CN113467457A - Graph optimization path planning method for edge-pasting sweeping of unmanned sanitation vehicle - Google Patents

Graph optimization path planning method for edge-pasting sweeping of unmanned sanitation vehicle Download PDF

Info

Publication number
CN113467457A
CN113467457A CN202110770495.6A CN202110770495A CN113467457A CN 113467457 A CN113467457 A CN 113467457A CN 202110770495 A CN202110770495 A CN 202110770495A CN 113467457 A CN113467457 A CN 113467457A
Authority
CN
China
Prior art keywords
vehicle
edge
path planning
constraint
graph
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.)
Granted
Application number
CN202110770495.6A
Other languages
Chinese (zh)
Other versions
CN113467457B (en
Inventor
苏金亚
杨增辉
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.)
Wuxi Taiji Brain Intelligent Technology Co ltd
Original Assignee
Wuxi Taiji Brain Intelligent 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 Wuxi Taiji Brain Intelligent Technology Co ltd filed Critical Wuxi Taiji Brain Intelligent Technology Co ltd
Priority to CN202110770495.6A priority Critical patent/CN113467457B/en
Publication of CN113467457A publication Critical patent/CN113467457A/en
Application granted granted Critical
Publication of CN113467457B publication Critical patent/CN113467457B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

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
    • G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of 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
    • G05D1/0212—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

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 graph optimization path planning method for unmanned sanitation vehicle edge-pasting cleaning, which belongs to the technical field of path planning and comprises the following two steps: firstly, classifying obstacle targets; secondly, designing a constraint edge in a graph structure; the method adopts a cost function minimization-based graph optimization method to research the path planning problem during the welting cleaning of the sanitation vehicle, and can ensure that the sanitation vehicle can safely and effectively execute the welting cleaning task after adding welting constraints and integral cleaning efficiency constraints to vehicle state nodes in the graph according to different types of obstacles.

Description

Graph optimization path planning method for edge-pasting sweeping of unmanned sanitation vehicle
Technical Field
The invention relates to the technical field of path planning, in particular to a graph optimization path planning method for edge-pasting cleaning of an unmanned sanitation vehicle.
Background
The path planning is an important ring in a decision module of the unmanned vehicle, and integrates position information of obstacles around the vehicle and a pre-established environment map to plan a path which accords with a motion rule and can quickly reach a destination for the vehicle. Here we mainly pay attention to the problem of path planning on irregular road surfaces and applicable to low-speed unmanned sanitation vehicles.
Unmanned technology develops rapidly in recent years, and path planning algorithms suitable for various vehicles are emerging and perfected continuously. New challenges may follow when deploying the drone module onto a conventional sanitation vehicle. The traditional path planning algorithm only needs to guide the vehicle from a starting point to a target point and avoid obstacles, but the sanitation vehicle also needs to perform a cleaning task while driving, and cleaning along the road edge is one of the more typical scenes.
The welt cleaning operation of the sanitation vehicle requires that the path planning module not only safely guide the vehicle from a starting point to a target point, but also enable the vehicle cleaning disc to cover all road edges as far as possible in the shortest time, and when the vehicle approaches the road edges and cannot advance, a feasible recovery path is planned to continue the cleaning task. These characteristics are not satisfied by the traditional sampling and searching path planning algorithm. In the traditional method, all path points to be determined are assumed as unknown states needing to be calculated, the states comprise vehicle positions and yaw angles, the states are restrained by positions of obstacles, the states are restrained by motion rules of vehicles and driving time, and when all the states meet the minimum turning radius limitation and simultaneously keep enough redundant distance with the obstacles, a set of the states is a drivable path.
As shown in FIG. 8, { X0,X1,X2Represents the vehicle position and angle information to be calculated, the vehicle is from X0Go to X2Need to avoid quadrangular obstacle, so X1Need to be located to the left of the barrier; it does not take too long while avoiding the obstacle, and the time difference Δ t is kept as small as possible.
In order to plan the driving path of the unmanned vehicle in real time, a planning method based on sampling or searching generally utilizes the motion constraint of the vehicle to simplify a search space, for example, an optimal path is searched out in a forward driving area at certain intervals, but the method is limited by the range of the search space, and a proper reverse recovery path is usually planned without regulations. In the traditional path planning based on graph optimization, in order to safely avoid obstacles, a stable driving path close to a border cannot be planned.
Based on the method, the invention designs a graph optimization path planning method for the edge-attaching sweeping of the unmanned sanitation vehicle, so as to solve the problems.
Disclosure of Invention
The invention aims to research the path planning problem during the welting sweeping of an sanitation vehicle by adopting a cost function minimization-based graph optimization method, and provides a graph optimization path planning method for the welting sweeping of an unmanned sanitation vehicle.
In order to achieve the purpose, the invention provides the following technical scheme: a graph optimization path planning method for unmanned sanitation vehicle edge-pasting sweeping comprises the following two steps: firstly, classifying obstacle targets; secondly, designing nodes and edges in graph optimization;
classification of obstacle targets: conventional unmanned vehicles generally attribute road edges as non-collision contactable obstacles and need to maintain a sufficient safe redundant distance therewith, but unmanned sanitation vehicles often need to perform welt cleaning operations. Therefore, it is necessary to divide the obstacles around the vehicle into obstacles such as a road edge which cannot be passed over but needs to be as close as possible, or an obstacle such as a person or a vehicle which cannot be approached by the sanitation vehicle and needs to be detoured. In practice, it is found that roadside green plants are one of the most confusing objects with road edges, and particularly, when branches of green plants extend to the road or leaves continuously fall, the path planning algorithm needs to continue the welt planning without being affected by the green plants, and when an obstacle really exists to block the welt path, the vehicle needs to safely go around. Since the classification of obstacles is not the focus of this patent, it will not be explained in depth here.
Designing nodes and edges in graph optimization: when the number of vehicle states to be planned is large, the vehicle states need to be represented as a hypergraph structure consisting of nodes and edges so as to analyze the relation and the constraint between the state nodes. In the optimization of the graph, the position state of the vehicle needing to be planned is represented as a node, and the constraint borne by the node is represented as an edge.
The nodes are divided into two types, namely state nodes representing the position and the yaw angle of the vehicle; the second is a node representing the travel time between vehicle states. The types of edges also fall into two categories: the method comprises the following steps that firstly, constraints borne by adjacent vehicle state nodes, such as the limitation of turning radius, angular velocity and acceleration, are limited; the second is the constraint that the vehicle state node itself is subject to, such as the minimum distance from a certain obstacle or road edge.
