An automatic driving tractor autonomous obstacle avoidance method and system

Abstract

The present application relates to the technical field of autonomous obstacle avoidance, and discloses an automatic driving tractor autonomous obstacle avoidance method and system, comprising the following steps: acquiring surrounding real-time traffic information data of a tractor driving process, determining a heavy traffic area, and determining a selectable path set by searching in combination with total driving time. The present application can help the tractor to identify and avoid the heavy traffic area in advance with a high probability, reduce the probability of encountering obstacles, and reduce the complexity of obstacle avoidance. By selecting a priority path in combination with historical traffic information, the rationality of path planning is improved, path splicing operation further optimizes the driving path, reduces the road section passing through the heavy traffic area, improves driving safety and efficiency, and the best driving path is determined by comprehensively considering the total driving time, so that the tractor can reach the destination more quickly.

Description

Technical Field

[0001] This invention relates to the field of autonomous obstacle avoidance technology, specifically to an autonomous obstacle avoidance method and system for an autonomous driving tractor. Background Technology

[0002] Autonomous driving tractors are intelligent vehicles that integrate advanced technologies to perform transportation tasks in specific scenarios. They have environmental perception, intelligent decision-making and automatic control capabilities, and are becoming key equipment in the logistics and industrial fields.

[0003] In application scenarios of autonomous driving tractors, such as logistics parks and port terminals, the tractors need to complete cargo transportation tasks in complex traffic environments.

[0004] Existing route planning methods often rely solely on static map information and fail to fully consider real-time traffic conditions. In actual operation, dynamic factors such as traffic flow, congestion, and traffic accidents are constantly changing, which may make the pre-planned route a less than optimal choice, or even cause the tractor to get stuck in congested sections, significantly increasing travel time and reducing transportation efficiency. Summary of the Invention

[0005] The purpose of this invention is to provide an autonomous obstacle avoidance method and system for an autonomous driving tractor, in order to solve the problem that existing path planning methods often rely solely on static map information and fail to fully consider real-time traffic conditions. In actual operation, dynamic factors such as traffic flow, congestion, and traffic accidents are constantly changing, which makes the pre-planned path may not be the optimal choice, and may even cause the tractor to get stuck in congested sections, significantly increasing travel time and reducing transportation efficiency.

[0006] In a first aspect, the present invention provides an autonomous obstacle avoidance method for an automated driving tractor, comprising the following steps:

[0007] The system acquires real-time traffic information data of the surrounding area during the driving process of the tractor-trailer, identifies areas with high traffic volume, and determines a set of selectable routes by searching and combining the total driving time.

[0008] Based on the set of selectable paths, the system first calculates and processes the historical traffic situation data of the selectable paths to obtain the priority selection value, identifies the priority selection path, and then performs path splicing to obtain the effective spliced ​​path set.

[0009] The traffic situation data includes traffic congestion data and traffic accident data;

[0010] The optimal travel route is obtained by comparing and analyzing the preferred route set and the effective route splicing set, combined with the total travel time of the route.

[0011] Secondly, the present invention provides an autonomous obstacle avoidance system for an automated driving tractor, the system comprising:

[0012] Selectable route acquisition module: acquires real-time traffic information data of the surrounding area during the driving process of the tractor, identifies areas with high traffic volume, and determines a set of selectable routes by searching and combining the total driving time;

[0013] Priority route acquisition module: Based on the set of selectable routes, and combined with historical traffic situation data of selectable routes, it calculates and processes to obtain priority values ​​and identifies priority routes;

[0014] The traffic information data includes traffic congestion data and traffic accident data;

[0015] Path splicing module: Based on a prioritized set of paths, it splices paths to obtain valid spliced ​​paths;

[0016] Optimal route selection module: Based on the set of preferred routes and the set of effective spliced ​​routes, and combined with the total travel time of the route, the optimal travel route is obtained.

