CN111596664B - Unmanned vehicle path planning method based on three-layer architecture - Google Patents
Unmanned vehicle path planning method based on three-layer architecture Download PDFInfo
- Publication number
- CN111596664B CN111596664B CN202010469972.0A CN202010469972A CN111596664B CN 111596664 B CN111596664 B CN 111596664B CN 202010469972 A CN202010469972 A CN 202010469972A CN 111596664 B CN111596664 B CN 111596664B
- Authority
- CN
- China
- Prior art keywords
- map
- path
- layer
- planning
- road network
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000013256 coordination polymer Substances 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 6
- 238000010845 search algorithm Methods 0.000 claims description 5
- 238000013519 translation Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 abstract description 8
- 230000009286 beneficial effect Effects 0.000 abstract description 2
- 238000011156 evaluation Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000008447 perception Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 239000002131 composite material Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
- G05D1/0221—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
-
- 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
- G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Navigation (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses a three-layer architecture-based unmanned vehicle path planning method, which comprises the following steps: step 1: establishing a diagram, carrying out abstract and mathematical description on a road of an application scene, and representing and storing the road; step 2: and in the application, the road network map established in the specific scene is utilized, and the planned path is realized on the road network map according to the task requirement. The invention has the beneficial effects that: (1) the global path planning and the local path planning are considered overall by utilizing a three-layer architecture, so that the global path planning and the local path planning are closely connected with a physical platform, more useful information is provided for the road local path planning, and the planning performance is improved; the third layer planning execution layer introduces an improved A star search method based on guide lines, and by using the guide lines and key points, the local planning path which meets the expectation is reserved to the greatest extent, and the flexible obstacle avoidance characteristic is kept.
Description
Technical Field
The invention belongs to a path planning method, and particularly relates to a path planning method for an unmanned vehicle.
Background
With the development of the automobile industry, automobiles become more and more important components in social production and daily life; meanwhile, the issue of automobile safety is becoming a focus of attention, and how to improve the safety of vehicle running more effectively has become a common issue facing governments and research institutions of various countries. Among them, the unmanned automobile is recognized as the best way to greatly reduce traffic accidents, and thus becomes the leading edge and hot spot of the world traffic field.
The unmanned automobile is a composite system integrating environment perception, path planning and motion control, wherein the path planning is a bridge for the environment perception and vehicle control of the unmanned automobile, is a key technology for realizing important functions of vehicle task execution, active obstacle avoidance, automatic navigation and the like, and is the basis for autonomous driving of the unmanned automobile.
The unmanned vehicle path planning means that an effective path which is free of collision and can safely reach a target point is planned according to performance indexes after an unmanned vehicle starting point and the target point are given on the basis of a certain environment model. The path planning task can be broadly divided into a global path planning part and a local path planning part, wherein the global path planning part is used for searching a non-collision static geometric track from a starting point to a terminal point, mainly focuses on a road representation method, can not embody various dynamic or static obstacles such as pedestrians and vehicles on the road, and does not consider the factors such as the motion performance and the motion time of the vehicles; the local path planning is also called as movement path planning, focuses on considering the current local environment information of the vehicle, enables the unmanned vehicle to have good obstacle avoidance capacity, detects the working environment of the robot through the sensor to acquire the information such as the position and the geometric property of an obstacle, and is used for realizing the close-distance path planning for safely driving the vehicle in a local range to avoid the obstacle. The local path planning needs to consider factors such as the size, turning performance and movement speed of the vehicle, and ensure that the planned result can be correctly executed by the vehicle.
The existing unmanned driving path planning methods are numerous, the global path planning method comprises a Dubins path algorithm, an A star search algorithm, a genetic algorithm and the like, for example, the typical Dubins path algorithm is one of the most common, most extensive and famous global path planning methods for generating smooth paths, the Dubins path algorithm represents the shortest path for the forward driving of the robot, and the robot is formed by combining a plurality of groups of circular arcs and straight line segments, wherein the straight line segments are tangents of corresponding circular arcs. The method has the disadvantages that the method is discontinuous at the connecting point of the circular arc and the straight line, and if the vehicle is required to accurately travel according to a preset path, the vehicle must stop at the connecting point, then turn on the spot and start to travel. The A star search algorithm and the genetic algorithm are to establish a global road network represented in a point and line form, and then to find a proper global path track through different search strategies.
The local path planning mainly includes a graph search-based method, a random generation-based method, a trajectory generation-based method, an intelligent community algorithm-based method, and the like, but most methods are graph search-based methods. The classic a-star algorithm is implemented as follows: establishing a search grid, determining a starting point, a target point and an obstacle position, establishing an OPEN table and a CLOSE table, using the distance between the points as a cost, and adopting an evaluation function F which is G + H: f is the cost estimate from the initial state to the target state, G is the cost from the initial state to the next state, and H is the cost of the best path from the next state to the target state.
The local path planning and the global path planning are designed separately in the industry, and the method has the advantages that each part has universality and independence due to modular design, but the defects that the consideration is not combined with a bottom platform and the global environment overall planning, the mutual relevance is not strong, so that a lot of useful information is lost, and the method is not the optimal choice for specific unmanned automobile application.
Disclosure of Invention
The invention aims to provide a three-layer architecture-based unmanned vehicle path planning method, which can tightly couple top-layer road network information and bottom-layer local path planning aiming at a specific application scene, reserve more environmental information and platform performance information and improve the autonomous driving performance of an unmanned vehicle.
The technical scheme of the invention is as follows: a three-layer architecture-based unmanned vehicle path planning method comprises the following steps:
step 1: build a picture
Abstracting and mathematically describing a road of an application scene, and representing and storing the road;
step 2: applications of
And planning a path on the road network map by using the road network map established in the specific scene according to task requirements.
The step 1 comprises the following steps:
s11: determining the range of an application scene, acquiring a satellite Map of the scene, and acquiring a real driving trajectory Map Tra of the unmanned vehicle of the application scene;
s12: selecting key points of roads in a scene, and constructing a global road network layer Info _ Map;
s13: establishing a mapping relation (R, T, k) between Map and Tra, so that Map is k (R Tra + T);
s14: selecting a track section P between any two connected nodes ij from Tra according to the road network nodes of the global road network layerijForming a path track layer sigma P;
s15: constructing a Search List Info _ Map _ Search and an index List Info _ Map _ List;
s16: and finishing the construction of the graph.
In the step S11, the real driving trajectory graph Tra is actually run by the application, the driving trajectory graph Tra includes the satellite positioning information, and then the trajectory graph is thinned according to the coefficient dis _ Tra, and the value of dis _ Tra is between 0.5 m and 3 m.
In step S12, when the global road network layer is constructed, two nodes are used to represent a turn, three nodes are required to represent a three-way intersection in the Info _ Map, and four nodes are required to represent a cross-road intersection.
In step S14, the track segments forming the track layer of the path are obtained from the real track graph Tra, PijRepresenting the real track segment from node i to node j.
In step S15, the Search list Info _ Map _ Search is only related to the global road network layer Info _ Map, and defines the serial number of each road network node and the number of the adjacent nodes; the index List Info _ Map _ List defines the correspondence between the road network nodes and the path trajectory layer Σ P.
The step 2 comprises the following steps:
s21: inputting a target position TP and a current position CP, and setting parameters such as the size, the resolution and the like of a CostMap in a planning execution layer;
s22: searching in the Search List Info _ Map _ Search to obtain a path sequence List in the global network layer;
s23: finding out a corresponding track segment in the index List Info _ Map _ List according to the List, and generating a track path Guide _ Line in a path track layer;
s24: intercepting a desired path Guide Line Part _ Guide _ Line from the Guide _ Line according to the current position CP and the size of the CostMap;
s25: performing a local obstacle avoidance planning method based on an expected path guideline Part _ Guide _ Line on a path planning layer to obtain a local path planning result _ L;
s26: and outputting a result _ L.
In S22, the sequence point list between the target position TP and the current position CP can be calculated by using a conventional a-star search algorithm.
The improved a star search method is adopted in S25, and is combined with Part _ Guide _ Line, where f (i) ═ g (i) + H1(i) × α 1+ H2(i) × α 2+ H3(i) × α 3+ H4(keyPoint) × α 4, where H1(i) represents the minimum distance value between the node and the Guide Line Part _ Guide _ Line; h2(i) is the distance from the point corresponding to the minimum distance from the inode to the guideline to the target point; h3(i) is the distance between node i to keyPoint; h4(keyPoint) represents the distance from keyPoint to the target point; α 1, α 2, α 3, α 4 are weighting coefficients.
The invention has the beneficial effects that: (1) the global path planning and the local path planning are considered overall by utilizing a three-layer architecture, so that the global path planning and the local path planning are closely connected with a physical platform, more useful information is provided for the road local path planning, and the planning performance is improved; (2) aiming at specific unmanned technology application scenes such as unmanned transportation logistics in large parks, unmanned express delivery vehicles in districts, unmanned transportation trucks in ports and the like, the invention utilizes a global road network layer to represent a road network structure, and is flexible to use; (3) the third layer planning execution layer of the invention introduces the improved A star searching method based on the guide line, and utilizes the guide line and the key point, thereby not only reserving the local planning path which is in line with the expectation to the maximum extent, but also keeping the characteristic of flexible obstacle detouring. The unmanned aerial vehicle can be directly used in specific unmanned technology application scenes of unmanned transportation logistics in large parks, unmanned express delivery vehicles in districts, unmanned transportation trucks in ports and the like, can improve the unmanned technology, further popularize the application of unmanned products and generate better economic benefit.
Drawings
FIG. 1 is an application scenario satellite Map;
FIG. 2 is a real trajectory diagram Tra of the unmanned vehicle in an application scene;
FIG. 3 is a schematic diagram illustrating an effect of the generated global nexus layer Info _ Map;
FIG. 4 is a diagram illustrating the effect of mapping a real trace graph Tra to a global road network layer Info _ Map;
FIG. 5 is a diagram illustrating the effect of mapping a path trace layer to a global road network layer Info _ Map;
FIG. 6 is a schematic diagram of improved guideline-based star A search;
FIG. 7 is a schematic diagram illustrating an effect of a path planning method based on a three-layer architecture;
fig. 8 is a schematic diagram illustrating the effect of planning the execution layer.
Detailed Description
The invention is described in further detail below with reference to the figures and the embodiments.
The invention provides a three-layer architecture-based unmanned automobile path planning method aiming at specific unmanned technology application scenes of large-scale park unmanned transportation logistics, district unmanned express delivery vehicles, port unmanned transportation trucks and the like, and on the basis of comprehensively considering the motion characteristics of a bottom platform and the top road network structure information: the first layer of global road network layer increases the turning information according with the motion characteristics of a specific platform while keeping the advantages of the road network structure of a sparse point-line combination; the second layer of path track layer is composed of sparse real platform motion track segments, and the path generated by the planning algorithm can be guaranteed to be executed by the platform; and the third layer planning execution layer introduces a second layer planning track result as input on the basis of classical A-star search, can approach an expected path as much as possible, and retains the advantage of flexible obstacle avoidance of A-star search. Through the three-layer architecture, the path planning method provided by the invention can comprehensively plan the global path planning task and the local path planning task, furthest retains the scene information and the motion characteristics of a real platform, and is suitable for fixed unmanned automobile transportation occasions such as district express transportation, park logistics transportation, port logistics transportation and the like.
A three-layer architecture-based unmanned vehicle path planning method comprises the following steps:
step 1: building a graph;
the method comprises the steps of abstracting and mathematically describing the road of an application scene, representing and storing the road in a manner which can be understood by the unmanned automobile, and providing support for autonomous driving of the unmanned automobile in the scene. The method specifically comprises the following steps:
s11: determining the range of an application scene, and acquiring a satellite Map of the scene (as shown in fig. 1), wherein the scene is a typical garden scene in the embodiment, and an unmanned automobile can move on several roads in a garden; acquiring a true driving track graph Tra (shown in figure 2) of the unmanned automobile in an application scene; tra is run by the application platform on all feasible roads, the motion trajectories (satellite positioning coordinate information) of the roads are recorded, and then the sparsification is performed according to the coefficient dis _ Tra being 1, namely 1 meter, and as a result, as shown in fig. 3, the trajectories are obtained by repeated driving, and therefore, part of the trajectories in fig. 2 are overlapped.
S12: selecting key points of roads in a scene, constructing a global road network layer Info _ Map, and representing turning by using two nodes, as shown in FIG. 3; in order to take the turning characteristics of the unmanned platform into consideration, a three-way intersection in the Info _ Map needs to be represented by three nodes, and an intersection needs to be represented by four nodes, such as the three-way intersection represented by nodes (8, 7, 11) in fig. 3.
S13: in order to perform path planning more intuitively, a track Map needs to be projected onto a satellite Map, and therefore, a mapping relation (R, T, k) between the scene satellite Map and the real driving track Map Tra needs to be calculated, so that Map ═ k (R × (Tra + T)) has the effect as shown in fig. 4, wherein R represents a rotation coefficient, T represents a translation coefficient, and k represents a scaling coefficient;
s14: according to the road network nodes of the global road network layer, any two connected nodes, namely a track segment P between a node i and a node j, are selected from the real driving track graph TraijAnd forming a path trace layer sigma P. In this embodiment, the track segments between all two adjacent network nodes are shown in fig. 5;
s15: constructing a Search List Info _ Map _ Search and an index List Info _ Map _ List; the Search list Info _ Map _ Search stores the ID number of each road network node (i.e. road network node number) and information of neighboring nodes, as shown in table 1, so that the Info _ Map _ Search can completely represent the global road network layer.
Table 1 Search list Info _ Map _ Search
The index List Info _ Map _ List mainly represents a mapping relationship between the global road network layer and the path trace layer, and as shown in table 2, for two road network nodes adjacent to each group, each trace segment P is stored in the index ListijThe ID numbers of the starting point i and the end point j (i.e. the road network node number), the number and length of the track points used in the track segment between the two points, and the file names stored in the track points, so that the global road network layer and the path track layer can be associated through the index list, and the result as shown in fig. 5 is obtained.
Table 2 index List Info _ Map _ List
S16: and finishing the construction of the graph.
Secondly, the method comprises the following steps: application is carried out.
The unmanned automobile utilizes the road network map established in the specific scene to plan a path on the road network map according to task requirements, and key support is realized for autonomous driving.
S21: inputting a target position TP and a current position CP, and setting parameters such as the size, the resolution and the like of an obstacle map CostMap in a planning execution layer, wherein the obstacle map CostMap is generally provided by an environment perception module;
s22: searching in the Search List Info _ Map _ Search to obtain a path sequence List in the global network layer; the definition of the Search List Info _ Map _ Search is shown in table 1, and the distance between two adjacent points in the index List Info _ Map _ List is shown in table 2, so that the sequence point List between the target position TP and the current position CP can be calculated by using the conventional a-star Search algorithm;
s23: finding out a corresponding track segment in the index List Info _ Map _ List according to the List, and generating a track path Guide _ Line in a path track layer;
s24: intercepting a desired path Guide Line Part _ Guide _ Line from the Guide _ Line according to the current position CP and the size of the CostMap;
s25: a local obstacle avoidance planning method based on a desired path guideline Part _ Guide _ Line is performed on a path planning layer to obtain a local path planning result _ L, the local path planning result is realized by adopting an improved a-star algorithm based on a guideline, the main idea of the local path planning is given in fig. 6, and the steps are as follows:
the method comprises the following steps: inputting an initial point S with a direction, a target point T with the direction, a Guide Line Part _ Guide _ Line and a barrier map CostMap;
step two: generating a key point keyPoint according to the Guide Line Part _ Guide _ Line and the obstacle map;
the key point keyPoint is obtained in the following manner: finding out all obstacles falling on the guide line, calculating the edge points of the obstacles, marking the edge points as candidate key points keyPoint, and then selecting one point from a plurality of candidate key points keyPoint as the keyPoint according to the following principle: (1) user tendency, either from left obstacle detour or from right obstacle detour; (2) the side of the guide line with smaller distance dis from the obstacle; (3) a passable area where the candidate key point is located;
step three: establishing an OPEN table and a CLOSE table;
step four: setting an evaluation function
F(i)＝G(i)+H1(i)*α1+H2(i)*α2+H3(i)*α3+H4(keyPoint)*α4；
Wherein i represents the ith node, and G (i) represents the cost value from the initial point to the ith node; h1(i) represents a minimum distance value between the node and the guideline Part _ Guide _ Line; h2(i) is the distance between the point j corresponding to the minimum distance from the inode to the guideline and the target point; h3(i) is the distance between node i to keyPoint; h4(keyPoint) represents the distance from keyPoint to the target point; alpha 1, alpha 2, alpha 3 and alpha 4 are weight coefficients
Step five: calculating an evaluation function value F of the initial point S and putting the evaluation function value F into an OPEN table;
step six: sorting the points in the OPEN table from small to large according to the F value;
step seven: if the OPEN table is not empty, popping up a first node K sequenced in the OPEN table, otherwise, failing to calculate;
step eight: judging whether the node K is a target point or not, and if so, executing a step thirteen; otherwise, executing step nine;
step nine: expanding the adjacent nodes of the node K according to the direction and the turning characteristic of the vehicle;
step ten: calculating the evaluation value of each expansion node according to an evaluation function F (i);
step eleven: putting the expansion node with the evaluation value into an OPEN table, and putting the node K into a CLOSE table;
step twelve: executing the step six;
step thirteen: and outputting the node K and a series of father nodes thereof as search results, and finishing the algorithm.
Fig. 7 shows the whole process of the application of the path planning method based on the three-layer architecture, in the figure, a node 10 represents the current vehicle position, a node 8 represents a target position which needs to be reached, and a list is obtained by searching according to step 2, wherein the list is [10,9,8,11,12,13,18 ]; and obtaining track route Guide _ Line in all track planning layers corresponding to the List according to the index List Info _ Map _ List in the step 3, guiding local route planning in the planning execution layer by using the Guide _ Line (as shown in fig. 8), and performing obstacle avoidance planning to obtain an output result _ L.
S26: and outputting a result _ L.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (3)
1. A three-layer architecture-based unmanned vehicle path planning method is characterized by comprising the following steps:
step 1: build a picture
Abstracting and mathematically describing a road of an application scene, and representing and storing the road;
step 2: applications of
Planning a path on the road network map by using the road network map established by the application scene according to task requirements;
the step 1 comprises the following steps:
s11: determining the range of an application scene, acquiring a satellite Map of the scene, and acquiring a real driving trajectory Map Tra of the unmanned vehicle of the application scene;
s12: selecting key points of roads in a scene, and constructing a global road network layer Info _ Map;
s13: establishing a mapping relation (R, T, k) between Map and Tra, so that Map is k (R Tra + T);
wherein R represents a rotation coefficient, T represents a translation coefficient, and k represents a scaling coefficient;
s14: selecting a track segment P between any two connected nodes i and j from the Tra according to the road network nodes of the global road network layerijForming a path track layer sigma P;
s15: constructing a Search List Info _ Map _ Search and an index List Info _ Map _ List;
s16: completing the map building;
in the step S11, the real driving trajectory graph Tra is actually run by an application, the driving trajectory graph Tra includes satellite positioning information, and then the trajectory graph is thinned according to a coefficient dis _ Tra, and the value of dis _ Tra is between 0.5 m and 3 m;
in step S12, when constructing the global road network layer, two nodes are used to represent a turn, three nodes are needed to represent a three-way intersection in the Info _ Map, and four nodes are needed to represent a cross-way intersection;
in step S14, the track segments forming the track layer of the path are obtained from the real track graph Tra, PijRepresenting the real track segment from node i to node j;
in step S15, the Search list Info _ Map _ Search is only related to the global road network layer Info _ Map, and defines the serial number of each road network node and the number of the adjacent nodes; the index List Info _ Map _ List defines the corresponding relation between the road network nodes and the path track layer sigma P;
the step 2 comprises the following steps:
s21: inputting a target position TP and a current position CP, and setting the size and resolution parameters of a CostMap in a planning execution layer;
s22: searching in the Search List Info _ Map _ Search to obtain a path sequence List in the global network layer;
s23: finding out a corresponding track segment in the index List Info _ Map _ List according to the List, and generating a track path Guide _ Line in a path track layer;
s24: intercepting a desired path Guide Line Part _ Guide _ Line from the Guide _ Line according to the current position CP and the size of the CostMap;
s25: performing a local obstacle avoidance planning method based on an expected path guideline Part _ Guide _ Line on a path planning layer to obtain a local path planning result _ L;
s26: and outputting a result _ L.
2. The unmanned vehicle path planning method based on the three-layer architecture as claimed in claim 1, wherein: in S22, the sequence point List between the target position TP and the current position CP can be calculated by using the conventional a-star search algorithm.
3. The unmanned vehicle path planning method based on the three-layer architecture as claimed in claim 1, wherein: the improved a star search method is adopted in S25, and a Part _ Guide _ Line is combined, where f (i) ═ g (i) + H1(i) × α 1+ H2(i) × α 2+ H3(i) × α 3+ H4(keyPoint) × α 4, where H1(i) represents a minimum distance value between a node i and a Guide Line Part _ Guide _ Line; h2(i) is the distance from the point corresponding to the minimum distance from the inode to the guideline to the target point; h3(i) is the distance between node i to keyPoint; h4(keyPoint) represents the distance from keyPoint to the target point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010469972.0A CN111596664B (en) | 2020-05-28 | 2020-05-28 | Unmanned vehicle path planning method based on three-layer architecture |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010469972.0A CN111596664B (en) | 2020-05-28 | 2020-05-28 | Unmanned vehicle path planning method based on three-layer architecture |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111596664A CN111596664A (en) | 2020-08-28 |
| CN111596664B true CN111596664B (en) | 2021-08-10 |
Family
ID=72192248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010469972.0A Active CN111596664B (en) | 2020-05-28 | 2020-05-28 | Unmanned vehicle path planning method based on three-layer architecture |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111596664B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112990572A (en) * | 2021-03-12 | 2021-06-18 | 上海交通大学 | Dynamic scheduling system and method for park unmanned logistics vehicles |
| CN114286383A (en) * | 2021-12-27 | 2022-04-05 | 中国联合网络通信集团有限公司 | Network quality determination method, device and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009176223A (en) * | 2008-01-28 | 2009-08-06 | Geo Technical Laboratory Co Ltd | Data structure of route guidance database |
| CN104914866A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Tour inspection robot global path planning method based on topological point classification and system |
| CN105740964A (en) * | 2014-12-08 | 2016-07-06 | 吉林大学 | Urban road network data organization and shortest path rapid calculation method |
| CN106371445A (en) * | 2016-11-17 | 2017-02-01 | 浙江大学 | Unmanned vehicle planning control method based on topology map |
| CN110333659A (en) * | 2019-07-15 | 2019-10-15 | 中国人民解放军军事科学院国防科技创新研究院 | A kind of pilotless automobile local paths planning method based on improvement A star search |
-
2020
- 2020-05-28 CN CN202010469972.0A patent/CN111596664B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2009176223A (en) * | 2008-01-28 | 2009-08-06 | Geo Technical Laboratory Co Ltd | Data structure of route guidance database |
| CN105740964A (en) * | 2014-12-08 | 2016-07-06 | 吉林大学 | Urban road network data organization and shortest path rapid calculation method |
| CN104914866A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Tour inspection robot global path planning method based on topological point classification and system |
| CN106371445A (en) * | 2016-11-17 | 2017-02-01 | 浙江大学 | Unmanned vehicle planning control method based on topology map |
| CN110333659A (en) * | 2019-07-15 | 2019-10-15 | 中国人民解放军军事科学院国防科技创新研究院 | A kind of pilotless automobile local paths planning method based on improvement A star search |
Non-Patent Citations (1)
| Title |
|---|
| "Path Planning in Urban Area Using Local Features of the Road System";Csaba ANTONYA;《2017 2nd International Conference on Computational Modeling, Simulation and Applied Mathematics》;20171231;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111596664A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Jiang et al. | A flexible multi-layer map model designed for lane-level route planning in autonomous vehicles | |
| CN110333659B (en) | Unmanned vehicle local path planning method based on improved A star search | |
| Li et al. | Path planning based on combinaion of improved A-STAR algorithm and DWA algorithm | |
| CN111596664B (en) | Unmanned vehicle path planning method based on three-layer architecture | |
| CN110487290B (en) | Unmanned vehicle local path planning method based on variable step size A star search | |
| CN106643783A (en) | Shortest path Thiessen polygon-based electric vehicle charging station searching method | |
| CN111982142B (en) | Intelligent vehicle global path planning method based on improved A-star algorithm | |
| CN102435200A (en) | Rapid path planning method | |
| CN107402018A (en) | A kind of apparatus for guiding blind combinatorial path planing method based on successive frame | |
| CN113341991A (en) | Path optimization method based on dynamic window and redundant node filtering | |
| CN111337047B (en) | Unstructured road macroscopic path planning method based on multi-task point constraint | |
| CN115077550A (en) | Unmanned vehicle route planning method based on matching of navigation map and high-precision map | |
| CN112833904A (en) | Unmanned vehicle dynamic path planning method based on free space and fast search random tree algorithm | |
| Yijing et al. | Local path planning of autonomous vehicles based on A* algorithm with equal-step sampling | |
| Liu et al. | Design of a multi-layer lane-level map for vehicle route planning | |
| CN104699791A (en) | Lost floating car track path recovery method | |
| CN111272187B (en) | Optimal driving path planning method and system based on improved A-star algorithm | |
| CN116414139B (en) | Mobile robot complex path planning method based on A-Star algorithm | |
| CN117249842A (en) | Unmanned vehicle mixed track planning method based on track smooth optimization | |
| Meng et al. | Improved hybrid A-star algorithm for path planning in autonomous parking system based on multi-stage dynamic optimization | |
| CN116610109A (en) | Gradient-based forward ant colony algorithm unmanned vehicle path planning method | |
| CN114580796B (en) | Tour attribute path planning method and system | |
| Oh et al. | Coordinated road network search for multiple UAVs using dubins path | |
| CN112214037B (en) | Unmanned aerial vehicle remote sensing networking flight path planning method based on field station | |
| Zhang et al. | An efficient decision and planning method for high speed autonomous driving in dynamic environment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |