CN116107300A - Priori knowledge-based path planning method applicable to unmanned in off-road environment - Google Patents

Priori knowledge-based path planning method applicable to unmanned in off-road environment Download PDF

Info

Publication number
CN116107300A
CN116107300A CN202211573240.1A CN202211573240A CN116107300A CN 116107300 A CN116107300 A CN 116107300A CN 202211573240 A CN202211573240 A CN 202211573240A CN 116107300 A CN116107300 A CN 116107300A
Authority
CN
China
Prior art keywords
road
path
turning radius
gradient
shortest path
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211573240.1A
Other languages
Chinese (zh)
Inventor
徐田凡
周睿
梁乐
李峰
邓烨峰
胡明伟
欧国峰
王宏亮
刘汉鼎
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
716th Research Institute of CSIC
CSIC Information Technology Co Ltd
Original Assignee
716th Research Institute of CSIC
CSIC Information Technology Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 716th Research Institute of CSIC, CSIC Information Technology Co Ltd filed Critical 716th Research Institute of CSIC
Priority to CN202211573240.1A priority Critical patent/CN116107300A/en
Publication of CN116107300A publication Critical patent/CN116107300A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0214—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with safety or protection criteria, e.g. avoiding hazardous areas
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The invention discloses a path planning method applicable to unmanned under off-road environment based on priori knowledge, which comprises the following steps: importing a road network map file containing elevation signals, and marking target points; establishing a priori knowledge base based on the off-road capability of different vehicle types, and confirming the maximum climbing gradient and the minimum turning radius which can be achieved by the current unmanned driving according to the different vehicle types; calculating the space distance of each road section and recording the space distance into a road network file; calculating the shortest path from the starting point to the target point based on Dijkstra algorithm; adjusting according to the gradient, and recalculating the shortest path; adjusting according to the turning radius, and recalculating the shortest path; assigning values to the corresponding mark quantities according to the shortest path length, the gradient and the turning radius; and calculating the minimum cost function value to obtain an optimal path with the minimum cost from the starting point to the target point. The obtained path is relatively good in road condition, short in distance and suitable for unmanned driving.

Description

Priori knowledge-based path planning method applicable to unmanned in off-road environment
Technical Field
The invention relates to the technical field of automatic driving, in particular to a path planning method applicable to unmanned driving based on priori knowledge in an off-road environment.
Background
The application technology of the current path planning algorithm is mature, mainly aims at the urban structured road environment, and is seldom used for the cross-country road research with complex environment. The path planning algorithm mostly adopts a method of combining path length and obstacle collision prevention degree, is a rigid obstacle rather than an unvented area, lacks analysis of the passing difficulty of the whole terrain, and cannot adapt to planning tasks of complex terrain. For complex terrain, mileage, time and safety are all considerations for unmanned vehicles. The gradient, the turning radius and the number of turns have an influence not only on the running speed but also on the safety, which are factors that must be considered.
Disclosure of Invention
The invention aims to provide a path planning method based on priori knowledge and suitable for unmanned in off-road environment, so that the vehicle can reach a target point in an optimal path in an unmanned manner in the off-road environment, and the robustness and the safety are improved.
The technical solution for realizing the purpose of the invention is as follows: a priori knowledge based path planning method for use in an off-road environment suitable for use in unmanned situations, the method comprising:
s110: and importing a road network map file containing elevation signals, and marking target points. Estimating the gradient of the path according to the elevation signal; the minimum turning radius at the sharp turn is estimated from the road network. The starting point is the current position of the vehicle.
S120: the method comprises the steps of selecting a vehicle type, establishing a priori knowledge base based on the off-road capability of different vehicle types, and confirming the maximum climbing gradient theta and the minimum turning radius gamma which can be achieved by the current unmanned driving according to different vehicle types.
S130: and calculating the space distance of each road section and recording the space distance into a road network file.
S140: and calculating the shortest path from the starting point to the target point based on the Dijkstra algorithm, and recording the shortest path length, the maximum gradient and the minimum turning radius data in a table.
S150: and (3) adjusting according to the gradient, recalculating the shortest path, and recording the shortest path length, the maximum gradient and the minimum turning radius data in a table.
S160: and adjusting according to the turning radius, recalculating the shortest path, and recording the shortest path length, the maximum gradient and the minimum turning radius data in a table.
S170: and assigning corresponding mark quantities according to the path length, the gradient and the turning radius in the table.
S180: and calculating the minimum cost function value to obtain an optimal path with the minimum cost from the starting point to the target point.
Further, the maximum climbing gradient of the road section in step S110 can be estimated by the east-west direction elevation change rate and the north-south direction elevation change rate, i.e
Figure BDA0003988956310000021
Wherein h is x (i)、h y (i) The elevation change rate of the current point in the east-west direction and the elevation change rate of the current point in the north-south direction are respectively. h is a x (i)、h y (i) And calculating by using elevation signal values of two adjacent points. />
Further, in step S120, the priori knowledge base includes the vehicle model and its corresponding maximum climbing gradient θ and minimum turning radius γ. When the minimum turning radius gamma>Υ i When the unmanned vehicle cannot pass throughAnd deleting the corresponding i road section from the road network file. When the maximum climbing gradient theta<θ i When the unmanned vehicle cannot pass through the road section, the corresponding i road section is deleted from the road network file, so that a new road network file is obtained and is recorded as osmfile.
Further, in step S130, the distance of the spatial path is calculated as the difference in elevation and the planar distance between the points.
Figure BDA0003988956310000022
Wherein η (i, i-1) represents the spatial distance between the current point and the previous point; h (i) is the elevation of the current point, and H (i-1) is the elevation of the previous point; l (i, i-1) is the planar path element distance, which is the projection of the spatial path onto the plane. With the geodetic coordinates, the calculation formula for L (i, i-1) is as follows:
Figure BDA0003988956310000023
wherein, (X i ,Y i )、(X i-1 ,Y i-1 ) The geodetic coordinates of the current point i and the previous point i-1 are respectively, namely longitude and latitude values obtained from road network file data; r= 6371393 meters, which is the average earth radius in china.
Calculating the space distance between the current point i and the previous point i-1 through eta (i, i-1), summing the space distances among all points on the road sections to obtain the space distance of each road section, and recording the space distance into a road network file.