[0017] The beneficial effects of this invention are:

[0018] This invention helps tractor units identify and avoid high-traffic areas in advance, reducing the probability of encountering obstacles and simplifying obstacle avoidance. By combining historical traffic information to select priority paths, it improves the rationality of path planning. The path splicing operation further optimizes the driving path, reduces the number of sections passing through high-traffic areas, and improves driving safety and efficiency. By comprehensively considering the total travel time, it determines the optimal driving path, enabling tractor units to reach their destination more quickly. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0020] Figure 1 This is a flowchart of an autonomous obstacle avoidance method for an automated driving tractor according to the present invention;

[0021] Figure 2 This is a schematic diagram of the structure of an autonomous obstacle avoidance system for an automated driving tractor according to the present invention;

[0022] Figure 3 This is a structural schematic diagram of an autonomous obstacle avoidance device for an autonomous driving tractor according to the present invention.

[0023] In the diagram: 3. Computer equipment; 301. Processor; 302. Memory; 303. Computer program; Detailed Implementation

[0024] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0025] Example 1

[0026] Figure 1 This is a flowchart illustrating an autonomous obstacle avoidance method for an automated driving tractor provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where autonomous obstacle avoidance selects a path with superior obstacle avoidance performance. This autonomous obstacle avoidance method for an automated driving tractor can be executed by an autonomous obstacle avoidance system for an automated driving tractor. This system can be implemented using software and / or hardware and can be configured within an autonomous obstacle avoidance device for an automated driving tractor. Optionally, the autonomous obstacle avoidance device for an automated driving tractor can be an electronic device, such as a laptop, desktop computer, or smart tablet, etc. This embodiment of the present invention does not impose any limitations on this.

[0027] An embodiment of the present invention provides an autonomous obstacle avoidance method for an automated driving tractor, which specifically includes the following steps:

[0028] Step 1: During the autonomous driving process, the tractor acquires and analyzes real-time traffic information data from the surrounding area to search and determine a set of selectable paths.

[0029] The traffic information data includes pedestrian flow data and vehicle flow data;

[0030] In some embodiments, sensors are installed at different locations on the tractor, wherein the sensors include, but are not limited to, lidar;

[0031] Set a monitoring period, process the 3D point cloud data generated by the lidar, use a point cloud segmentation algorithm to divide the point cloud into different analysis areas, obtain the pedestrian and vehicle traffic based on the density and distribution of the point cloud in each area, and identify areas with high traffic and low traffic.

[0032] It needs to be explained that the reason for identifying high-traffic and low-traffic areas is that high-traffic areas mean there are more pedestrians and vehicles, which are potential obstacles for the towing vehicle. When planning the route, the towing vehicle can prioritize low-traffic areas and try to avoid high-traffic areas, thereby reducing the probability of encountering obstacles and reducing the complexity of obstacle avoidance. In high-traffic areas, the movement of pedestrians and vehicles may be more complex and disorderly, and the towing vehicle needs to consider more factors to make obstacle avoidance decisions. Therefore, identifying high-traffic areas before route planning and avoiding these areas during route planning can reduce the difficulty for the towing vehicle to perform autonomous obstacle avoidance.

[0033] Based on any analysis region, the point cloud counts of pedestrians and vehicles are obtained separately, and then summed to obtain the total point cloud count. The point cloud density value is obtained by calculating the ratio of the total point cloud count to the total area of ​​the region.

[0034] The point cloud distribution coefficients are calculated using the DBSCAN algorithm. The specific process is as follows:

[0035] Set the neighborhood radius and minimum number of points. For all point clouds in the analysis area, check if the number of points within its neighborhood radius is greater than or equal to the minimum number of points. If so, the point is a core point and forms a cluster with the points in its neighborhood. If the number of points in a point's neighborhood is less than the minimum number of points, but it intersects with the neighborhood of a core point, then the point is a boundary point and belongs to the cluster of the core point. Otherwise, it is a noise point.

[0036] For each point cloud i, calculate its average distance Ai with other point clouds in the same cluster, and its average distance Bi with all point clouds in other clusters, and substitute these values ​​into the formula. The profile coefficient Si is calculated.

[0037] It should be explained that max{Ai, Bi} means taking the maximum value between Ai and Bi. When Si is close to 1, it indicates that the point cloud is very compact within its own cluster and is well separated from other clusters. When Si is close to -1, it means that the point cloud may be incorrectly clustered. When Si is close to 0, it indicates that the point cloud is at the cluster boundary.

[0038] The summation and average of the contour coefficients of all point clouds are obtained as the point cloud distribution coefficient.

[0039] The point cloud density value and the point cloud distribution coefficient are multiplied to obtain the flow rate assessment value;

[0040] Set a flow rate assessment threshold. The analysis area corresponding to the flow rate assessment value that is greater than the flow rate assessment threshold is marked as a high flow rate area, and the analysis area corresponding to the flow rate assessment value that is less than or equal to the flow rate assessment threshold is marked as a low flow rate area.

[0041] Obtain a high-precision map containing the area where the tractor is traveling, including but not limited to: the topology of the roads;

[0042] The identified high-traffic areas are integrated with high-precision maps to clarify the specific location and extent of these areas on the map.

[0043] Using Dijkstra's algorithm, the search for alternative paths is as follows:

[0044] Set the current position of the tractor as the starting point and the destination as the target point, and obtain several drivable paths;

[0045] Based on any drivable path, it is divided into several calculation segments, and the travel time of each calculation segment is obtained.

[0046] It should be noted that the driving time was set by those skilled in the art based on historical driving speeds;

[0047] The high travel time is calculated by multiplying the travel time of the calculated road segment that passes through the high traffic area with the risk coefficient, and the travel time of the calculated road segment that does not pass through the high traffic area is marked as the normal travel time.

[0048] The risk coefficient is a value greater than 1, which is set by those skilled in the art based on the specific characteristics of areas with high traffic volume and in combination with historical driving speeds. The value is chosen to reflect that the travel time will increase due to the large flow of pedestrians or vehicles in the calculated road segment.

[0049] Sum all the high travel times and normal travel times to get the total travel time for the route;

[0050] Set a route travel time threshold, retain the drivable routes with travel times less than the threshold and mark them as selectable routes, and mark the remaining drivable routes as unselectable routes.

[0051] Retrieve all selectable paths and mark them as a set of selectable paths;

[0052] Step 2: Based on the set of selectable routes and combined with historical traffic data of the selectable routes, identify the preferred routes;

[0053] In some embodiments, a set of selectable paths is obtained based on any one of the selectable paths;

[0054] Based on the current travel time, the travel end time is calculated by summing it with the total travel time of the route. The period from the current travel time to the travel end time is marked as the analysis period, and traffic situation data for each day in the analysis period is obtained from historical data.

[0055] The traffic situation data includes traffic congestion data and traffic accident data;

[0056] Traffic congestion data includes route congestion duration and congestion length; traffic accident data includes the number of traffic accidents and accident processing time.

[0057] The average path congestion duration is obtained by summing and averaging the path congestion durations in historical data. The average path congestion duration is then compared with the analysis period of the selectable paths to obtain the congestion duration percentage.

[0058] The average path congestion length is obtained by summing and averaging the path congestion lengths in the historical data. The average path congestion length is then compared with the total travel path length of the selectable paths to obtain the congestion length percentage.

[0059] The congestion characterization value is obtained by multiplying the congestion duration percentage value with the congestion length percentage value.

[0060] The purpose of calculating congestion characterization values ​​is threefold: firstly, to intuitively and comprehensively reflect the severity of congestion on a given alternative route during a specific analysis period; secondly, to improve the accuracy and rationality of route planning by using congestion characterization values ​​as an important quantitative indicator in the process of identifying preferred routes; and thirdly, to allow the tractor to plan routes that avoid congested sections in advance based on the calculated congestion characterization values ​​and other traffic information during autonomous driving.

[0061] The total number of traffic accidents is obtained by summing the number of traffic accidents in the historical data. The accident frequency value is obtained by calculating the ratio of the total number of accidents to the total number of days in the historical data.

[0062] The average accident handling time is obtained by summing and averaging the accident handling times in historical data. The average accident handling time is then compared with the analysis period to obtain the accident handling time percentage.

[0063] The traffic mutation value is obtained by multiplying the accident frequency value with the accident handling time ratio value.

[0064] The purpose of calculating traffic mutation is threefold: firstly, to quantify the impact of traffic accidents on traffic conditions, intuitively reflecting the degree to which a route is affected by traffic accidents within a specific time period; secondly, to use the traffic mutation value as an important indicator in the calculation of priority selection values ​​when determining priority routes; and thirdly, to select routes with lower traffic mutation values, which means that the risk of the tractor unit encountering traffic accidents during its journey is relatively low, effectively reducing situations such as stopping and detours caused by traffic accidents.

[0065] The priority selection value is obtained by weighted summation of congestion indicator value, traffic change value and total travel time;

[0066] Obtain the priority value of all selectable paths, extract the maximum value xd, and take it as the maximum priority value.

[0067] Set the interval step size c, and identify the number of preferred values ​​within the interval [xd-c, xd].

[0068] Among them, the interval step size c is used to determine whether there is a value close to the maximum value xd in the priority selection corresponding to the selectable path. The interval step size c is set by the implementer in this field according to the characteristics of the data.

[0069] If the quantity 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 preferred path.

[0070] If the number is not one, it means that there is a value close to the maximum value xd, and the corresponding selectable path is marked as the set of preferred paths;

[0071] The technical solution of this embodiment is as follows: During the autonomous driving process, the tractor acquires real-time traffic information data through sensors, identifies areas with high traffic volume using point cloud data processing technology, searches for drivable paths using the Dijkstra algorithm in conjunction with a high-precision map, calculates the total travel time of the path based on the travel time and risk coefficient of the road segment passing through the high traffic volume area, sets a threshold to determine the set of selectable paths, and calculates the congestion characterization value, traffic change value, etc. based on the set of selectable paths in conjunction with historical traffic information data to obtain the priority selection value, and then identifies the priority selection path.

[0072] The effects of this implementation are as follows: Firstly, when planning the path, the tractor can avoid areas with high potential pedestrian and vehicle movement in advance, reducing the probability of encountering obstacles, reducing the complexity of obstacle avoidance decisions, and significantly improving the safety and reliability of obstacle avoidance.

[0073] Secondly, by combining real-time traffic data and high-precision maps, the Dijkstra algorithm is used to search for drivable routes. The travel time and risk coefficient of road segments passing through high-traffic areas are calculated, and the total travel time of the route is comprehensively calculated. Thresholds are set to filter out the set of selectable routes. The traffic conditions of different road segments are taken into account, making the planned routes more reasonable, reducing travel in congested or dangerous areas, and improving travel efficiency.

[0074] Thirdly, based on the set of selectable routes, the analysis period is determined according to the current travel time. Historical traffic information data for this period is obtained. By calculating congestion characterization values, traffic change values, etc., and performing weighted summation, a priority selection value is obtained, and priority routes are identified. The evaluation method of historical data takes into account the traffic risks of different routes in similar time periods, which improves the scientificity and accuracy of route selection and improves the smoothness of travel.

[0075] Example 2

[0076] Based on the above embodiments, such as Figure 1 As shown in the figure, an autonomous obstacle avoidance method for an automated driving tractor provided by an embodiment of the present invention specifically includes the following steps:

[0077] Step 3: Based on the preferred path set, perform path concatenation to obtain an effective concatenated path;

[0078] In some embodiments, a set of preferred paths is obtained based on any one of the preferred paths;

[0079] Obtain the calculation segment on the preferred path that passes through the area with high traffic volume, and calculate the distance deviation value of the adjacent preferred path based on the starting point of the calculation segment;

[0080] The methods for calculating distance deviation include, but are not limited to, the Euclidean distance formula;

[0081] It should be noted that when calculating the distance deviation value of the adjacent preferred path, the path of the corresponding small traffic area should be selected;

[0082] Set a distance deviation threshold, retain the selectable paths corresponding to distance deviation values ​​less than the distance deviation threshold as splicing segments, and splice them with the original preferred paths;

[0083] Perform duplicate identification, complete all possible splicing processes, and obtain the splicing path;

[0084] It should be noted that if there are multiple matching distance deviation values, the minimum value will be taken.

