An autonomous obstacle avoidance method for unmanned vehicles used in ports and mines

By obtaining and binding the planning information of the driverless car, performing path rehearsals and three-dimensional model marking, analyzing obstacle avoidance risks, and optimizing motion characteristic information, the problem of obstacle avoidance risk assessment and control of driverless car in the application scenarios of port and mines is solved. , achieving safe and efficient vehicle transportation.

CN118484009BActive Publication Date: 2024-11-08JIANGSU DALUOTOU ZHIJIA TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410939466.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-15
Publication Date
2024-11-08
Estimated Expiration
2044-07-15

AI Technical Summary

Technical Problem

In the application scenarios of port and mines, the obstacle avoidance risks of driverless cars in the surrounding environment of the transport area have not been effectively evaluated and controlled, resulting in congestion and safety hazards.

Method used

By obtaining and binding the number and planning path of the driverless car, a vehicle planning information set is generated, motion feature information is obtained in real time, path information previews are performed, three-dimensional model marks the intersection area, analyze obstacle avoidance risks, and lock in related obstacle avoidance points. And optimize the motion feature information for control.

Benefits of technology

Rehearsal and environmental information assessment of the transport area are realized, related obstacle avoidance points are locked, vehicle motion characteristics information is optimized, and driverless cars are effectively avoided and safe transportation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118484009B_ABST
    Figure CN118484009B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of unmanned driving technology, and specifically to an autonomous obstacle avoidance method for unmanned vehicles used in ports and mines, including constructing a three-dimensional model of the unmanned vehicle on a planned path, and marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle; analyzing the obstacle avoidance risk assessment value of each intersection area compared to the surrounding environment, and locking the associated obstacle avoidance points corresponding to each intersection area. In the process of performing obstacle avoidance control on the unmanned vehicle, the present invention realizes a preview of the merging area, and analyzes the environmental information around the previewed merging area to evaluate the obstacle avoidance risks existing in the vehicle merging process, locks the associated obstacle avoidance points in the merging area, and optimizes the vehicle's motion characteristic information, thereby realizing effective control of the unmanned vehicle.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the field of unmanned driving technology, and in particular to an autonomous obstacle avoidance method for an unmanned driving vehicle used in a port mine. Background Art

[0002] With the rapid development of unmanned driving technology, the application areas of unmanned vehicles are becoming more and more extensive. In the field of port and mining applications, a large number of vehicles are needed for the loading and unloading and transportation of goods, and there are high requirements for the transportation efficiency and safety of unmanned vehicles.

[0003] However, autonomous driving technology also faces some challenges, one of which is how to control the driverless car to avoid obstacles effectively. Traditional collision warning methods usually judge whether there is a collision risk based on the distance between vehicles. However, in port and mining application scenarios, due to the large number of vehicles and the high overlap of transportation routes, vehicles often merge. Traditional technologies do not take into account the impact of the environment around the merging area on the merging results in actual transportation scenarios, resulting in congestion caused by the inability to merge. Therefore, the existing technology has major defects. Summary of the invention

[0004] The purpose of the present invention is to provide an autonomous obstacle avoidance method for an unmanned vehicle used in ports and mines, so as to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an autonomous obstacle avoidance method for an unmanned vehicle used in a port mine, the method comprising the following steps:

[0006] S100, obtaining the serial number of each unmanned vehicle entered into the port and mining vehicle command center and the planned path corresponding to each unmanned vehicle, and generating a port and mining vehicle planning information set;

[0007] S200, obtaining in real time the motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, and performing a path information preview for each unmanned vehicle in combination with the port and mine vehicle planning information set, and generating each vehicle intersection area corresponding to each unmanned vehicle and other unmanned vehicles;

[0008] S300, constructing a three-dimensional model of the unmanned vehicle on the planned path, and marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle; analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment, and locking the associated obstacle avoidance point corresponding to each intersection area;

[0009] S400, combining the positions of the associated obstacle avoidance points corresponding to each unmanned vehicle and the motion characteristic information in the corresponding planned path, optimizing the motion characteristic information of the corresponding unmanned vehicle in each planned path section, and uploading it to the port and mining vehicle control terminal;

[0010] S500, the port and mining vehicle control terminal controls the travel status of the corresponding unmanned vehicle according to the optimized motion feature information, and when the distance between adjacent unmanned vehicles is less than a preset value, controls the image acquisition devices on the adjacent unmanned vehicles to remain turned on, generates an adjacent vehicle image acquisition group, and feeds back to the front-end display page.

[0011] Furthermore, when the numbers of the unmanned vehicles and the planned paths corresponding to the unmanned vehicles entered into the port and mining vehicle command center are obtained in S100, the unmanned vehicle numbers are bound to the planned paths corresponding to the corresponding unmanned vehicles to obtain the vehicle planning information pairs corresponding to the corresponding unmanned vehicles.

[0012] Each element in the port and mine vehicle planning information set corresponds to a vehicle planning information pair;

[0013] The planned paths corresponding to the driverless vehicles are preset in a database, and the planned paths corresponding to different driverless vehicles partially overlap.

[0014] Further, the S200 includes the following steps:

[0015] S201, real-time acquisition of motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, wherein the motion characteristic information includes the position, forward direction and historical speed fluctuation range of the current unmanned vehicle in the planned path,

[0016] The forward direction is the direction from the starting point to the end point of the corresponding unmanned vehicle in the planned path; the historical speed fluctuation interval represents the interval formed by the average speed of the corresponding unmanned vehicle from the starting point to the current position in the planned path and the instantaneous speed corresponding to the current position;

[0017] S202, obtaining a port and mine vehicle planning information set, treating two unmanned vehicles with intersection sections in corresponding planning paths in the port and mine vehicle planning information set as an analysis combination pair, and binding each corresponding intersection section with the analysis combination pair, which is recorded as a first binding result;

[0018] S203, performing path information preview for the two driverless vehicles corresponding to the first binding result;

[0019] During the preview process, the path interval time interval corresponding to the first unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T1; the path interval time interval corresponding to the second unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T2; the intersection of T1 and T2 is recorded as the time interval preview interval; the intersection of the preview sections corresponding to the two unmanned vehicles in the first binding result in the time interval preview interval is recorded as the intersection dynamic preview section;

[0020] The path information preview result includes a time interval preview section and a dynamic intersection preview section.

[0021] The minimum value in the path interval time interval is equal to the quotient of the shortest distance between the corresponding intersection section and the current position divided by the maximum value in the corresponding historical speed fluctuation interval; the maximum value in the path interval time interval is equal to the quotient of the longest distance between the corresponding intersection section and the current position divided by the minimum value in the corresponding historical speed fluctuation interval;

[0022] The preview section corresponding to the unmanned vehicle in the time interval preview interval in the first binding result is equal to the path section in the path planned by the corresponding unmanned vehicle, where the distance between the corresponding unmanned vehicle and the current position along the forward direction of the corresponding unmanned vehicle is greater than the first determination distance and less than the second determination distance;

[0023] The first determination distance is equal to the product of the minimum value of the unmanned vehicle in the time interval preview interval in the first binding result and the minimum value in the corresponding historical speed fluctuation interval; the second determination distance is equal to the product of the maximum value of the unmanned vehicle in the time interval preview interval in the first binding result and the maximum value in the corresponding historical speed fluctuation interval;

[0024] S204: Use the intersection dynamic preview section in the path information preview result corresponding to the first binding result as a subset of the intersection areas corresponding to the two driverless vehicles corresponding to the first binding result.

[0025] When the present invention obtains the intersection dynamic preview section in the path information preview result, it is considered that the motion state of the unmanned vehicle may fluctuate, which will affect the preview result of the intersection point. Therefore, the preview result of the merging vehicle is a corresponding area rather than a specific location point. At the same time, it also provides data support for analyzing the associated obstacle avoidance points in the intersection area in subsequent steps.

[0026] Further, when marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle in S300, the planned path of each unmanned vehicle and the environment at a first unit distance from the planned path are scanned by a three-dimensional scanner to generate a three-dimensional model of the unmanned vehicle on the planned path;

[0027] When analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment in S300, a three-dimensional model of the unmanned vehicle on the planned path and a marking result of each intersection area in the corresponding three-dimensional model are obtained;

[0028] Obtaining the positions of the intersection areas of the same unmanned vehicle and the different marked intersection areas corresponding to different unmanned vehicles, determining that different intersection areas whose shortest distance between the corresponding intersection areas is less than a first preset distance are associated, and regionally merging the associated intersection areas, replacing the original associated intersection areas with the fused intersection areas;

[0029] The present invention considers the fusion of intersection areas because adjacent closely adjacent intersection areas may cause a vehicle to frequently merge with other vehicles, thereby increasing the risk of merging with other vehicles; and realizing the fusion of intersection areas can effectively reduce the frequency of vehicles merging with other vehicles and ensure the safety of merging with other vehicles.

[0030] The fused intersection area is equal to the intersection of the intersection results of the intersection sections to which the corresponding associated intersection areas belong and the fused feature area, and the fused feature area is the road section area composed of the corresponding associated intersection areas and the unmarked areas therebetween;

[0031] Calculate the obstacle avoidance risk assessment value of each intersection area compared to the surrounding environment, and record the obstacle avoidance risk assessment value of the i-th intersection area compared to the surrounding environment as Pi;

[0032] Pi=FHi / FUi,

[0033] Record the road interference value in a circular area with any position point as the center and a second unit distance as the radius in the i-th intersection area as the environmental risk value of the corresponding position point, wherein the second unit distance is less than the first unit distance and the first unit distance and the second unit distance are both constants preset in the database;

[0034] Among them, FHi represents the maximum value of the environmental risk values ​​corresponding to each location point in the i-th intersection area;

[0035] FUi represents the maximum value of the environmental risk values ​​corresponding to each location point in the intersection section corresponding to the i-th intersection area;

[0036] The road interference value in the circular area with any position point as the center and the second unit distance as the radius is recorded as D.

[0037] D = Z + β·LC / XC;

[0038] Z represents the ratio of the road pothole area in the corresponding circular area to the total area;

[0039] LC represents the vehicle width of the driverless car;

[0040] XC represents the effective convergence width of the road in the direction perpendicular to the central axis of the path in the corresponding circular area;

[0041] The intersection points of the diameter of the corresponding circular area perpendicular to the central axis of the path and the contour of the circular area are respectively recorded as obstacle points, and each obstacle point in the corresponding area of ​​each obstacle in the corresponding circular area is obtained. Each obstacle point in the corresponding circular area is mapped in a direction perpendicular to the central axis of the path, and the maximum value of the distance between any two adjacent points after mapping is recorded as XC; the obstacle corresponding area is collected and set in advance in the database.

[0042] When analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment, the present invention takes into account the proportion of road potholes (road surface flatness), vehicle width and effective merging width of the road, thereby achieving effective quantification of merging risks.

[0043] Furthermore, when the associated obstacle avoidance point corresponding to each intersection area is locked in S300,

[0044] Obtain feature information of the i-th intersection area, recorded as Ei, the first parameter in Ei is the position point corresponding to FHi, the second parameter in Ei is the position point corresponding to FUi, and the third parameter in Ei is Pi;

[0045] Constructing each initial associated obstacle avoidance point combination corresponding to the intersection area, each element in each initial associated obstacle avoidance point combination corresponds to an intersection area, and each element in the obtained initial associated obstacle avoidance point combination is one of the first parameter and the second parameter in the feature information of the corresponding intersection area;

[0046] Filter the initial associated obstacle avoidance point combination with the smallest corresponding associated deviation, and use each element in the selected initial associated obstacle avoidance point combination as the associated obstacle avoidance point of the corresponding intersection area;

[0047] The associated deviation of the initial associated obstacle avoidance point combination is recorded as G,

[0048] ,

[0049] Wherein, k1 represents the total number of elements in the corresponding initial associated obstacle avoidance point combination; g represents the first coefficient and g is a constant preset in the database;

[0050] LPk represents the distance between the second parameter and the first parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs;

[0051] PWk represents the third parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs.

[0052] When locking the associated obstacle avoidance points corresponding to each intersection area, the present invention first constructs each initial associated obstacle avoidance point combination, and screens the initial associated obstacle avoidance point combinations according to the associated deviations corresponding to different initial associated obstacle avoidance point combinations, thereby generating associated obstacle avoidance points corresponding to each intersection area.

[0053] Furthermore, when optimizing the motion characteristic information of the corresponding unmanned vehicle in each planned path segment, the S400 optimizes the motion characteristic information in the planned path segment between the current position of the unmanned vehicle and the nearest intersection area in the same direction as the unmanned vehicle's forward movement in real time;

[0054] Obtain the associated obstacle avoidance point corresponding to the corresponding intersection area; obtain the median of the time interval preview interval in the path information preview result where the corresponding intersection dynamic preview section and the corresponding intersection area intersect, and record it as the first movement duration.

[0055] The length of the planned path from the current position of the unmanned vehicle to the nearest intersection area in the same direction as the unmanned vehicle is recorded as the first movement distance;

[0056] In the result after optimizing the motion feature information in the corresponding planned path section, the current position and forward direction of the driverless vehicle in the planned path remain unchanged, and the corresponding historical speed fluctuation range is changed to the quotient of the first motion distance and the first motion duration.