Further, in step S140, the shortest path from the starting point to the target point is calculated based on Dijkstra algorithm, that is, the shortest path from the starting point to other points is stored using the array, but the initial road segment space distance from the starting point to other points is stored at the beginning. Find the shortest through the traversal of n-1 passes, where n is the number of road segments. Finding the minimum value in the array in the remaining nodes each time, adding the minimum value into the array, updating the array of the remaining nodes to obtain the shortest path, and recording the maximum gradient theta in the path max And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length. I.e. the optimal path with the smallest cost from the starting point to the target point is obtained and recorded in the table (including distance, maximum gradient, minimum turning radius).
Further, in step S150, the adjustment is performed according to the gradient, that is:
newly creating a road network file ossfile-theta, enabling the ossfile-theta to be equal to the ossfile, and enabling the maximum gradient theta to be equal to the maximum gradient theta in the road network file ossfile-theta max Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length.
The latest maximum gradient theta is obtained in the road network file osmfile-theta max new Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length. This procedure was repeated 9 times, and 9 sets of data were obtained in turn and recorded in the table.
Further, in step S160, adjustment is performed according to the turning radius, that is:
newly-built road network file osmfile-y, enabling osmfile-y=osmfile, and enabling the minimum turning radius gamma to be in the road network file osmfile-y min Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max And the corresponding road section number and minimum turning radius gamma min new And its corresponding road segment number, the path length.
The latest minimum turning radius gamma is obtained in the road network file osmfile-gamma min new Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max And the corresponding road section number and minimum turning radius gamma min new And its corresponding road segment number, the path length. This procedure was repeated 9 times, and 9 sets of data were obtained in turn and recorded in the table.
Further, in step S170, the corresponding flag amounts are assigned according to the path length, the gradient, and the turning radius in the table, that is:
the path mark quantity S is sequentially checked in the table according to the path length Label (C) Assigned values of 10,9,8,7,6,5,4,3,2,1; grade marking quantity theta sequentially corresponding to grade Label (C) Assigned values of 10,9,8,7,6,5,4,3,2,1; the turning radius mark quantity gamma is sequentially controlled according to the turning radius Label (C) Assigned 1,2,3,4,5,6,7,8,9, 10.
Further, a minimum cost function value is calculated in step S180, i.e
Minimum cost function f (S Label (C) ,θ Label (C) ,γ Label (C) )＝ω1×S Label (C) +ω2×θ Label (C) +ω3×γ Label (C)
Where ω1+ω2+ω3=1, ω2, ω3 are related to the autopilot capability, the stronger the autopilot capability, the smaller the values of ω2 and ω3, ω2=ω3=0, ω1=1 when the manual driving level is reached.
Compared with the prior art, the invention has the remarkable advantages that: according to the method, according to the elevation information in the road network map file and the priori knowledge of the cross-country capability of the current vehicle type when the vehicle is unmanned, the shortest path is obtained based on Dijkstra algorithm, and then the optimal path is obtained by combining the gradient and the turning radius and through the cost function, and the path is relatively good in road condition, short in distance and suitable for unmanned; the invention increases the passing difficulty of the whole terrain and improves the robustness and safety of path planning of the unmanned vehicle under different environments by analyzing the safety, namely introducing the parameters of the gradient and the turning radius into the cost function.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following description will briefly introduce the drawings that are required to be used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present application, and other embodiments may also be obtained according to these drawings to those skilled in the art.
Fig. 1 is a schematic flow chart of a path planning method according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. Based on the embodiments herein, a person of ordinary skill in the art would be able to obtain all other embodiments based on the disclosure herein, which are within the scope of the disclosure herein.
In order to solve the problem that unmanned paths with good road conditions and short distances are searched in an off-road complex environment, the embodiment of the application provides a path planning method applicable to unmanned paths based on priori knowledge in the off-road environment.
Referring to fig. 1, fig. 1 is a schematic flow chart of a path planning method applicable to unmanned vehicles based on a priori knowledge in an off-road environment according to an embodiment of the present application, where the method may include the following steps:
s110: and importing a road network map file containing elevation signals, and marking target points. Estimating the gradient of the path according to the elevation signal; the minimum turning radius at the sharp turn is estimated from the road network. The starting point is the current position of the vehicle.
Specifically, qt programming is used, a map is interactively driven through Qwebchannel and html communication, road network files are loaded to analyze road section information and draw the road section information on the map, target points are marked on the map, and a formula is used for marking the target points on the map
Figure BDA0003988956310000041
Calculating the maximum gradient theta of the ith road section i Is the maximum gradient of the path point, where h x (i)、h y (i) The elevation change rate of the current point in the east-west direction and the elevation change rate of the current point in the north-south direction are respectively.
S120: the vehicle type is selected, a priori knowledge base is established according to the cross-country capability of different vehicle types, and the maximum climbing gradient theta and the minimum turning radius gamma which can be achieved by the current unmanned driving are confirmed according to different vehicle types.
In particular, when the minimum turns halfRadial gamma>Υ i And when the unmanned vehicle cannot pass through the road section, deleting the corresponding i road section from the road network file. When the maximum climbing gradient theta<θ i And when the unmanned vehicle cannot pass through the road section, deleting the corresponding i road section from the road network file, so as to obtain a new road network file, marking the new road network file as osmfile, and redrawing the new road network file in the map.
S130: and calculating the space distance of each road section and recording the space distance into a road network file.
Specifically, according to the formula
Figure BDA0003988956310000051
Wherein, eta (i, i-1) represents the space distance between the current point and the previous point; h (i) is the elevation of the current point, and H (i-1) is the elevation of the previous point; l (i, i-1) is the planar path element distance, which is the projection of the spatial path onto the plane.
Calculating the space distance between the current point i and the previous point i-1 through eta (i, i-1), summing the space distances among all points on the road sections to obtain the space distance of each road section, and recording the space distance into a road network file.
S140: the shortest path from the starting point to the target point is calculated based on Dijkstra's algorithm.
Specifically, an array is created to store the shortest route from the starting point to the other points, but the initial road segment space distance from the starting point to the other points is stored at the beginning. Find the shortest through the traversal of n-1 passes, where n is the number of road segments. Finding the minimum value in the array in the remaining nodes each time, adding the minimum value into the array, updating the array of the remaining nodes to obtain the shortest path, and recording the maximum gradient theta in the path max And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length. And obtaining the optimal path with the minimum cost from the starting point to the target point, and recording the optimal path in a table. The table format is shown in table 1.
Table 1, data recording table
Figure BDA0003988956310000052
S150: and adjusting according to the gradient, recalculating the shortest path, and recording the data in a table.
Specifically, newly creating a road network file ossfile-theta, enabling the ossfile-theta=ossfile, and setting the maximum gradient theta in the road network file ossfile-theta max Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length.
The latest maximum gradient theta is obtained in the road network file osmfile-theta max new Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And its corresponding road segment number, the path length. This procedure was repeated 9 times, and 9 sets of data were obtained in turn and recorded in the table.
S160: and adjusting according to the turning radius, recalculating the shortest path, and recording the data in a table.
Specifically, newly built road network file osmfile-y, letting osmfile-y=osmfile, and setting minimum turning radius gamma in road network file osmfile-y min Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max And the corresponding road section number and minimum turning radius gamma min new And its corresponding road segment number, the path length.
The latest minimum turning radius gamma is obtained in the road network file osmfile-gamma min new Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max And the corresponding road section number and minimum turning radius gamma min new And its corresponding road segment number, the path length. This procedure was repeated 9 times, and 9 sets of data were obtained in turn and recorded in the table.
S170: and assigning corresponding mark quantities according to the path length, the gradient and the turning radius in the table.
Specifically, the table is sequentially provided according to the path lengthFor the path mark quantity S Label (C) Assigned values of 10,9,8,7,6,5,4,3,2,1; grade marking quantity theta sequentially corresponding to grade Label (C) Assigned values of 10,9,8,7,6,5,4,3,2,1; the turning radius mark quantity gamma is sequentially controlled according to the turning radius Label (C) Assigned 1,2,3,4,5,6,7,8,9, 10.
S180: and calculating the minimum cost function value to obtain an optimal path with the minimum cost from the starting point to the target point.
Minimum cost function f (S Label (C) ,θ Label (C) ,γ Label (C) )＝ω1×S Label (C) +ω2×θ Label (C) +ω3×γ Label (C)
Where ω1+ω2+ω3=1, ω2, ω3 are related to the autopilot capability, the stronger the autopilot capability, the smaller the values of ω2 and ω3, ω2=ω3=0, ω1=1 when the manual driving level is reached. In this example, ω1=0.6, ω2=0.25, and ω3=0.15 were taken.
Because the road condition is poor in the off-road environment, the method has high requirements on an unmanned system, and the method obtains the shortest path based on Dijkstra algorithm according to the elevation information in the road network map file and the off-road capability priori knowledge when the current vehicle type is unmanned, and obtains the optimal path through a cost function by combining the gradient and the turning radius. The path is relatively good in road condition, short in distance and suitable for unmanned driving.
The above examples illustrate only one embodiment of the invention, which is described in more detail and is not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.