[0085] Based on any splicing path, obtain all distance deviation values ​​during its splicing operation, and sum them to obtain the total distance deviation value;

[0086] Set a total distance deviation threshold, retain the splicing paths corresponding to the total distance deviation values ​​that are greater than the total distance deviation threshold, mark them as valid paths, and mark the remaining splicing paths as invalid paths;

[0087] Retrieve all valid concatenation paths and mark them as a set of valid concatenation paths;

[0088] The purpose of the above-mentioned path splicing is as follows: the priority path may contain some areas with high traffic volume, which have a large number of pedestrians and vehicles, increasing the difficulty of obstacle avoidance for the towing vehicle. By splicing the road segments that pass through high traffic volume areas in the original priority path with adjacent roads that pass through low traffic volume areas, the road segments that pass through high traffic volume areas can be effectively avoided or reduced, thereby reducing the probability of the towing vehicle encountering obstacles, reducing the complexity of obstacle avoidance, and improving driving safety and efficiency.

[0089] During the path splicing process, factors such as distance deviation value and total distance deviation value were comprehensively considered to select effective splicing paths. These effective splicing paths are smoother during the journey, reduce unnecessary detours, optimize travel time, and enable the tractor to reach the destination more quickly.

[0090] Step 4: Based on the preferred path set and the effective spliced ​​path set, and combined with the total travel time of the path, analyze to obtain the optimal travel path;

[0091] In some embodiments, a set of valid splicing paths is obtained, based on any one of the valid splicing paths;

[0092] Calculate the total travel time of the valid spliced ​​path and obtain the total travel time of the preferred path;

[0093] It should be noted that the total travel time of the spliced ​​path is calculated in the same way as in step one, and will not be repeated here.

[0094] Extract the corresponding paths from the set of valid splicing paths and the set of preferred paths, and mark them as paths to be compared;

[0095] Extract the minimum total travel time among the paths to be compared, and mark the path to be compared corresponding to the minimum total travel time as the best travel path;

[0096] The reason for minimizing the total travel time of the corresponding paths in the effective splicing path set and the preferred path set is that: a longer travel time means that the tractor spends more time on the road, which increases the possibility of encountering obstacles and raises the risk of obstacle avoidance. The path with the shortest total travel time can reduce the time spent in complex traffic environments and reduce the probability of encountering sudden traffic situations.

[0097] The technical solution of this embodiment is as follows: obtain a set of preferred paths, calculate the distance deviation between the calculated road segment passing through the high traffic area and the adjacent preferred paths, set a threshold for path splicing, then filter out the effective spliced ​​paths according to the total distance deviation, and finally combine the total travel time of the preferred path set and the effective spliced ​​path set to select the path corresponding to the minimum value as the best travel path.

[0098] The effect of this embodiment is that, firstly, for areas with high traffic volume that may exist in the priority selection path, by calculating the distance deviation value, the road segment passing through the high traffic volume area is spliced ​​with the adjacent path of the low traffic volume area, reducing the road segment passing through the high traffic volume area, reducing the probability of the tractor encountering obstacles, reducing the complexity of the obstacle avoidance process, and improving driving safety.

[0099] Secondly, during the path splicing process, a distance deviation threshold and a total distance deviation threshold are set to filter the spliced ​​paths and retain the valid spliced ​​paths. The valid spliced ​​paths are smoother during the journey, reduce unnecessary detours, optimize the travel time, enable the tractor to reach the destination more quickly, and improve the overall travel efficiency.

[0100] Thirdly, based on the preferred path set and the effective splicing path set, the total travel time of each path is calculated. By comparing and extracting the path corresponding to the minimum value as the best travel path, from a global perspective, the travel time under different path planning methods is comprehensively considered, so that the path selected by the tractor is the optimal one under the current traffic conditions, further improving the driving performance.

[0101] Example 3

[0102] Based on the above embodiments, such as Figure 2 As shown in the figure, an autonomous obstacle avoidance system for an automated driving tractor provided in this embodiment of the invention specifically includes:

[0103] Selectable Path Acquisition Module: During the autonomous driving process, the tractor acquires real-time traffic information data of the surrounding area, analyzes it, and searches to determine a set of selectable paths;

[0104] The traffic information data includes pedestrian flow data and vehicle flow data;

[0105] Priority route acquisition module: Based on the set of selectable routes and combined with historical traffic information data of selectable routes, it identifies the priority route;

[0106] Path splicing module: Based on a set of preferred paths, it splices paths to obtain the spliced ​​path;

[0107] Optimal route selection module: Based on the set of selectable routes and the set of spliced ​​routes, and combined with the total travel time of the route, the optimal travel route is obtained through analysis.

[0108] Example 4

[0109] like Figure 3 As shown, this embodiment of the invention also provides a computer device 3, including: 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, it implements an autonomous obstacle avoidance method for an automated driving tractor as described in any of the above methods.

[0110] The computer device 3 may be a desktop computer, laptop, handheld computer, or cloud server, etc. The computer device 3 may include, but is not limited to, a processor 301 and a memory 302. Those skilled in the art will understand that...

[0111] Figure 3 The computer device 3 is merely an example and does not constitute a limitation on the computer device 3. It may include more or fewer components than shown in the figure, or combine certain components, or different components, such as input / output devices, network access devices, etc.

[0112] The processor 301 may be a Central Processing Unit (CPU), or it may be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0113] In some embodiments, the memory 302 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 302 may be an external storage device of the computer device 3, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc., equipped on the computer device 3. Furthermore, the memory 302 may include both internal and external storage units of the computer device 3. The memory 302 is used to store the operating system, applications, bootloader, data, and other programs, such as the program code of the computer program. The memory 302 can also be used to temporarily store data that has been output or will be output.

[0114] Example 5

[0115] This invention also provides a computer-readable storage medium storing a computer program thereon, which, when executed by a processor, implements an autonomous obstacle avoidance method for an automated driving tractor as described in any of the above methods.

[0116] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include at least: any entity or device capable of carrying computer program code to a photographing device / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electrical carrier signal, a telecommunication signal, and a software distribution medium. Examples include USB flash drives, portable hard drives, magnetic disks, or optical disks. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electrical carrier signals or telecommunication signals.

[0117] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0118] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0119] In the embodiments disclosed in this application, it should be understood that the disclosed apparatus / terminal devices and methods can be implemented in other ways. For example, the apparatus / terminal device embodiments described above are merely illustrative. For instance, the division of modules or units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed.

[0120] Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0121] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0122] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0123] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. An automatic driving tractor autonomous obstacle avoidance method, characterized in that, The method comprises the following steps: obtaining surrounding real-time traffic information data of a tractor driving process, determining a heavy traffic area, and determining a selectable path set by searching combined with total travel time; based on the selectable path set, first calculating and processing historical traffic situation data of the selectable path to obtain a priority selection value, identifying a priority selection path, and then performing path splicing to obtain an effective spliced path set; wherein the traffic situation data comprises traffic congestion data and traffic accident data; the effective spliced path obtaining process is as follows: obtaining a calculation section passing through the heavy traffic area on each priority selection path, and calculating a distance deviation value of the adjacent priority selection path based on the starting point of the calculation section; retaining the selectable path with a distance deviation value less than a distance deviation threshold value, and marking the path as a spliced section and splicing the original priority selection path; performing repeated identification to complete the splicing process and obtain a spliced path; obtaining all distance deviation values in the splicing operation process of each spliced path, and summing the distance deviation values to obtain a total distance deviation value; setting a total distance deviation threshold value, retaining the spliced path corresponding to the total distance deviation value greater than the total distance deviation threshold value, marking the path as an effective path, and constructing an effective spliced path set; comparing and analyzing the priority selection path set and the effective spliced path set combined with the total path travel time to obtain the best travel path.

2. The autonomous obstacle avoidance method for an autonomous tractor of claim 1, wherein, The process of determining the selectable path set is as follows: obtaining several drivable paths from the current position to the destination of the tractor; dividing each drivable path into several calculation sections, and obtaining the travel time of each calculation section; calculating the travel time of the calculation section passing through the heavy traffic area with the risk coefficient to obtain a high travel time, and marking the travel time of the calculation section not passing through the heavy traffic area as a normal travel time; calculating all high travel times and normal travel times to obtain a total path travel time; retaining the drivable path with a total path travel time less than a total path travel time threshold value as a selectable path, and constructing a selectable path set.

3. The autonomous obstacle avoidance method for an autonomous towing vehicle according to claim 1, wherein, The process of obtaining the heavy traffic area is as follows: obtaining a point cloud density value and a point cloud distribution coefficient; calculating and processing the point cloud density value and the point cloud distribution coefficient to obtain a traffic degree evaluation value; marking an analysis area with a traffic degree evaluation value greater than a traffic degree evaluation threshold value as a heavy traffic area.

4. The autonomous obstacle avoidance method for an autonomous towing vehicle according to claim 3, wherein, The method of obtaining the point cloud density value and the point cloud distribution coefficient is as follows: the traffic information data comprises pedestrian flow data and vehicle flow data; obtaining three-dimensional point cloud data, and dividing the point cloud into different analysis areas by using a point cloud segmentation algorithm; obtaining the point cloud quantity of pedestrians and the point cloud quantity of vehicles in each analysis area, calculating a total point cloud quantity, and calculating the total point cloud quantity and the total area of the region by ratio to obtain a point cloud density value; calculating the contour coefficient of each point cloud by using a DBSCAN algorithm; performing mean value processing on the contour coefficients of all point clouds to obtain a point cloud distribution coefficient.

5. The autonomous obstacle avoidance method for an autonomous tractor of claim 1, wherein, The process of identifying the priority selection path is as follows: obtaining a time period from the current travel time to the end of travel of each selectable path, marking the time period as an analysis time period, and obtaining traffic information data in the analysis time period each day in the historical data; obtaining the priority selection values of all selectable paths, and extracting the maximum value xd; An interval step c is set, and the number of the priority selection values in the interval [xd-c, xd] is identified; If the number is one, the maximum value xd corresponds to the priority selection path; If the number is not one, the corresponding selectable path is the priority selection path set.

6. The autonomous obstacle avoidance method for an autonomous towing vehicle according to claim 1, wherein, The priority selection value acquisition process is: The traffic congestion data and the traffic accident data are analyzed to obtain the congestion characteristic value, the traffic mutation value, and the total travel time; The congestion characteristic value, the traffic mutation value, and the total travel time are weighted and summed to obtain the priority selection value.

7. The autonomous obstacle avoidance method for an autonomous towing vehicle according to claim 6, wherein, The congestion characteristic value and the traffic mutation value acquisition process is: The traffic congestion data includes the path congestion duration and the congestion length, and the traffic accident data includes the number of traffic accidents and the accident handling duration; The path congestion duration in the historical data is processed by mean value, and the analysis period of the selectable path is processed by ratio to obtain the congestion duration ratio value; The path congestion length in the historical data is processed by mean value, and the total path length of the selectable path is processed by ratio to obtain the congestion length ratio value; The congestion duration ratio value and the congestion length ratio value are calculated to obtain the congestion characteristic value; The number of traffic accidents in the historical data is summed, and the total number of days in the historical data is calculated by ratio to obtain the accident frequency value; The accident handling duration of the traffic accident in the historical data is processed by mean value, and the analysis period is processed by ratio to obtain the accident handling duration ratio value; The accident frequency value and the accident handling duration ratio value are calculated to obtain the traffic mutation value.

8. The autonomous obstacle avoidance method for an autonomous towing vehicle according to claim 1, wherein, The best travel path acquisition process is: The path total travel time of each effective splicing path and the priority selection path is calculated; The effective splicing path and the priority selection path are marked as paths to be compared; The minimum value of the path total travel time in the path to be compared is extracted, and the path to be compared corresponding to the minimum value of the path total travel time is marked as the best travel path.

9. An autonomous obstacle avoidance system for an autonomous tractor, the system comprising: The system is used to execute the method of any one of claims 1-8, and the system comprises: The selectable path acquisition module: acquires the surrounding real-time traffic information data of the tractor driving process, determines the large flow area, and determines the selectable path set by searching and combining the total travel time; The priority selection path acquisition module: based on the selectable path set, combines the historical traffic situation data of the selectable path to obtain the priority selection value, and identifies the 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 the effective splicing path; The best path selection module: according to the priority selection path set and the effective splicing path set, combines the path total travel time to analyze and obtain the best travel path.

Images