cloud into different analysis areas; Obtain the number of pedestrian point clouds and vehicle point clouds in each analysis area, calculate the total number of point clouds, and calculate the ratio of the total number of point clouds to the total area of ​​the area to obtain the point cloud density value; The DBSCAN algorithm is used to calculate the silhouette coefficient of each point cloud; The silhouette coefficients of all point clouds are averaged to obtain the point cloud distribution coefficient.

5. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of identifying the preferred path is as follows: Obtain the time period from the current execution time to the end time of each selectable path, mark it as the analysis period, and obtain the traffic information data of each day in the analysis period from the historical data; Get the priority values ​​of all selectable paths and extract the maximum value xd; Set the interval step size c and identify the number of preferred values ​​in the interval [xd-c, xd]; If the number is one, the selectable path corresponding to the maximum value xd is the preferred path; If the number is not one, the corresponding selectable path will be the priority path set.

6. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of obtaining the priority value is as follows: Analyze traffic congestion data and traffic accident data to obtain congestion characterization values, traffic mutation values, and total travel time; The congestion characterization value, traffic mutation value and total travel time are weighted and summed to obtain the priority value.

7. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 6, characterized in that: The process of obtaining the congestion characterization value and traffic mutation value is as follows: Traffic congestion data includes route congestion duration and congestion length; traffic accident data includes the number of traffic accidents and accident handling time; The congestion duration of the paths in the historical data is averaged and compared with the analysis period of the selectable paths to obtain the congestion duration ratio. The congestion lengths in the historical data are averaged and then the ratio of the average value to the total length of the optional routes is calculated to obtain the congestion length ratio. Calculate the congestion duration ratio and the congestion length ratio to obtain a congestion characterization value; The number of traffic accidents in the historical data is summed up and the ratio is calculated with the total number of days in the historical data to obtain the accident frequency value; The accident handling time of traffic accidents in historical data is averaged and compared with the analysis period to obtain the accident handling time ratio; The accident frequency value and the accident handling time ratio are calculated to obtain the traffic mutation value.

8. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of obtaining the effective splicing path is as follows: Obtain the calculated road segment on each preferred route that passes through the high-traffic area, and calculate the distance deviation value of the adjacent preferred routes based on the starting point of the calculated road segment; The selectable paths with a distance deviation less than the threshold are retained and recorded as splicing sections, and then spliced ​​with the original preferred path; Repeated recognition is performed to complete all splicing processes and obtain the splicing path; Obtain all distance deviation values ​​during the splicing operation of each splicing path and sum them up to obtain the total distance deviation value; The splicing paths with a value greater than the total distance deviation are retained, marked as valid paths, and a valid splicing path set is constructed.

9. The autonomous obstacle avoidance method for an automatic driving tractor according to claim 1, characterized in that: The process of obtaining the optimal driving path is as follows: Calculate the total travel time of each valid splicing path and the preferred path; Mark the effective splicing path and the preferred path as paths to be compared; The minimum value of the total travel time among the paths to be compared is extracted, and the path to be compared corresponding to the minimum total travel time is marked as the best travel path.

10. An autonomous obstacle avoidance system for an automatic driving tractor, characterized in that: The system is used to execute the method according to any one of claims 1 to 9, and the system comprises: Optional Path Acquisition Module: This module acquires real-time traffic information data around the tractor during its driving process, identifies areas with high traffic volume, and determines a set of optional paths by searching and combining the total driving time. Priority path acquisition module: Based on the set of selectable paths and the historical traffic situation data of the selectable paths, the module calculates and processes the priority value and identifies the priority path; Among them, traffic information data includes traffic congestion data and traffic accident data; Path splicing module: Based on the preferred path set, path splicing is performed to obtain a valid splicing path; Optimal path selection module: Based on the preferred path set and the effective splicing path set, combined with the total path travel time, the optimal travel path is obtained through analysis.

Images