Claims (10)

1. A priori knowledge based path planning method for use in an off-road environment suitable for use in unmanned situations, comprising the steps of:
s110: importing a road network map file containing elevation signals, marking target points, and estimating the gradient of each path according to the elevation signals; estimating the minimum turning radius of the sharp turning position according to the road network map file, wherein the starting point is the current position of the vehicle;
s120: selecting a vehicle type, establishing a priori knowledge base based on the off-road capability of different vehicle types, and confirming the maximum climbing gradient and the minimum turning radius which can be achieved by the current unmanned driving according to different vehicle types;
s130: calculating the space distance of each road section and recording the space distance into a road network map file;
s140: calculating the shortest path from the starting point to the target point based on Dijkstra algorithm according to the starting point, the target point and the road section space distance in the road network map file, and recording the shortest path length, the maximum gradient and the minimum turning radius;
s150: regulating according to the gradient, recalculating the shortest path, and recording the length of the shortest path, the maximum gradient and the minimum turning radius;
s160: adjusting according to the minimum turning radius, recalculating the shortest path, and recording the length of the shortest path, the maximum gradient and the minimum turning radius;
s170: assigning values to the corresponding mark quantities according to the shortest path length, the maximum gradient and the maximum turning radius of the steps S140, S150 and S160;
s180: and calculating the minimum cost function value to obtain an optimal path with the minimum cost from the starting point to the target point.
2. The method for unmanned path planning based on a priori knowledge in an off-road environment according to claim 1, wherein the road network map file is composed of road segments each having a corresponding road segment number, maximum gradient, minimum turning radius, each road segment being composed of path points containing longitude and latitude information and corresponding elevation signals.
3. The method for unmanned path planning based on a priori knowledge in an off-road environment according to claim 1, wherein the step S110 is based on elevation signalsThe estimating the gradient of the path specifically includes: calculating gradient of elevation signal by partial derivative method to estimate gradient corresponding to each path point, maximum gradient theta of ith road section i Is the maximum gradient of the path point, i.e
Figure FDA0003988956300000011
Wherein h is x (i)、h y (i) The elevation change rate of the current point in the east-west direction and the elevation change rate of the current point in the north-south direction are respectively.
4. The method for path planning based on a priori knowledge for use in an off-road environment according to claim 1, wherein estimating the minimum turning radius at the sharp turn based on the road network map file in step S110 specifically comprises: estimating turning radius according to longitude and latitude coordinates of adjacent path points, and minimum turning radius gamma of ith road section i Is the minimum turning radius of the path point.
5. The method for path planning for unmanned aerial vehicles based on a priori knowledge in an off-road environment according to claim 1, wherein the a priori knowledge base in S120 includes vehicle type and its corresponding maximum climbing gradient θ and minimum turning radius γ, when minimum turning radius γ>γ i When the unmanned vehicle cannot pass through the road section, deleting the corresponding i road section from the road network map file; when the maximum climbing gradient theta<θ i When the unmanned vehicle cannot pass through the road section, the corresponding i road section is deleted from the road network map file, so that a new road network map file is obtained and recorded as osmfile.
6. The method for path planning for unmanned aerial vehicles based on a priori knowledge in an off-road environment of claim 1, wherein said step S130 comprises in particular
Calculating the space distance between every two adjacent points by the elevation difference and the plane distance between the points:
Figure FDA0003988956300000021
wherein eta (i, i-1) represents the spatial distance between the current point i and the previous point i-1; h (i) is the elevation of the current point, and H (i-1) is the elevation of the previous point; l (i, i-1) is a plane path unit distance, which is a projection of a spatial path on a plane, and the calculation formula of L (i, i-1) is as follows using geodetic coordinates:
Figure FDA0003988956300000022
wherein, (X i ,Y i )、(X i-1 ,Y i-1 ) The geodetic coordinates of the current point i and the previous point i-1 are respectively, namely longitude and latitude values obtained from road network file data; r is the average earth radius in China;
calculating the space distance between the current point i and the previous point i-1 through eta (i, i-1), summing the space distances among all points on the road sections to obtain the space distance of each road section, and recording the space distance into a road network map file.
7. The method for unmanned path planning based on a priori knowledge in an off-road environment according to claim 1, wherein the adjusting according to the gradient, and the recalculating the shortest path specifically comprises:
newly creating a road network file ossfile-theta, enabling the ossfile-theta to be equal to the ossfile, and enabling the maximum gradient theta to be equal to the maximum gradient theta in the road network file ossfile-theta max Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And the corresponding road section number and the path length;
the latest maximum gradient theta is obtained in the road network file osmfile-theta max new Deleting the corresponding road section, recalculating the shortest path, and recording the shortest path in the new shortest pathLarge gradient theta max new And the corresponding road section number and minimum turning radius gamma min And the corresponding road section number and the path length, and repeating the process for 9 times to obtain 9 groups of data.
8. The method for path planning based on a priori knowledge for use in an off-road environment according to claim 1, wherein said adjusting according to the turning radius, recalculating the shortest path comprises:
newly creating a road network file osmfile-gamma, enabling the osmfile-gamma=osmfile, and enabling the minimum turning radius gamma to be in the road network file osmfile-gamma min Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max And the corresponding road section number and minimum turning radius gamma min new And the corresponding road section number and the path length;
the latest maximum gradient theta is obtained in the road network file osmfile-theta max new Deleting the corresponding road section, recalculating the shortest path, and recording the maximum gradient theta in the new shortest path max new And the corresponding road section number and minimum turning radius gamma min And the corresponding road section number and the path length, and repeating the process for 9 times to obtain 9 groups of data.
9. The method for path planning based on a priori knowledge for use in an off-road environment according to claim 1, wherein said step S170 specifically comprises: the path mark quantity S is sequentially adjusted according to the length of the path Label (C) Assigned values 10,9,8,7,6,5,4,3,2,1; grade marking quantity theta sequentially corresponding to grade Label (C) Assigned values 10,9,8,7,6,5,4,3,2,1; the turning radius mark quantity gamma is sequentially controlled according to the turning radius Label (C) Assigned values 1,2,3,4,5,6,7,8,9, 10.
10. The method for unmanned path planning based on a priori knowledge for use in an off-road environment of claim 1, wherein the minimum cost function is:
f(S label (C) ,θ Label (C) ,γ Label (C) )＝ω1×S Label (C) +ω2×θ Label (C) +ω3×γ Label (C)
Wherein the weight coefficients ω1+ω2+ω3=1, ω2, ω3 are related to the autopilot capability, ω2=ω3=0, ω1=1 when the set manual driving level is reached.
CN202211573240.1A 2022-12-08 2022-12-08 Priori knowledge-based path planning method applicable to unmanned in off-road environment Pending CN116107300A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211573240.1A CN116107300A (en) 2022-12-08 2022-12-08 Priori knowledge-based path planning method applicable to unmanned in off-road environment