The graph structure needs to be converted to a mathematical description before solving for the optimal set of vehicle states. The state nodes of the vehicle are denoted by X, including plane coordinates and yaw angle, and the set of these states in a certain path is denoted by Q:
Q＝{X1,X2...,Xn}
let Δ T denote the travel time node of the vehicle, T denotes its set:
T＝{Δt1,Δt2...,Δtn}
denote all node sets by B:
B＝(Q,T)
converting the path planning process into a solution B when solving the minimum value of an objective function f (B)*F (B) is composed of several constraint sub-functions fk(B) Composition B*The set of vehicle states in (1) is the final vehicle path:
f(B)＝∑γkfk(B)
B*＝argmin f(B)
albeit fk(B) The constraint objectives for the vehicle state are different, but the vehicle state is optimized to a certain fixed interval, and therefore has a similar calculation mode, where the lower boundary constraint function is calculated as follows:
Figure BDA0003153082940000031
unifying constraint functions of different scales to the same level by using normalization parameters s, nrAnd e is the optimized redundancy quantity.
For the problem of path planning during edge pasting and cleaning of the unmanned sanitation vehicle, the following three constraints are considered emphatically while the conventional constraint is kept: firstly, the road edge has attraction and repulsion effects on vehicle state nodes, and vehicles are attached to the road edge as much as possible but cannot cross the road edge; secondly, the stability of the vehicle in the welting process is kept as much as possible; and thirdly, the stable vehicle speed is maintained to improve the cleaning efficiency, the cleaning is not clean when the vehicle speed is too fast, and the cleaning efficiency is too low when the vehicle speed is too slow.
After the obstacles around the vehicle are classified, the unary edge of the vehicle state node is kept with a certain attractive force according to the required welting distance while being repelled by the road edge, and the constraint subfunction fedgeThe calculation is as follows:
Figure BDA0003153082940000041
wherein
Figure BDA0003153082940000042
For a three-segment objective function with both upper and lower boundaries, ± d represents the distance offset within the allowable range when the sanitation vehicle is welted.
Sanitation car keeps the stability of welt distance in the cleaning process not only can improve the life of hardware motor and can also improve the clean and tidy degree of cleaning, consequently can add the degree of becoming of change of welt distance into the constraint function:
Figure BDA0003153082940000043
wherein,
Figure BDA0003153082940000044
the mean value of the welt distances, N the number of vehicle state nodes, and δ the normalization parameter of the constraint function.
In the process of sweeping the welt of the sanitation vehicle, the driving speed of the sweeping disc and the vehicle needs to be adapted while keeping the welt so as to achieve the sweeping efficiency as high as possible, and the constraint is added into a subfunction:
Figure BDA0003153082940000045
wherein deltap,δvIs a normalized parameter of the distance traveled and the speed,
Figure BDA0003153082940000046
is the distance between the vehicle states, vi,vsThe speed corresponding to the vehicle state node and the rotating speed of the cleaning disc.
Compared with the prior art, the invention has the beneficial effects that: the method adopts a cost function minimization-based graph optimization method to research the path planning problem during the welting cleaning of the sanitation vehicle, and can ensure that the sanitation vehicle can safely and effectively execute the welting cleaning task after classifying the barrier nodes in the graph optimization and adding the stable welting constraint.
Of course, it is not necessary for any product in which the invention is practiced to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a state diagram of a path planning method according to the present invention;
FIG. 2 is a state diagram of the inventive curb at the "suction" cleaning pan boundary;
FIG. 3 is a diagram of an implementation state of the path planning method of the present invention in which a new stability constraint edge is added;
FIG. 4 is a diagram illustrating a straight-line welting state of a conventional drawing;
FIG. 5 is a diagram of the optimized straight-line welting state of the method of the present invention;
FIG. 6 is a turn welt diagram of a conventional drawing;
FIG. 7 is a diagram of the optimized turn welt state of the method of the present invention;
fig. 8 is a state diagram of a conventional method for calculating a path. .
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-7, the present invention provides a technical solution: a graph optimization path planning method for unmanned sanitation vehicle edge-pasting sweeping comprises the following two steps: firstly, classifying obstacle targets; secondly, designing nodes and edges in graph optimization.
Classification of obstacle targets: conventional unmanned vehicles generally attribute the curb as a non-bump contactable obstacle, requiring a sufficient safe redundant distance to be maintained therefrom. But the unmanned sanitation vehicle firstly needs to distinguish whether the surrounding obstacle is required to be close to the road edge all the time or to be far away from other objects which are detoured. In practice, it is found that roadside green plants are one of the most confusing objects with road edges. In particular, when green branches extend onto the road or leaves fall continuously, the path planning algorithm needs to continue welt planning without being affected by the green branches, and when there is indeed an obstacle blocking the welt path, the vehicle needs to go around safely. It is assumed herein that the barrier species information is known.
Designing nodes and edges in graph optimization: when the number of the vehicle states needing to be planned is large, the state variables and the constraints borne by the variables can be represented as nodes and edges in the hypergraph, and the association and the constraints among the nodes are convenient to analyze.
As shown in fig. 1, in the vehicle path planning problem, the position state of the vehicle can be represented as a node in the graph, and the constraint imposed on the node can be represented as an edge. The nodes are divided into two types, namely state nodes { X) representing horizontal and vertical coordinates and yaw angles of the vehicle0,X1,X2}; second, node { Δ t) representing travel time between vehicle states1,Δt2}. The types of edges also fall into two categories: one is the constraint between adjacent vehicle state nodes, such as the limitation of turning radius, angular velocity and acceleration, and the rectangular frame of velocity in the graph is a tableShowing the upper and lower limits of the linear speed; secondly, the vehicle state node is self-constrained, such as the minimum distance from a certain obstacle or road edge, and the obstacle rectangular box in the graph represents X1And X2The corresponding obstacle.
The graph structure needs to be converted to a mathematical description before solving for the optimal set of vehicle states. The state nodes of the vehicle are denoted by X, including plane coordinates and yaw angle, and the set of these states in a certain path is denoted by Q:
Q＝{X1,X2...,Xn}
let Δ T denote the travel time node of the vehicle, T denotes its set:
T＝{Δt1,Δt2...,Δtn}
denote all node sets by B:
B＝(Q,T)
converting the path planning process into a solution B when solving the minimum value of an objective function f (B)*F (B) is composed of several constraint sub-functions fk(B) Composition B*The set of vehicle states in (1) is the final vehicle path:
f(B)＝∑γkfk(B)
B*＝argmin f(B)
albeit fk(B) The constraint objectives for the vehicle state are different, but the vehicle state is optimized to a certain fixed interval, and therefore has a similar calculation mode, where the lower boundary constraint function is calculated as follows:
Figure BDA0003153082940000061
unifying constraint functions of different scales to the same level by using normalization parameters s, nrAnd e is the optimized redundancy quantity.
Although the traditional graph optimization method can plan a path from the starting point to the end point for the unmanned sweeper. However, since the sweeper cannot hit the road edge, when the road edge is used as an obstacle, the planned path point is not attached to the road edge due to the pushing-away function of the obstacle constraint function, so that the sweeper cannot sweep the garbage on the road edge. When the pushing-away effect of the obstacle constraint function is reduced, the path point cannot keep a safe distance with obstacles such as vehicles, people and the like. Thus, the "push-away" and "attract" effects are added simultaneously herein to the road edge to vehicle state node constraint function, such that the vehicle and road edge maintain a stable welt travel distance.
As shown in fig. 2, the curb also maintains a push-off action on the body of the unmanned sweeper truck while "attracting" the sweeper truck boundary, which is optimal when the sweeper truck boundary and curb happen to coincide.
As shown in FIG. 3, the graph structure adds an edge bound by the coexistence of repulsive force and attractive force on the basis of the traditional nodes and edges. This constraint subfunction
Figure BDA0003153082940000071
The calculation is as follows:
Figure BDA0003153082940000072
wherein
Figure BDA0003153082940000073
For a three-segment objective function with both upper and lower boundaries, ± d represents the distance offset within the allowable range when the sanitation vehicle is welted.
In order to avoid left-right oscillation of the vehicle body, the change degree of the vertical distance between the vehicle body and the road edge is added into the graph as a new stability constraint edge:
Figure BDA0003153082940000074
wherein,
Figure BDA0003153082940000075
is the mean of the vertical distances, N is the number of vehicle state nodesThe number, δ, is the normalized parameter of the constraint function.
In the process of sweeping the welt of the sanitation vehicle, the driving speed of the sweeping disc and the vehicle needs to be adapted while keeping the welt so as to achieve the sweeping efficiency as high as possible, and the constraint is added into a graph:
Figure BDA0003153082940000076
wherein deltap,δvIs a normalized parameter of the distance traveled and the speed,
Figure BDA0003153082940000077
is the distance between the vehicle states, vi,vsThe speed corresponding to the vehicle state node and the rotating speed of the cleaning disc.
As shown in fig. 4, the conventional graph optimizes the path planning straight-line welting situation: the distance from the road edge is far, and redundant maneuvering for backing into a target point occurs;
as shown in fig. 5, the straight-line welting situation of the method of the invention: the sweeping disc is just attached to the road edge, and the road points are uniformly and stably distributed;
as shown in fig. 6, the conventional graph optimizes the turn welting situation of the path plan: the distance from the road edge is far, and the condition of uneven path points occurs;
as shown in fig. 7, the method of the present invention is applied to the case of turning welting: the distance between the road and the road edge is short, and the turning is smooth and stable.
In conclusion, the method adopts a cost function minimization-based graph optimization method to research the path planning problem during the welting cleaning of the sanitation vehicle, and can ensure that the sanitation vehicle can safely and effectively execute the welting cleaning task after classifying the obstacles and adding the stable welting constraint in the graph.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended to be illustrative only. The preferred embodiments are not intended to be exhaustive or to limit the invention to the precise embodiments disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims (5)

1. A graph optimization path planning method for unmanned sanitation vehicle edge-pasting sweeping comprises the following two steps:
obstacle target classification: obstacles encountered by the sanitation vehicle are divided into two types, one type is a road edge which cannot be crossed but needs to be close as much as possible, and the other type is obstacles such as people or vehicles which cannot be close to the sanitation vehicle and need to be bypassed;
designing a graph structure: representing unknown vehicle states and constraints borne by the states as a hypergraph structure, and analyzing recursive associations and constraints among the vehicle states; in path planning, an unknown vehicle state is represented as nodes, and a constraint relation between the nodes is represented as an edge; nodes are divided into two categories: one is a state node X ═ X, (X, y, θ) indicating the vehicle position, yaw angle; second, a node Δ t representing travel time between vehicle states; the types of edges also fall into two categories: firstly, the constraints borne by adjacent vehicle state nodes comprise the limits of turning radius, angular velocity and acceleration; secondly, the vehicle state node is restrained by itself, including the minimum distance from a certain obstacle or road edge;
before solving the optimal vehicle state set, converting the graph structure into mathematical description; the state nodes of the vehicle are denoted by X, including plane coordinates and yaw angle, and the set of these states in a certain path is denoted by Q:
Q＝{X1,X2...,Xn}
let Δ T denote the travel time node of the vehicle, T denotes its set:
T＝{Δt1,Δt2...,Δtn}
denote all node sets by B:
B＝(Q,T)。
2. the graph-optimized path planning method for unmanned sanitation vehicle edge-to-edge sweeping according to claim 1, characterized in that: converting the path planning process into a solution B when solving the objective function f (B) to obtain the minimum value*F (B) is composed of several constraint sub-functions fk(B) Composition B*The set of vehicle states in (1) is the final vehicle path:
f(B)＝∑γkfk(B)
B*＝argmin f(B)
albeit fk(B) The constraint objectives for the vehicle state are different, but the vehicle state is optimized to a certain fixed interval, and therefore has a similar calculation mode, where the lower boundary constraint function is calculated as follows:
Figure FDA0003153082930000021
unifying constraint functions of different scales to the same level by using normalization parameters s, nrTo satisfy the optimal state of the constraint sub-function, e is the optimized redundancy amount.
3. The graph-optimized path planning method for unmanned sanitation vehicle edge-to-edge sweeping according to claim 2, characterized in that: after the obstacles around the vehicle are classified, the unary edge of the vehicle state node is kept with a certain attractive force according to the required welting distance while being repelled by the road edge, and the constraint subfunction fedgeThe calculation is as follows:
Figure FDA0003153082930000022
wherein
Figure FDA0003153082930000023
For a three-segment objective function with both upper and lower boundaries, ± d represents the distance excursion within the allowable range when the sanitation vehicle is welted.
4. The graph-optimized path planning method for unmanned sanitation vehicle edge-to-edge sweeping according to claim 2, characterized in that: sanitation car keeps the stability of welt distance in the cleaning process not only can improve the life of hardware motor and can also improve the clean and tidy degree of cleaning, consequently can add the degree of becoming of change of welt distance into the constraint function:
Figure FDA0003153082930000024
wherein,
Figure FDA0003153082930000025
the mean value of the welt distances, N the number of vehicle state nodes, and δ the normalization parameter of the constraint function.
5. The graph-optimized path planning method for unmanned sanitation vehicle edge-to-edge sweeping according to claim 2, characterized in that: in the process of sweeping the welt of the sanitation vehicle, the driving speed of the sweeping disc and the vehicle needs to be adapted while keeping the welt so as to achieve the sweeping efficiency as high as possible, and the constraint is added into a subfunction:
Figure FDA0003153082930000026
wherein deltap,δvIs a normalized parameter of the distance traveled and the speed,
Figure FDA0003153082930000031
is the distance between the vehicle states, vi,vsThe speed corresponding to the vehicle state node and the rotating speed of the cleaning disc.
CN202110770495.6A 2021-07-08 2021-07-08 Graph optimization path planning method for edge-attached cleaning of unmanned sanitation truck Active CN113467457B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110770495.6A CN113467457B (en) 2021-07-08 2021-07-08 Graph optimization path planning method for edge-attached cleaning of unmanned sanitation truck

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110770495.6A CN113467457B (en) 2021-07-08 2021-07-08 Graph optimization path planning method for edge-attached cleaning of unmanned sanitation truck

Publications (2)

Publication Number Publication Date
CN113467457A true CN113467457A (en) 2021-10-01
CN113467457B CN113467457B (en) 2024-07-26

Family

ID=77879091

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110770495.6A Active CN113467457B (en) 2021-07-08 2021-07-08 Graph optimization path planning method for edge-attached cleaning of unmanned sanitation truck

Country Status (1)

Country Link
CN (1) CN113467457B (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113863195A (en) * 2021-11-03 2021-12-31 安徽酷哇机器人有限公司 Edge cleaning method and sweeper
WO2023092835A1 (en) * 2021-11-26 2023-06-01 上海仙途智能科技有限公司 Obstacle avoidance during edgewise sweeping of unmanned sweeper

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105759820A (en) * 2016-04-08 2016-07-13 济宁中科先进技术研究院有限公司 Road autonomous cleaning control system and method based on laser and vision
US20170168485A1 (en) * 2015-12-14 2017-06-15 Mitsubishi Electric Research Laboratories, Inc. System and Method for Controlling Autonomous Vehicles
CN107563426A (en) * 2017-08-25 2018-01-09 清华大学 A kind of learning method of locomotive operation temporal aspect
CN108674415A (en) * 2018-04-18 2018-10-19 北京汽车集团有限公司 Control method for vehicle and device
CN110749333A (en) * 2019-11-07 2020-02-04 中南大学 Unmanned vehicle motion planning method based on multi-objective optimization
CN111258316A (en) * 2020-01-20 2020-06-09 浙江工业大学 Robot trajectory planning method for trend perception in dynamic environment
CN111736603A (en) * 2020-06-22 2020-10-02 广州赛特智能科技有限公司 Unmanned sweeper and long-distance welting sweeping method thereof
CN111879307A (en) * 2020-06-22 2020-11-03 国网河北省电力有限公司信息通信分公司 Vehicle path planning method based on vehicle body parameters and engineering construction information
CN112193244A (en) * 2020-09-30 2021-01-08 浙江大学 Automatic driving vehicle motion planning method based on linear constraint

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170168485A1 (en) * 2015-12-14 2017-06-15 Mitsubishi Electric Research Laboratories, Inc. System and Method for Controlling Autonomous Vehicles
CN105759820A (en) * 2016-04-08 2016-07-13 济宁中科先进技术研究院有限公司 Road autonomous cleaning control system and method based on laser and vision
CN107563426A (en) * 2017-08-25 2018-01-09 清华大学 A kind of learning method of locomotive operation temporal aspect
CN108674415A (en) * 2018-04-18 2018-10-19 北京汽车集团有限公司 Control method for vehicle and device
CN110749333A (en) * 2019-11-07 2020-02-04 中南大学 Unmanned vehicle motion planning method based on multi-objective optimization
CN111258316A (en) * 2020-01-20 2020-06-09 浙江工业大学 Robot trajectory planning method for trend perception in dynamic environment
CN111736603A (en) * 2020-06-22 2020-10-02 广州赛特智能科技有限公司 Unmanned sweeper and long-distance welting sweeping method thereof
CN111879307A (en) * 2020-06-22 2020-11-03 国网河北省电力有限公司信息通信分公司 Vehicle path planning method based on vehicle body parameters and engineering construction information
CN112193244A (en) * 2020-09-30 2021-01-08 浙江大学 Automatic driving vehicle motion planning method based on linear constraint

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
王力虎 等: "一种室内自主清扫机器人的路径规划算法", 机床与液压, no. 07, pages 84 - 86 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113863195A (en) * 2021-11-03 2021-12-31 安徽酷哇机器人有限公司 Edge cleaning method and sweeper
WO2023092835A1 (en) * 2021-11-26 2023-06-01 上海仙途智能科技有限公司 Obstacle avoidance during edgewise sweeping of unmanned sweeper

Also Published As

Publication number Publication date
CN113467457B (en) 2024-07-26

Similar Documents

Publication Publication Date Title
Badue et al. Self-driving cars: A survey
CN113467457A (en) Graph optimization path planning method for edge-pasting sweeping of unmanned sanitation vehicle
EP3678911B1 (en) Pedestrian behavior predictions for autonomous vehicles
CN111982143B (en) Vehicle and vehicle path planning method and device
CN111736603A (en) Unmanned sweeper and long-distance welting sweeping method thereof
US20080059015A1 (en) Software architecture for high-speed traversal of prescribed routes
US10578443B2 (en) Method for re-mapping safe and traversable routes
CN112798002A (en) Intelligent vehicle autonomous path planning method and system and readable storage medium
Reda et al. Path planning algorithms in the autonomous driving system: A comprehensive review
CN104590259A (en) Track searching method and system
CN113432610B (en) Robot passing planning method and device, robot and storage medium
CN115571130A (en) Vehicle lane change assisting method and system based on lane reference line
CN114372375A (en) Method and system for solving safe driving area of off-road vehicle
CN115546749A (en) Road surface depression detection, cleaning and avoidance method based on camera and laser radar
Shah et al. Offline reinforcement learning for visual navigation
CN112798001A (en) Garbage disposal platform path planning method and system based on Internet of things and readable storage medium
López et al. A new approach to local navigation for autonomous driving vehicles based on the curvature velocity method
CN116243724A (en) Unmanned aerial vehicle path planning method based on A-algorithm and improved minimized snap
WO2023092835A1 (en) Obstacle avoidance during edgewise sweeping of unmanned sweeper
Li et al. Coarse-to-fine segmentation on lidar point clouds in spherical coordinate and beyond
Yan et al. RH-Map: Online Map Construction Framework of Dynamic Object Removal Based on 3D Region-wise Hash Map Structure
Gao et al. Design and Implementation of an Autonomous Driving Delivery Robot
Saska et al. Roads sweeping by unmanned multi-vehicle formations
Rosenfeld et al. Unsupervised surface classification to enhance the control performance of a UGV
Petrovskaya et al. Model based vehicle tracking in urban environments

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