[0057] Furthermore, when the S500 Zhonggang Mine Vehicle Control Terminal controls the travel status of the corresponding unmanned vehicle according to the optimized motion feature information, each unmanned vehicle obtains the distance between itself and the surrounding unmanned vehicles in real time; each time the unmanned vehicle completes a vehicle intersection, the motion feature information of the corresponding unmanned vehicle in each planned path section is re-optimized; the number of unmanned vehicles corresponding to the captured images contained in the generated adjacent vehicle image acquisition group is more than two.

[0058] Furthermore, when the generated adjacent vehicle image acquisition group is fed back to the front-end display page in S500, the front-end administrator monitors the image screen in the front-end display page. When the content corresponding to the image screen is detected to be abnormal, the driving state of the unmanned vehicle controlled by the port and mining vehicle control terminal is adjusted and decided through manual intervention.

[0059] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: in the process of obstacle avoidance control of the unmanned vehicle, the present invention realizes the preview of the merging area, analyzes the environmental information around the previewed merging area to evaluate the obstacle avoidance risks existing in the vehicle merging process, locks the associated obstacle avoidance points in the merging area, and optimizes the vehicle's motion characteristic information, thereby realizing effective control of the unmanned vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0061] Figure 1 The present invention is a flow chart of an autonomous obstacle avoidance method for an unmanned vehicle used in a port mine. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. 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 creative work are within the scope of protection of the present invention.

[0063] See also Figure 1 The present invention provides a technical solution: an autonomous obstacle avoidance method for an unmanned vehicle used in a port mine, the method comprising the following steps:

[0064] S100, obtaining the serial number of each unmanned vehicle entered into the port and mining vehicle command center and the planned path corresponding to each unmanned vehicle, and generating a port and mining vehicle planning information set;

[0065] When the numbers of the unmanned vehicles and the planned paths corresponding to the unmanned vehicles entered into the port and mining vehicle command center are obtained in S100, the unmanned vehicle numbers are bound to the planned paths corresponding to the corresponding unmanned vehicles to obtain the vehicle planning information pairs corresponding to the corresponding unmanned vehicles.

[0066] Each element in the port and mine vehicle planning information set corresponds to a vehicle planning information pair;

[0067] The planned paths corresponding to the driverless vehicles are preset in a database, and the planned paths corresponding to different driverless vehicles partially overlap.

[0068] S200, obtaining in real time the motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, and performing a path information preview for each unmanned vehicle in combination with the port and mine vehicle planning information set, and generating each vehicle intersection area corresponding to each unmanned vehicle and other unmanned vehicles;

[0069] The S200 includes the following steps:

[0070] S201, real-time acquisition of motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, wherein the motion characteristic information includes the position, forward direction and historical speed fluctuation range of the current unmanned vehicle in the planned path,

[0071] The forward direction is the direction from the starting point to the end point of the corresponding unmanned vehicle in the planned path; the historical speed fluctuation interval represents the interval formed by the average speed of the corresponding unmanned vehicle from the starting point to the current position in the planned path and the instantaneous speed corresponding to the current position;

[0072] In this embodiment, if the average speed of a driverless car from the starting point to the current position is v1, and the instantaneous speed corresponding to the current position is v2,

[0073] If v1>v2, the historical speed fluctuation range is [v2, v1];

[0074] If v1<v2, the historical speed fluctuation range is [v1, v2];

[0075] If v1=v2, the historical speed fluctuation range is a constant value v1.

[0076] S202, obtaining a port and mine vehicle planning information set, treating two unmanned vehicles with intersection sections in corresponding planning paths in the port and mine vehicle planning information set as an analysis combination pair, and binding each corresponding intersection section with the analysis combination pair, which is recorded as a first binding result;

[0077] S203, performing path information preview for the two driverless vehicles corresponding to the first binding result;

[0078] During the preview process, the path interval time interval corresponding to the first unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T1; the path interval time interval corresponding to the second unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T2; the intersection of T1 and T2 is recorded as the time interval preview interval; the intersection of the preview sections corresponding to the two unmanned vehicles in the first binding result in the time interval preview interval is recorded as the intersection dynamic preview section;

[0079] In this embodiment, when two driverless cars have an intersection section, T1 and T2 respectively correspond to the intervals corresponding to the time intervals between the two driverless cars and the current time during their passage through the intersection area.

[0080] Then, when the two corresponding driverless cars meet, the corresponding interval times in T1 and T2 are equal, and then it is necessary to calculate the intersection of T1 and T2 as the time interval preview interval, which corresponds to the interval composed of the interval durations based on the current time when the two corresponding driverless cars meet. The time point corresponding to any value in the interval may be the time point when the two corresponding driverless cars meet.

[0081] Then, the intersection of the rehearsal sections corresponding to the two unmanned vehicles in the time interval rehearsal interval is recorded as the intersection dynamic rehearsal section. The obtained rehearsal result has higher accuracy and can provide more powerful data support for subsequent steps.

[0082] The path information preview result includes a time interval preview section and a dynamic intersection preview section.

[0083] The minimum value in the path interval time interval is equal to the quotient of the shortest distance between the corresponding intersection section and the current position divided by the maximum value in the corresponding historical speed fluctuation interval; the maximum value in the path interval time interval is equal to the quotient of the longest distance between the corresponding intersection section and the current position divided by the minimum value in the corresponding historical speed fluctuation interval;

[0084] The preview section corresponding to the unmanned vehicle in the time interval preview interval in the first binding result is equal to the path section in the path planned by the corresponding unmanned vehicle, where the distance between the corresponding unmanned vehicle and the current position along the forward direction of the corresponding unmanned vehicle is greater than the first determination distance and less than the second determination distance;

[0085] The first determination distance is equal to the product of the minimum value of the unmanned vehicle in the time interval preview interval in the first binding result and the minimum value in the corresponding historical speed fluctuation interval; the second determination distance is equal to the product of the maximum value of the unmanned vehicle in the time interval preview interval in the first binding result and the maximum value in the corresponding historical speed fluctuation interval;

[0086] S204: Use the intersection dynamic preview section in the path information preview result corresponding to the first binding result as a subset of the intersection areas corresponding to the two driverless vehicles corresponding to the first binding result.

[0087] S300, constructing a three-dimensional model of the unmanned vehicle on the planned path, and marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle; analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment, and locking the associated obstacle avoidance point corresponding to each intersection area;

[0088] When marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle in S300, the planned path of each unmanned vehicle and the environment at a first unit distance from the planned path are scanned by a three-dimensional scanner to generate a three-dimensional model of the unmanned vehicle on the planned path;

[0089] When analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment in S300, a three-dimensional model of the unmanned vehicle on the planned path and a marking result of each intersection area in the corresponding three-dimensional model are obtained;

[0090] Obtaining the positions of the intersection areas of the same unmanned vehicle and the different marked intersection areas corresponding to different unmanned vehicles, determining that different intersection areas whose shortest distance between the corresponding intersection areas is less than a first preset distance are associated, and regionally merging the associated intersection areas, replacing the original associated intersection areas with the fused intersection areas;

[0091] The fused intersection area is equal to the intersection of the intersection results of the intersection sections to which the corresponding associated intersection areas belong and the fused feature area, and the fused feature area is the road section area composed of the corresponding associated intersection areas and the unmarked areas therebetween;

[0092] Calculate the obstacle avoidance risk assessment value of each intersection area compared to the surrounding environment, and record the obstacle avoidance risk assessment value of the i-th intersection area compared to the surrounding environment as Pi;

[0093] Pi=FHi / FUi,

[0094] Record the road interference value in a circular area with any position point as the center and a second unit distance as the radius in the i-th intersection area as the environmental risk value of the corresponding position point, wherein the second unit distance is less than the first unit distance and the first unit distance and the second unit distance are both constants preset in the database;

[0095] Among them, FHi represents the maximum value of the environmental risk values ​​corresponding to each location point in the i-th intersection area;

[0096] FUi represents the maximum value of the environmental risk values ​​corresponding to each location point in the intersection section corresponding to the i-th intersection area;

[0097] The road interference value in the circular area with any position point as the center and the second unit distance as the radius is recorded as D.

[0098] D = Z + β·LC / XC;

[0099] Z represents the ratio of the road pothole area in the corresponding circular area to the total area;

[0100] LC represents the vehicle width of the driverless car;

[0101] XC represents the effective convergence width of the road in the direction perpendicular to the central axis of the path in the corresponding circular area;

[0102] The intersection points of the diameter of the corresponding circular area perpendicular to the central axis of the path and the contour of the circular area are respectively recorded as obstacle points, and each obstacle point in the corresponding area of ​​each obstacle in the corresponding circular area is obtained. Each obstacle point in the corresponding circular area is mapped in a direction perpendicular to the central axis of the path, and the maximum value of the distance between any two adjacent points after mapping is recorded as XC; the obstacle corresponding area is collected and set in advance in the database.

[0103] When the associated obstacle avoidance point corresponding to each intersection area is locked in S300,

[0104] Obtain feature information of the i-th intersection area, recorded as Ei, the first parameter in Ei is the position point corresponding to FHi, the second parameter in Ei is the position point corresponding to FUi, and the third parameter in Ei is Pi;

[0105] Constructing each initial associated obstacle avoidance point combination corresponding to the intersection area, each element in each initial associated obstacle avoidance point combination corresponds to an intersection area, and each element in the obtained initial associated obstacle avoidance point combination is one of the first parameter and the second parameter in the feature information of the corresponding intersection area;

[0106] Filter the initial associated obstacle avoidance point combination with the smallest corresponding associated deviation, and use each element in the selected initial associated obstacle avoidance point combination as the associated obstacle avoidance point of the corresponding intersection area;

[0107] The associated deviation of the initial associated obstacle avoidance point combination is recorded as G,

[0108] ,

[0109] Wherein, k1 represents the total number of elements in the corresponding initial associated obstacle avoidance point combination; g represents the first coefficient and g is a constant preset in the database;

[0110] LPk represents the distance between the second parameter and the first parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs;

[0111] PWk represents the third parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs.

[0112] S400, combining the positions of the associated obstacle avoidance points corresponding to each unmanned vehicle and the motion characteristic information in the corresponding planned path, optimizing the motion characteristic information of the corresponding unmanned vehicle in each planned path section, and uploading it to the port and mining vehicle control terminal

[0113] When optimizing the motion characteristic information of the corresponding driverless vehicle in each planned path segment, the S400 optimizes the motion characteristic information in the planned path segment between the current position of the driverless vehicle and the nearest intersection area in the same direction as the driverless vehicle's forward movement in real time;

[0114] Obtain the associated obstacle avoidance point corresponding to the corresponding intersection area; obtain the median of the time interval preview interval in the path information preview result where the corresponding intersection dynamic preview section and the corresponding intersection area intersect, and record it as the first movement duration.

[0115] The length of the planned path from the current position of the unmanned vehicle to the nearest intersection area in the same direction as the unmanned vehicle is recorded as the first movement distance;

[0116] In the result after optimizing the motion feature information in the corresponding planned path section, the current position and forward direction of the driverless vehicle in the planned path remain unchanged, and the corresponding historical speed fluctuation range is changed to the quotient of the first motion distance and the first motion duration.

[0117] S500, the port and mining vehicle control terminal controls the travel state of the corresponding unmanned vehicle according to the optimized motion feature information, and when the distance between adjacent unmanned vehicles is less than a preset value, controls the image acquisition device on the adjacent unmanned vehicle to remain turned on, generates an adjacent vehicle image acquisition group, and feeds it back to the front-end display page;

[0118] In this embodiment, when the distance between adjacent unmanned vehicles is greater than or equal to a preset value, the image acquisition devices on the adjacent unmanned vehicles are controlled to remain in a closed state, and no adjacent vehicle image acquisition group is generated;

[0119] When the S500 Zhonggang Mine vehicle control terminal controls the travel status of the corresponding unmanned vehicle according to the optimized motion feature information, each unmanned vehicle obtains the distance between itself and the surrounding unmanned vehicles in real time; every time the unmanned vehicle completes a vehicle intersection, the motion feature information of the corresponding unmanned vehicle in each planned path section is re-optimized; the number of unmanned vehicles corresponding to the captured images contained in the generated adjacent vehicle image acquisition group is more than two.

[0120] When the generated adjacent vehicle image acquisition group is fed back to the front-end display page in S500, the front-end administrator monitors the image screen in the front-end display page. When the content corresponding to the image screen is detected to be abnormal, the front-end administrator makes a decision on the driving state of the unmanned vehicle controlled by the port and mining vehicle control terminal through manual intervention.

[0121] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0122] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. An autonomous obstacle avoidance method for unmanned vehicles in ports and mines. It is characterized in that The method comprises the following steps: S100, obtaining the serial number of each unmanned vehicle entered into the port and mining vehicle command center and the planned path corresponding to each unmanned vehicle, and generating a port and mining vehicle planning information set; S200, obtaining in real time the motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, and performing a path information preview for each unmanned vehicle in combination with the port and mine vehicle planning information set, and generating each vehicle intersection area corresponding to each unmanned vehicle and other unmanned vehicles; S300, constructing a three-dimensional model of the unmanned vehicle on the planned path, and marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle; analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment, and locking the associated obstacle avoidance point corresponding to each intersection area; S400, combining the positions of the associated obstacle avoidance points corresponding to each unmanned vehicle and the motion characteristic information in the corresponding planned path, optimizing the motion characteristic information of the corresponding unmanned vehicle in each planned path section, and uploading it to the port and mining vehicle control terminal; S500, the port and mining vehicle control terminal controls the travel state of the corresponding unmanned vehicle according to the optimized motion feature information, and when the distance between adjacent unmanned vehicles is less than a preset value, controls the image acquisition device on the adjacent unmanned vehicle to remain turned on, generates an adjacent vehicle image acquisition group, and feeds it back to the front-end display page; The S200 includes the following steps: S201, real-time acquisition of motion characteristic information of each port and mine unmanned vehicle in the corresponding planned path, wherein the motion characteristic information includes the position, forward direction and historical speed fluctuation range of the current unmanned vehicle in the planned path, The forward direction is the direction from the starting point to the end point of the corresponding unmanned vehicle in the planned path; the historical speed fluctuation interval represents the interval formed by the average speed of the corresponding unmanned vehicle from the starting point to the current position in the planned path and the instantaneous speed corresponding to the current position; S202, obtaining a port and mine vehicle planning information set, treating two unmanned vehicles with intersection sections in corresponding planning paths in the port and mine vehicle planning information set as an analysis combination pair, and binding each corresponding intersection section with the analysis combination pair, which is recorded as a first binding result; S203, performing path information preview for the two driverless vehicles corresponding to the first binding result; During the preview process, the path interval time interval corresponding to the first unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T1; the path interval time interval corresponding to the second unmanned vehicle passing through the corresponding intersection section in the first binding result is calculated, which is recorded as T2; the intersection of T1 and T2 is recorded as the time interval preview interval; the intersection of the preview sections corresponding to the two unmanned vehicles in the first binding result in the time interval preview interval is recorded as the intersection dynamic preview section; The path information preview result includes a time interval preview section and a dynamic intersection preview section. The minimum value in the path interval time interval is equal to the quotient of the shortest distance between the corresponding intersection section and the current position divided by the maximum value in the corresponding historical speed fluctuation interval; the maximum value in the path interval time interval is equal to the quotient of the longest distance between the corresponding intersection section and the current position divided by the minimum value in the corresponding historical speed fluctuation interval; The preview section corresponding to the unmanned vehicle in the time interval preview interval in the first binding result is equal to the path section in the path planned by the corresponding unmanned vehicle, where the distance between the corresponding unmanned vehicle and the current position along the forward direction of the corresponding unmanned vehicle is greater than the first determination distance and less than the second determination distance; The first determination distance is equal to the product of the minimum value of the unmanned vehicle in the time interval preview interval in the first binding result and the minimum value in the corresponding historical speed fluctuation interval; the second determination distance is equal to the product of the maximum value of the unmanned vehicle in the time interval preview interval in the first binding result and the maximum value in the corresponding historical speed fluctuation interval; S204, taking the intersection dynamic preview section in the path information preview result corresponding to the first binding result as a subset of the intersection areas corresponding to the two driverless vehicles corresponding to the first binding result; When marking the intersection area in the three-dimensional model on the planned path corresponding to each unmanned vehicle in S300, the planned path of each unmanned vehicle and the environment at a first unit distance from the planned path are scanned by a three-dimensional scanner to generate a three-dimensional model of the unmanned vehicle on the planned path; When analyzing the obstacle avoidance risk assessment value of each intersection area compared with the surrounding environment in S300, a three-dimensional model of the unmanned vehicle on the planned path and a marking result of each intersection area in the corresponding three-dimensional model are obtained; Obtaining the positions of the intersection areas of the same unmanned vehicle and the different marked intersection areas corresponding to different unmanned vehicles, determining that different intersection areas whose shortest distance between the corresponding intersection areas is less than a first preset distance are associated, and regionally merging the associated intersection areas, replacing the original associated intersection areas with the fused intersection areas; The fused intersection area is equal to the intersection of the intersection results of the intersection sections to which the corresponding associated intersection areas belong and the fused feature area, and the fused feature area is the road section area composed of the corresponding associated intersection areas and the unmarked areas therebetween; Calculate the obstacle avoidance risk assessment value of each intersection area compared to the surrounding environment, and record the obstacle avoidance risk assessment value of the i-th intersection area compared to the surrounding environment as Pi; Pi=FHi / FUi, Record the road interference value in a circular area with any position point as the center and a second unit distance as the radius in the i-th intersection area as the environmental risk value of the corresponding position point, wherein the second unit distance is less than the first unit distance and the first unit distance and the second unit distance are both constants preset in the database; Among them, FHi represents the maximum value of the environmental risk values ​​corresponding to each location point in the i-th intersection area; FUi represents the maximum value of the environmental risk values ​​corresponding to each location point in the intersection section corresponding to the i-th intersection area; The road interference value in the circular area with any position point as the center and the second unit distance as the radius is recorded as D. D = Z + β·LC / XC; Z represents the ratio of the road pothole area in the corresponding circular area to the total area; LC represents the vehicle width of the driverless car; XC represents the effective convergence width of the road in the direction perpendicular to the central axis of the path in the corresponding circular area; The intersection points of the diameter of the corresponding circular area perpendicular to the central axis of the path and the contour of the circular area are respectively recorded as an obstacle point, and each obstacle point in the corresponding area of ​​each obstacle in the corresponding circular area is obtained, and each obstacle point in the corresponding circular area is mapped in the direction perpendicular to the central axis of the path, and the maximum value of the distance between any two adjacent points after mapping is recorded as XC; the obstacle corresponding area is collected and set in advance in the database; When the associated obstacle avoidance point corresponding to each intersection area is locked in S300, Obtain feature information of the i-th intersection area, recorded as Ei, the first parameter in Ei is the position point corresponding to FHi, the second parameter in Ei is the position point corresponding to FUi, and the third parameter in Ei is Pi; Constructing each initial associated obstacle avoidance point combination corresponding to the intersection area, each element in each initial associated obstacle avoidance point combination corresponds to an intersection area, and each element in the obtained initial associated obstacle avoidance point combination is one of the first parameter and the second parameter in the feature information of the corresponding intersection area; Filter the initial associated obstacle avoidance point combination with the smallest corresponding associated deviation, and use each element in the selected initial associated obstacle avoidance point combination as the associated obstacle avoidance point of the corresponding intersection area; The associated deviation of the initial associated obstacle avoidance point combination is recorded as G, , Wherein, k1 represents the total number of elements in the corresponding initial associated obstacle avoidance point combination; g represents the first coefficient and g is a constant preset in the database; LPk represents the distance between the second parameter and the first parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs; PWk represents the third parameter in the feature information to which the kth element in the corresponding initial associated obstacle avoidance point combination belongs; When optimizing the motion characteristic information of the corresponding driverless vehicle in each planned path segment, the S400 optimizes the motion characteristic information in the planned path segment between the current position of the driverless vehicle and the nearest intersection area in the same direction as the driverless vehicle's forward movement in real time; Obtain the associated obstacle avoidance point corresponding to the corresponding intersection area; obtain the median of the time interval preview interval in the path information preview result where the corresponding intersection dynamic preview section and the corresponding intersection area intersect, and record it as the first movement duration. The length of the planned path from the current position of the unmanned vehicle to the nearest intersection area in the same direction as the unmanned vehicle is recorded as the first movement distance; In the result after optimizing the motion feature information in the corresponding planned path section, the current position and forward direction of the driverless vehicle in the planned path remain unchanged, and the corresponding historical speed fluctuation range is changed to the quotient of the first motion distance and the first motion duration.

2. The autonomous obstacle avoidance method for an unmanned vehicle used in a port mine according to claim 1, Features: When the numbers of the unmanned vehicles and the planned paths corresponding to the unmanned vehicles entered into the port and mining vehicle command center are obtained in S100, the unmanned vehicle numbers are bound to the planned paths corresponding to the corresponding unmanned vehicles to obtain the vehicle planning information pairs corresponding to the corresponding unmanned vehicles. Each element in the port and mine vehicle planning information set corresponds to a vehicle planning information pair; The planned paths corresponding to the driverless vehicles are preset in a database, and the planned paths corresponding to different driverless vehicles partially overlap.

3. The autonomous obstacle avoidance method for an unmanned vehicle used in a port mine according to claim 1, Features: When the S500 Zhonggang Mine vehicle control terminal controls the travel status of the corresponding unmanned vehicle according to the optimized motion feature information, each unmanned vehicle obtains the distance between itself and the surrounding unmanned vehicles in real time; every time the unmanned vehicle completes a vehicle intersection, the motion feature information of the corresponding unmanned vehicle in each planned path section is re-optimized; the number of unmanned vehicles corresponding to the captured images contained in the generated adjacent vehicle image acquisition group is more than two.

4. The autonomous obstacle avoidance method for an unmanned vehicle used in a port mine according to claim 1, Features: When the generated adjacent vehicle image acquisition group is fed back to the front-end display page in S500, the front-end administrator monitors the image screen in the front-end display page. When the content corresponding to the image screen is detected to be abnormal, the front-end administrator makes a decision on the driving state of the unmanned vehicle controlled by the port and mining vehicle control terminal through manual intervention.