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211573240.1A CN116107300A (en) 2022-12-08 2022-12-08 Priori knowledge-based path planning method applicable to unmanned in off-road environment

Publications (1)

Publication Number Publication Date
CN116107300A true CN116107300A (en) 2023-05-12

Family

ID=86264697

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211573240.1A Pending CN116107300A (en) 2022-12-08 2022-12-08 Priori knowledge-based path planning method applicable to unmanned in off-road environment

Country Status (1)

Country Link
CN (1) CN116107300A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117553820A (en) * 2024-01-12 2024-02-13 北京理工大学 Path planning method, system and equipment in off-road environment
CN117558147A (en) * 2024-01-11 2024-02-13 上海伯镭智能科技有限公司 Mining area unmanned vehicle road right distribution remote control method

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117558147A (en) * 2024-01-11 2024-02-13 上海伯镭智能科技有限公司 Mining area unmanned vehicle road right distribution remote control method
CN117558147B (en) * 2024-01-11 2024-03-26 上海伯镭智能科技有限公司 Mining area unmanned vehicle road right distribution remote control method
CN117553820A (en) * 2024-01-12 2024-02-13 北京理工大学 Path planning method, system and equipment in off-road environment
CN117553820B (en) * 2024-01-12 2024-04-05 北京理工大学 Path planning method, system and equipment in off-road environment

Similar Documents

Publication Publication Date Title
CN116107300A (en) Priori knowledge-based path planning method applicable to unmanned in off-road environment
US11604071B2 (en) Motion graph construction and lane level route planning
CN113126618B (en) Unmanned global path planning and re-planning method in cross-country environment
CN111102988A (en) Map-based path planning method, server, vehicle-mounted terminal, and storage medium
CN102208011B (en) Image processing system and vehicle control system
CN103674046B (en) Vehicle travel is planned
CN102901505B (en) Navigational system and road matching method and device
CN106323321A (en) Vehicle navigation real-time correction method and vehicle navigation real-time correction system
CN109642800B (en) Route searching method and route searching device
US8260532B2 (en) Traffic probe in-vehicle map-based process to reduce data communications and improve accuracy
EP2427726A1 (en) Methods and systems for creating digital transportation networks
CN113031033B (en) Track deviation correcting device and method based on GPS data
US20170074670A1 (en) Travel time data processing apparatus, travel time data processing method and program
CN109520499B (en) Method for realizing regional real-time isochrones based on vehicle GPS track data
US10949682B2 (en) Method for ascertaining a piece of topological information of an intersection
CN116202533B (en) Vehicle track navigation planning method and device based on terrain reconstruction
CN108253974A (en) Floating Car location data automatic adaptation cushion route matching system and method
CN111328412A (en) Adaptive traffic control based on vehicle trajectory data
CN105806355A (en) Green vehicle path navigation system and method
CN110830915B (en) Method and device for determining starting point position
CN104515528B (en) Single-point map-matching method based on section cumulative probability
CN108983782A (en) A kind of choosing method of the mobile target point of unmanned vehicle path trace
CN114690231A (en) Vehicle positioning method
CN117741717A (en) Global positioning system bias detection and reduction
CN114061597B (en) Autonomous positioning method for vehicle map matching

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination