CN114756034A - Robot real-time obstacle avoidance path planning method and device - Google Patents
Robot real-time obstacle avoidance path planning method and device Download PDFInfo
- Publication number
- CN114756034A CN114756034A CN202210663255.0A CN202210663255A CN114756034A CN 114756034 A CN114756034 A CN 114756034A CN 202210663255 A CN202210663255 A CN 202210663255A CN 114756034 A CN114756034 A CN 114756034A
- Authority
- CN
- China
- Prior art keywords
- path
- robot
- routing inspection
- inspection
- position information
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 238000007689 inspection Methods 0.000 claims abstract description 220
- 238000004891 communication Methods 0.000 claims description 24
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000002360 preparation method Methods 0.000 claims description 11
- 238000001816 cooling Methods 0.000 claims description 10
- 238000009826 distribution Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000002922 simulated annealing Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000009827 uniform distribution Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 8
- 238000012986 modification Methods 0.000 description 8
- 230000004048 modification Effects 0.000 description 8
- 238000004422 calculation algorithm Methods 0.000 description 5
- 238000005457 optimization Methods 0.000 description 5
- 238000000137 annealing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005070 sampling 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
- G05D1/0214—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
- G05D1/0217—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory in accordance with energy consumption, time reduction or distance reduction criteria
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
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 method and a device for planning a real-time obstacle avoidance path of a robot, wherein the method comprises the following steps: collecting work area information and constructing a work area map; arranging inspection points based on the working area information, and acquiring inspection point information according to the working area map; constructing a topological graph according to the routing inspection point information; acquiring current position information and target inspection point position information of the robot; calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph; guiding the robot to move according to the optimal routing inspection path, and replanning the path when the obstacle is detected; the method can enable the robot to detect the obstacles in real time and replan the path in the process of traveling according to the planned path, can effectively deal with emergency situations, and has the advantages of high path planning accuracy, good stability and strong safety.
Description
Technical Field
The invention relates to the technical field of inspection robots, in particular to a method and a device for planning a real-time obstacle avoidance path of a robot.
Background
With the development of informatization intelligence, the intelligent inspection robot gradually becomes an important component in the Internet operation and maintenance machine room environment, is favored by enterprises of various Internet companies, and develops more and more mature. In recent years, an inspection system taking an intelligent inspection robot as a core realizes the functions of automatic inspection of daily equipment, asset inventory, instruction arrival, one-key return and the like of an internet machine room, and provides necessary technical support for unmanned inspection of the machine room.
The global shortest path planning of robot fixed-point inspection is to autonomously find a shortest path from a starting point to a target point through a plurality of stop points according to the communication relation among inspection points. The following two problems are involved in path planning: firstly, the robot smoothly walks to a terminal point according to a planned path; secondly, the robot can smoothly bypass the obstacle section when encountering the obstacle. In the existing research, the gravity center always falls on the control optimization of a robot chassis and the collection and analysis processing of routing inspection information, and the optimization of a routing inspection path planning method is not enough.
For example, patent document CN114253258A discloses a global path planning method for a mobile robot, which plans a feasible path of the mobile robot according to a starting point, a target point and an obstacle distribution, forms a backbone path from the feasible path, and connects the new starting point and the target point to the backbone path by using a local path planning method to obtain a final feasible path.
The scheme can consider the avoidance of the obstacle in the path planning process, but does not effectively process the encountered emergency in real time, and cannot plan the path again after encountering the obstacle.
Disclosure of Invention
The invention provides a method and a device for planning a real-time obstacle avoidance path of a robot, which can effectively cope with emergency situations by detecting obstacles in real time and replanning the path in the process of travelling according to the planned path, and have the advantages of high path planning accuracy, good stability and strong safety.
A robot real-time obstacle avoidance path planning method comprises the following steps:
collecting work area information and constructing a work area map;
arranging patrol points based on the work area information, and acquiring patrol point information according to the work area map;
constructing a topological graph according to the routing inspection point information;
acquiring current position information and target inspection point position information of the robot;
calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
and guiding the robot to move according to the optimal routing inspection path, and replanning the path when the obstacle is detected.
Further, the inspection point comprises a data acquisition point, a charging point and a charging preparation point;
The inspection point information comprises inspection point position information and a communication relation between inspection points.
Furthermore, after the patrol point is configured based on the working area information and the patrol point information is acquired according to the working area map, the method further comprises the following steps:
establishing a database based on the routing inspection point position information and the communication relation between routing inspection points;
constructing a topological graph according to the routing inspection point information, comprising the following steps:
reading routing inspection point position information and the communication relation between routing inspection points from the database;
calculating the distance between the inspection points according to the inspection point position information and the communication relation between the inspection points;
and constructing a topological graph by taking the inspection points as vertexes and taking the distance between the inspection points as a weight according to the communication relation between the inspection points.
Further, according to the current position information of the robot, the position information of the target inspection point and the topological graph, calculating an optimal inspection path, including:
calculating to obtain the shortest path between each target inspection point and other target inspection points according to the position information of the target inspection points and the topological graph;
generating a plurality of alternative routing inspection paths for inspecting the target routing inspection points according to different routing inspection sequences, and calculating the lengths of the alternative routing inspection paths according to the shortest paths between each target routing inspection point and other target routing inspection points;
And respectively calculating the distances between the current position of the robot and the starting points of the multiple alternative routing inspection paths, and respectively overlapping the distances with the alternative routing inspection paths to obtain the total path length, wherein the path with the shortest total path length is the optimal routing inspection path.
Further, a plurality of alternative routing inspection paths for routing inspection of the target routing inspection points according to different routing inspection sequences are generated, and the alternative routing inspection paths comprise:
setting initial temperature, cooling gradient, finishing temperature, cycle times, path number, discarding probability and probability parameter range at each temperature, and randomly generating path sequences with corresponding number according to the set path number;
and from the initial temperature, iteratively executing the following operations at each temperature according to the cycle times to obtain alternative routing inspection paths at each temperature, and stopping until the alternative routing inspection paths are lower than the end temperature:
calculating the path lengths corresponding to the current multiple path sequences, and taking the path sequence with the shortest path length as a current optimal path;
the current optimal path is reserved, other path sequences are updated based on neighborhood change, the updated path length is calculated, if the updated path length is smaller than the path length before updating, the updated path sequence is accepted, and if not, the path sequence before updating is reserved;
Calculating the current discarding probability according to the previous discarding probability and the probability parameter, generating a random probability for each path sequence, judging whether the random probability of each path sequence is greater than the current discarding probability, if so, randomly generating a new path sequence, and if not, keeping the path sequence;
calculating the path length corresponding to each path sequence, sequencing according to the path length, and reserving a half path sequence with a smaller path length; for the other half path sequence with larger path length, randomly generating a corresponding number of new path sequences, judging whether the path length of the new path sequence is smaller than that of the original path sequence, if so, accepting the new path sequence, and if not, judging whether to accept the new path sequence according to the simulated annealing acceptance probability; and cooling according to the cooling gradient.
Further, updating the other path sequence based on the neighborhood change includes:
randomly selecting a preset number of routing inspection points in the path sequence to be updated as operators, and partially reserving or rearranging and combining the routing inspection points in the neighborhood interval of the operators to generate a new path sequence;
the preset number is two, three or five, wherein the probability of executing two operators is as follows:
Wherein, PGIn order to execute the probability calculated by adopting two operators, S is the maximum iteration number, and N is the current iteration round.
Further, the current discarding probability is calculated according to the previous discarding probability and the probability parameter, and is expressed by the following formula:
wherein, P1For the current discard probability, P0For the last discard probability, λ1For a preset minimum value of the probability parameter, λ2A is a random value generated according to (0,1) uniform distribution, and B is a random value generated according to F distribution.
Further, re-planning the path upon detection of the obstacle includes:
guiding the robot which detects the obstacle to stop moving, and collecting environmental information around the robot;
calculating the walking width according to the environment information, and judging whether the robot can bypass the obstacle, and when the robot can bypass the obstacle, guiding the robot to move according to the optimal routing inspection path after bypassing the obstacle;
when the robot cannot get around the obstacle, acquiring obstacle position information and deleting the communication relation including the position of the obstacle in the topological graph to obtain an obstacle avoidance topological graph;
Acquiring current position information of the robot and position information of a next target routing inspection point, and replanning an obstacle avoidance path according to the obstacle avoidance topological graph;
when the robot cannot plan an obstacle avoidance path, acquiring information of a charging preparation point, and replanning an obstacle avoidance return path according to the obstacle avoidance topological graph;
and generating and outputting an error reporting signal when the robot cannot plan an obstacle avoidance return path.
Further, when the robot can get around the obstacle, the walkable width satisfies the following relational expression:
wherein r is the radius of the robot, D is the preset expansion radius, and D is the walkable width.
A robot real-time obstacle avoidance path planning device applied to the method comprises the following steps:
the acquisition module is used for acquiring the information of the working area and constructing a working area map;
the configuration module is used for configuring the inspection points based on the working area information and acquiring the inspection point information according to the working area map;
the topology establishing module is used for establishing a topological graph according to the routing inspection point information;
the positioning module is used for acquiring the current position information of the robot and the position information of the target inspection point;
the calculation module is used for calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
And the obstacle avoidance module is used for guiding the robot to move according to the optimal routing inspection path and replanning the path when the obstacle is detected.
The invention provides a method and a device for planning a real-time obstacle avoidance path of a robot, which at least have the following beneficial effects:
(1) the routing inspection point information is constructed into a topological graph for shortest path planning, the obstacles are detected in real time in the process of traveling according to the planned path, and the obstacles are bypassed or the path is re-planned immediately when the obstacles are detected, so that the emergency situation can be effectively responded, and the safety is high.
(2) The positions and the communication relations of the inspection points are converted into vertexes and edges in the topological graph, and the distance between the inspection points is calculated to determine the weight, so that the path planning problem between the inspection points is converted into the problem of solving the shortest connecting line of the vertexes in the topological graph, and the path planning efficiency is improved.
(3) The simulation annealing algorithm is improved, multiple optimal alternative routing inspection paths are generated through calculation amount as less as possible, accidental errors can be effectively avoided, the alternative routing inspection paths are prevented from being trapped in local optimization, and accuracy and efficiency of path planning are improved.
(4) In the path planning process, the current discarding probability is calculated according to the previous discarding probability and the probability parameter instead of the discarding probability which is kept constant, so that not only can a large number of better path sequences be prevented from being discarded by mistake, but also the calculation speed can be increased, and the accuracy and the efficiency of path planning are improved.
Drawings
Fig. 1 is a flowchart of an embodiment of a method for planning a real-time obstacle avoidance path of a robot according to the present invention.
Fig. 2 is a flowchart of an embodiment of a method for generating a plurality of alternative routing inspection paths in the path planning method provided by the present invention.
Fig. 3 is a flowchart of an embodiment of a method for replanning a path when an obstacle avoidance object is detected in the path planning method according to the present invention.
Fig. 4 is a schematic structural diagram of an embodiment of the real-time obstacle avoidance path planning apparatus for a robot according to the present invention.
Reference numerals: 101-acquisition module, 102-configuration module, 103-topology establishment module, 104-positioning module, 105-calculation module and 106-obstacle avoidance module.
Detailed Description
In order to better understand the technical solution, the technical solution will be described in detail with reference to the drawings and the specific embodiments.
Referring to fig. 1, in some embodiments, there is provided a robot real-time obstacle avoidance path planning method, including:
s1, collecting work area information and constructing a work area map;
s2, arranging patrol points based on the working area information, and acquiring patrol point information according to the working area map;
s3, constructing a topological graph according to the routing inspection point information;
S4, acquiring the current position information of the robot and the position information of the target patrol point;
s5, calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
and S6, guiding the robot to move according to the optimal routing inspection path, and replanning the path when the obstacle is detected.
Specifically, in step S1, the work area map constructed is a grid map. In a specific application scene, when the intelligent inspection robot reaches the machine room environment for the first time, the robot is manually operated to inspect a circle around the machine room to be inspected, a laser sensor arranged on the robot is used for scanning the surrounding environment, the robot walks to each corner as far as possible to acquire working area information, and a relatively complete machine room grid map is constructed and stored. The grid map of the working area is a two-dimensional coordinate array, and the subsequent steps are realized by taking the grid map of the working area as a reference system.
In step S2, after the work area map is obtained, the required inspection points are configured according to the work area information, and the inspection point information of the inspection points in the work area map is obtained, where the inspection point information includes the inspection point position information and the communication relationship between the inspection points. The inspection points mainly comprise three types, namely data acquisition points, charging points and charging preparation points. The data acquisition point is a main inspection object, such as cabinet equipment of a machine room; the charging point is the position of the charging pile; the preparation point that charges is the position of filling electric pile dead ahead distance and filling electric pile preset distance. Preferably, the charging preparation point is located at a position which is 0.5m away from the charging pile right in front of the charging pile.
As a preferred embodiment, after configuring the patrol point based on the work area information and acquiring patrol point information according to the work area map, the method further includes: and establishing a database based on the routing inspection point position information and the communication relation between the routing inspection points. And storing the information of the inspection points into a database table, and correspondingly configuring the communication relationship between every two inspection points. In the database, the routing inspection point information can be adjusted and modified correspondingly by logging in the database table.
In a specific application scenario, a database is established, a data table is newly established in the database, and the database table comprises a routing inspection point basic information table and a communication relation table between routing inspection points. The inspection point basic information table comprises the number of inspection points, the types of the inspection points, coordinate point information of the inspection points in a map, data creation time and data modification time. The connection relation table between the inspection points stores the number of the inspection point, the number list of other inspection points which can reach the inspection point, the data creation time and the data modification time. And when the information in the database is modified, the data modification time of the corresponding column is updated.
In step S3, a topological graph is constructed according to the inspection point information, including:
S31, reading the position information of the routing inspection points and the communication relation among the routing inspection points from the database;
s32, calculating the distance between the inspection points according to the inspection point position information and the communication relation between the inspection points;
and S33, constructing a topological graph by taking the inspection points as vertexes and taking the distances between the inspection points as weights according to the communication relation between the inspection points.
In step S32, the distance between the inspection points is calculated as follows:
D= max(|x1−x2|, |y1−y2|)；
wherein the coordinate of one inspection point is (x)1, y1) The other patrol point has the coordinate of (x)2, y2)。
In step S5, calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point, and the topological graph, including:
s51, calculating to obtain the shortest path between each target inspection point and other target inspection points according to the target inspection point position information and the topological graph;
s52, generating a plurality of alternative routing inspection paths for routing inspection of the target routing inspection points according to different routing inspection sequences, and calculating the lengths of the alternative routing inspection paths according to the shortest path between each target routing inspection point and other target routing inspection points;
and S53, respectively calculating the distances between the current position of the robot and the starting points of the multiple alternative routing inspection paths, and respectively overlapping the distances with the alternative routing inspection paths to obtain the total length of the paths, wherein the path with the shortest total length is the optimal routing inspection path.
In step S51, in each inspection, a shortest path between each target inspection point and other target inspection points is calculated by passing through a plurality of target inspection points, and a Dijkstra algorithm is adopted. In the topological graph, calculating the shortest path between patrol points is equivalent to finding the shortest path between vertices in the topological graph and between the vertices. The Dijkstra algorithm is used for calculating the shortest path from one vertex to other vertices, and the shortest path is expanded outwards layer by layer from the starting point as the center until the calculation is finished to the end point.
Referring to fig. 2, in step S52, a plurality of alternative routing paths for routing a target routing point in different routing orders are generated, including:
s521, setting an initial temperature, a cooling gradient, an end temperature, the cycle number, the path number, the discarding probability and the probability parameter range at each temperature, and randomly generating path sequences with corresponding number according to the set path number;
s522, starting from the initial temperature, iteratively executing the following operations at each temperature according to the cycle number, and obtaining alternative routing inspection paths at each temperature until the alternative routing inspection paths are lower than the end temperature:
s5221, calculating the path lengths corresponding to the current path sequences, and taking the path sequence with the shortest path length as the current optimal path;
S5222, reserving the current optimal path, updating other path sequences based on neighborhood change, calculating the updated path length, receiving the updated path sequence if the updated path length is smaller than the path length before updating, and reserving the path sequence before updating if the updated path length is not smaller than the path length before updating;
s5223, calculating the current discarding probability according to the previous discarding probability and the probability parameters, generating a random probability for each path sequence, judging whether the random probability of each path sequence is greater than the current discarding probability, if so, randomly generating a new path sequence, and if not, keeping the path sequence;
s5224, calculating the path length corresponding to each path sequence, sequencing according to the path length, and reserving a half path sequence with a smaller path length; for the other half path sequence with larger path length, randomly generating a corresponding number of new path sequences, judging whether the path length of the new path sequence is smaller than that of the original path sequence, if so, accepting the new path sequence, and if not, judging whether to accept the new path sequence according to the simulated annealing acceptance probability; and cooling according to the cooling gradient.
In step S5222, updating other path sequences based on the neighborhood change includes:
randomly selecting a preset number of routing inspection points in the path sequence to be updated as operators, and partially reserving or rearranging and combining the routing inspection points in the neighborhood region of the operators to generate a new path sequence. The preset number is two, three or five.
In a specific application scenario, it is assumed that a path sequence to be updated is P (1) = (1,2,3,4,5,6,7,8,9,10), (1,2,3,4,5,6,7,8,9,10) as a label of a target inspection point, when the preset number is two, any two inspection points in the path sequence to be updated are randomly selected as operators, and inspection points in an operator neighborhood interval are partially reserved or sequentially turned, for example, when the selected operators are 4 and 8, sequences of the two operators may be rearranged and combined or may be left unchanged, and a sequence of inspection points in the operator neighborhood interval may be turned or may be left unchanged, which may include, but is not limited to, the following path sequences: p (2) = (1,2,3,8,7,6,5,4,9,10), P (3) = (3,2,1,4,5,6,7,8,9,10), P (4) = (1,2,3,4,5,6,7,8,10, 9); when the preset number is three, randomly selecting any three routing inspection points in the path sequence to be updated as operators, and partially reserving or rearranging and combining the routing inspection points in the neighborhood of the operators, for example, when the selected operators are 3,6 and 9, the following path sequences may be obtained, including but not limited to: p (5) = (1,2,5,4,3,8,7,6,9,10), P (6) = (2,1,5,4,3,6,7,8,10,9), P (7) = (2,1,3,4,5,8,7,6,10,9), P (8) = (2,1,5,4,3,8,7,6,10, 9); when the preset number is five, randomly selecting any five routing inspection points in the path sequence to be updated as operators, and partially reserving or rearranging and combining the routing inspection points in the neighborhood of the operators, for example, when the selected operators are 2, 4, 6, 8 and 10, the path sequence including but not limited to the following path sequence may be obtained: p (9) = (1,8,9,6,7,4,5,2,3, 10).
Wherein the probability of executing two operators is as follows:
wherein, PGIn order to execute the probability calculated by adopting two operators, S is the maximum iteration number, and N is the current iteration turn.
The calculation amount required for executing the operation of the two operators is larger, and meanwhile, the convergence can be achieved more quickly. Therefore, in order to obtain a better path sequence more quickly with less calculation cost, the present embodiment sets the probability of executing two operators, so that the probability of executing calculation with two operators increases with the increase of the iteration rounds.
In step S5223, the current discarding probability is calculated according to the previous discarding probability and the probability parameter, and is expressed by the following formula:
wherein, P1For the current drop probability, P0For the last discard probability, λ1For a preset minimum value of the probability parameter, lambda2For the preset maximum value of the probability parameter, A is a random value generated according to (0,1) uniform distribution, B is a random value generated according to F distribution, and the F distribution is a sampling distribution of the ratio of each of two independent random variables subjected to chi-square distribution divided by the degree of freedom of the independent random variables and is asymmetric distribution.
In step S5224, the adjusted simulated annealing algorithm is adopted, and the core idea is to accept a solution better than the current solution and accept a solution worse than the current solution with a certain probability, and then continue the search with the new solution. And receiving the path sequence with the smaller path length, and judging whether to receive a new path sequence with the larger path length according to the receiving probability of the simulated annealing, thereby avoiding the obtained global optimal path from falling into local optimization.
Wherein, the acceptance probability of the simulated annealing is calculated by the following formula:
wherein, L (P (i)) is the current path length, L (P (i + 1)) is the new path length, and T is the current cooling iteration round.
Referring to fig. 3, in step S6, the robot walks according to the planned optimal routing inspection path, and if no obstacle accidentally appears in the environment, the robot directly reaches the routing inspection point and completes the subsequent routing inspection task. Replanning the path upon detection of the obstacle, comprising:
s61, guiding the robot which detects the obstacle to stop moving, and collecting the environmental information around the robot;
s62, calculating the walking width according to the environment information, and judging whether the robot can bypass the obstacle, and when the robot can bypass the obstacle, guiding the robot to continue to move according to the optimal routing inspection path after bypassing the obstacle;
s63, when the robot cannot get around the obstacle, acquiring obstacle position information and deleting the communication relation including the position of the obstacle in the topological graph to obtain an obstacle avoidance topological graph;
s64, acquiring current position information of the robot and position information of a next target inspection point, and replanning an obstacle avoidance path according to the obstacle avoidance topological graph;
S65, when the robot cannot plan an obstacle avoidance path, acquiring position information of a charging preparation point, and replanning an obstacle avoidance return path according to the obstacle avoidance topological graph;
and S66, generating and outputting an error signal when the robot cannot plan an obstacle avoidance return path.
In step S61, during the operation of the robot, the laser sensor, the infrared sensor, and the ultrasonic sensor collect obstacle information to determine whether an obstacle exists in front of the robot. If the obstacle exists, the robot stops moving, and the surrounding environment is scanned and modeled through the laser radar so as to obtain environment information and prepare for calculating the width of the obstacle.
In step S62, the size of the robot is known, and the radius of the robot can be obtained, and for safety, when the robot can avoid the obstacle or the cabinet, and the obstacle can be avoided, the robot is determined to be able to bypass the obstacle by comparing the walking width, an expansion distance is preset and added to the radius of the robot, so as to avoid the collision better. When the robot can get around the obstacle, the walking width satisfies the following relational expression:
wherein r is the radius of the robot, D is the preset expansion radius, and D is the walking width.
When the walking width does not satisfy the above relational expression, the robot determines that the obstacle cannot be bypassed. When the robot determines that the obstacle can be bypassed but the bypass has failed, step S63 is continuously executed for the robot as if the robot determines that the obstacle cannot be bypassed.
In step S63, when the obstacle cannot be bypassed, the link related to the obstacle cannot pass through. Correspondingly, in the topological graph, in all the communication relations among the routing inspection points, all the connecting lines related to the positions of the obstacles are cut off, and the obstacle avoidance topological graph without the obstacle road sections is obtained. And re-planning the path based on the obstacle avoidance topological graph, wherein the obtained paths are all paths avoiding the obstacle.
As a preferred embodiment, when the robot determines that it cannot bypass the obstacle, it stays at the obstacle for five minutes before performing the subsequent operation.
In the step S64, according to the newly obtained obstacle avoidance topological graph, the current position information of the robot, and the next target inspection point position information, the method of the step S51-S53 is executed to perform obstacle avoidance path planning again, and the robot travels to the next target inspection point.
In step S65, if a path to the next target inspection point cannot be obtained in the obstacle avoidance topological graph, the method of steps S51-S53 is executed to perform obstacle avoidance path planning again according to the newly obtained obstacle avoidance topological graph, the current position information of the robot, and the position information of the charging preparation point, and return to the charging preparation point.
In step S66, when the robot cannot move forward around the obstacle, cannot plan a new route that can avoid the obstacle to reach the next target inspection point, or cannot plan a new route that can avoid the obstacle to return to the charge preparation point, an error signal is generated and output, and manual assistance processing is sought.
Referring to fig. 4, in some embodiments, there is provided a robot real-time obstacle avoidance path planning apparatus applied to the above method, including:
the acquisition module 101 is used for acquiring the information of the working area and constructing a map of the working area;
the configuration module 102 is used for configuring the inspection points based on the working area information and acquiring the inspection point information according to the working area map;
the topology establishing module 103 is used for establishing a topology map according to the routing inspection point information;
the positioning module 104 is used for acquiring the current position information of the robot and the position information of the target inspection point;
the calculation module 105 is used for calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
and the obstacle avoidance module 106 is used for guiding the robot to move according to the optimal routing inspection path and replanning the path when an obstacle is detected.
According to the method and the device for planning the real-time obstacle avoidance path of the robot, the routing inspection point information is constructed into the topological graph to plan the shortest path, the obstacle is detected in real time in the process of traveling according to the planned path, the obstacle is bypassed or the path is planned again immediately when the obstacle is detected, so that the emergency situation can be effectively responded, and the safety is high; the positions and the communication relations of the inspection points are converted into vertexes and edges in the topological graph, and the distance between the inspection points is calculated to determine the weight, so that the path planning problem between the inspection points is converted into the problem of solving the shortest connection line of the vertexes in the topological graph, and the path planning efficiency is improved; the simulation annealing algorithm is improved, a plurality of better alternative routing inspection paths are generated through calculation amount as less as possible, accidental errors can be effectively avoided, the alternative routing inspection paths are prevented from being trapped in local optimization, and accuracy and efficiency of path planning are improved; in the path planning process, the current discarding probability is calculated according to the previous discarding probability and the probability parameter instead of the discarding probability which is kept constant, so that not only can a large number of better path sequences be prevented from being discarded by mistake, but also the calculation speed can be increased, and the accuracy and efficiency of path planning are improved.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including the preferred embodiment and all changes and modifications that fall within the scope of the invention. It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A robot real-time obstacle avoidance path planning method is characterized by comprising the following steps:
collecting work area information and constructing a work area map;
arranging inspection points based on the working area information, and acquiring inspection point information according to the working area map;
constructing a topological graph according to the routing inspection point information;
acquiring current position information and target inspection point position information of the robot;
calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
And guiding the robot to move according to the optimal routing inspection path, and replanning the path when the obstacle is detected.
2. The method according to claim 1, wherein the patrol points include a data acquisition point, a charging point, and a charging preparation point;
the inspection point information comprises inspection point position information and a communication relation between inspection points.
3. The method of claim 2, wherein after configuring the patrol point based on the work area information and obtaining patrol point information according to the work area map, further comprising:
establishing a database based on the routing inspection point position information and the communication relation between routing inspection points;
constructing a topological graph according to the routing inspection point information, comprising the following steps:
reading routing inspection point position information and the communication relation between routing inspection points from the database;
calculating the distance between the inspection points according to the inspection point position information and the communication relation between the inspection points;
and taking the distance between the inspection points as a weight, and constructing a topological graph according to the communication relation between the inspection points.
4. The method of claim 1, wherein calculating an optimal routing inspection path based on the current position information of the robot, the target routing inspection point position information, and the topology map comprises:
According to the position information of the target inspection point and the topological graph, calculating to obtain the shortest path between each target inspection point and other target inspection points;
generating a plurality of alternative routing inspection paths for routing inspection of the target routing inspection points according to different routing inspection sequences, and calculating the lengths of the alternative routing inspection paths according to the shortest paths between each target routing inspection point and other target routing inspection points;
and respectively calculating the distances between the current position of the robot and the starting points of the plurality of alternative routing inspection paths, and respectively overlapping the distances with the alternative routing inspection paths to obtain the total path length, wherein the path with the shortest total path length is the optimal routing inspection path.
5. The method of claim 4, wherein generating a plurality of alternative inspection paths for inspecting the target inspection point in different inspection orders comprises:
setting initial temperature, cooling gradient, finishing temperature, circulation times, path number, discarding probability and probability parameter range at each temperature, and randomly generating path sequences with corresponding number according to the set path number;
and from the initial temperature, iteratively executing the following operations according to the cycle times at each temperature to obtain alternative routing inspection paths at each temperature, and stopping until the alternative routing inspection paths are lower than the end temperature:
Calculating the path lengths corresponding to the current multiple path sequences, and taking the path sequence with the shortest path length as a current optimal path;
reserving the current optimal path, updating other path sequences based on neighborhood change, calculating the updated path length, receiving the updated path sequence if the updated path length is smaller than the path length before updating, and reserving the path sequence before updating if the updated path length is not smaller than the path length before updating;
calculating the current discarding probability according to the previous discarding probability and the probability parameter, generating a random probability for each path sequence, judging whether the random probability of each path sequence is greater than the current discarding probability, if so, randomly generating a new path sequence, and if not, keeping the path sequence;
calculating the path length corresponding to each path sequence, sequencing according to the path length, and reserving a half path sequence with a smaller path length; for the other half path sequence with larger path length, randomly generating a corresponding number of new path sequences, judging whether the path length of the new path sequence is smaller than that of the original path sequence, if so, accepting the new path sequence, and if not, judging whether to accept the new path sequence according to the simulated annealing acceptance probability; and cooling according to the cooling gradient.
6. The method of claim 5, wherein updating the other path sequence based on the neighborhood change comprises:
randomly selecting a preset number of routing inspection points in the path sequence to be updated as operators, and partially reserving or rearranging and combining the routing inspection points in the neighborhood interval of the operators to generate a new path sequence;
the preset number is two, three or five, wherein the probability of executing two operators is as follows:
wherein, PGIn order to execute the probability calculated by adopting two operators, S is the maximum iteration number, and N is the current iteration turn.
7. The method of claim 5, wherein the current drop probability is calculated based on the previous drop probability and the probability parameter, and is expressed by the following formula:
wherein, P1For the current drop probability, P0For the last discard probability, λ1For a preset minimum value of the probability parameter, lambda2For the preset maximum value of the probability parameter, a is the random number generated according to the (0,1) uniform distribution, and B is the random number generated according to the F distribution.
8. The method of claim 2, wherein re-planning the path upon detection of an obstacle comprises:
directing the robot which detects the obstacle to stop moving and collecting environmental information around the robot;
Calculating the walking width according to the environment information, and judging whether the robot can bypass the obstacle, and when the robot can bypass the obstacle, guiding the robot to continue to move according to the optimal routing inspection path after bypassing the obstacle;
when the robot cannot get around the obstacle, acquiring obstacle position information and deleting the communication relation including the position of the obstacle in the topological graph to obtain an obstacle avoidance topological graph;
acquiring current position information and next target inspection point position information of the robot, and re-planning an obstacle avoidance path according to the obstacle avoidance topological graph;
when the robot cannot plan an obstacle avoidance path, acquiring position information of a charging preparation point, and re-planning an obstacle avoidance return path according to the obstacle avoidance topological graph;
and generating and outputting an error reporting signal when the robot cannot plan an obstacle avoidance return path.
9. The method of claim 8, wherein the walkable width satisfies the following relationship when the robot is able to clear an obstacle:
wherein r is the radius of the robot, D is the preset expansion radius, and D is the walkable width.
10. A robot real-time obstacle avoidance path planning device applied to the method according to any one of claims 1 to 9, comprising:
The acquisition module is used for acquiring the information of the working area and constructing a working area map;
the configuration module is used for configuring the inspection points based on the working area information and acquiring the inspection point information according to the working area map;
the topology establishing module is used for establishing a topological graph according to the routing inspection point information;
the positioning module is used for acquiring the current position information of the robot and the position information of the target inspection point;
the calculation module is used for calculating an optimal routing inspection path according to the current position information of the robot, the position information of the target routing inspection point and the topological graph;
and the obstacle avoidance module is used for guiding the robot to move according to the optimal routing inspection path and replanning the path when the obstacle is detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210663255.0A CN114756034B (en) | 2022-06-13 | 2022-06-13 | Robot real-time obstacle avoidance path planning method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210663255.0A CN114756034B (en) | 2022-06-13 | 2022-06-13 | Robot real-time obstacle avoidance path planning method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114756034A true CN114756034A (en) | 2022-07-15 |
| CN114756034B CN114756034B (en) | 2022-09-09 |
Family
ID=82336669
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210663255.0A Active CN114756034B (en) | 2022-06-13 | 2022-06-13 | Robot real-time obstacle avoidance path planning method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114756034B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328146A (en) * | 2022-08-30 | 2022-11-11 | 安徽机电职业技术学院 | Self-adaptive path inspection method of inspection robot |
| CN116520853A (en) * | 2023-06-08 | 2023-08-01 | 江苏商贸职业学院 | Agricultural inspection robot based on artificial intelligence technology |
| CN116777187A (en) * | 2023-08-25 | 2023-09-19 | 山东道万电气有限公司 | Multi-path inspection intelligent central control scheduling method and platform |
Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566576A (en) * | 2012-02-24 | 2012-07-11 | 山东鲁能智能技术有限公司 | Multiple inspection robot cooperative operation method for substation sequence control system |
| CN102799180A (en) * | 2012-07-26 | 2012-11-28 | 杭州高越科技有限公司 | Walking control method and device of cleaning machine |
| CN103439973A (en) * | 2013-08-12 | 2013-12-11 | 桂林电子科技大学 | Household cleaning robot capable of establishing map by self and cleaning method |
| CN104914865A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Transformer station inspection tour robot positioning navigation system and method |
| CN106156888A (en) * | 2016-06-30 | 2016-11-23 | 广东电网有限责任公司电力科学研究院 | A kind of polling path method and device for planning of crusing robot |
| CN108170134A (en) * | 2017-11-15 | 2018-06-15 | 国电南瑞科技股份有限公司 | A kind of robot used for intelligent substation patrol paths planning method |
| CN108638071A (en) * | 2018-05-22 | 2018-10-12 | 四川超影科技有限公司 | A kind of crusing robot optimal path dynamic programming method |
| CN109141430A (en) * | 2018-09-04 | 2019-01-04 | 南京理工大学 | Electric inspection process robot path planning method based on simulated annealing ant group algorithm |
| CN110009761A (en) * | 2019-03-20 | 2019-07-12 | 华南理工大学 | Smart machine automatic detecting paths planning method and system |
| CN111026114A (en) * | 2019-12-12 | 2020-04-17 | 南京苏美达智能技术有限公司 | Obstacle detouring method and self-walking equipment |
| CN111780762A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Patrol path generation method and device and storage medium |
| CN112729315A (en) * | 2021-04-01 | 2021-04-30 | 北京全路通信信号研究设计院集团有限公司 | Route planning method and system of inspection robot based on fusion networking technology |
| US20210348928A1 (en) * | 2020-05-06 | 2021-11-11 | Wuhan University Of Science And Technology | Multi-police-officer collaborative round-up task allocation and path planning method under constraint of road network |
| CN113777500A (en) * | 2021-09-29 | 2021-12-10 | 东方电气集团科学技术研究院有限公司 | Method for identifying battery parameters and optimizing precision by adopting simulated annealing method |
| CN113791617A (en) * | 2021-08-31 | 2021-12-14 | 金华市浙工大创新联合研究院 | Global path planning method based on physical dimension of fire-fighting robot |
| CN113917912A (en) * | 2020-07-08 | 2022-01-11 | 珠海格力电器股份有限公司 | Global path planning method, device, terminal and readable storage medium |
-
2022
- 2022-06-13 CN CN202210663255.0A patent/CN114756034B/en active Active
Patent Citations (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102566576A (en) * | 2012-02-24 | 2012-07-11 | 山东鲁能智能技术有限公司 | Multiple inspection robot cooperative operation method for substation sequence control system |
| CN102799180A (en) * | 2012-07-26 | 2012-11-28 | 杭州高越科技有限公司 | Walking control method and device of cleaning machine |
| CN103439973A (en) * | 2013-08-12 | 2013-12-11 | 桂林电子科技大学 | Household cleaning robot capable of establishing map by self and cleaning method |
| CN104914865A (en) * | 2015-05-29 | 2015-09-16 | 国网山东省电力公司电力科学研究院 | Transformer station inspection tour robot positioning navigation system and method |
| CN106156888A (en) * | 2016-06-30 | 2016-11-23 | 广东电网有限责任公司电力科学研究院 | A kind of polling path method and device for planning of crusing robot |
| CN108170134A (en) * | 2017-11-15 | 2018-06-15 | 国电南瑞科技股份有限公司 | A kind of robot used for intelligent substation patrol paths planning method |
| CN108638071A (en) * | 2018-05-22 | 2018-10-12 | 四川超影科技有限公司 | A kind of crusing robot optimal path dynamic programming method |
| CN109141430A (en) * | 2018-09-04 | 2019-01-04 | 南京理工大学 | Electric inspection process robot path planning method based on simulated annealing ant group algorithm |
| CN110009761A (en) * | 2019-03-20 | 2019-07-12 | 华南理工大学 | Smart machine automatic detecting paths planning method and system |
| CN111026114A (en) * | 2019-12-12 | 2020-04-17 | 南京苏美达智能技术有限公司 | Obstacle detouring method and self-walking equipment |
| US20210348928A1 (en) * | 2020-05-06 | 2021-11-11 | Wuhan University Of Science And Technology | Multi-police-officer collaborative round-up task allocation and path planning method under constraint of road network |
| CN111780762A (en) * | 2020-06-30 | 2020-10-16 | 杭州海康机器人技术有限公司 | Patrol path generation method and device and storage medium |
| CN113917912A (en) * | 2020-07-08 | 2022-01-11 | 珠海格力电器股份有限公司 | Global path planning method, device, terminal and readable storage medium |
| CN112729315A (en) * | 2021-04-01 | 2021-04-30 | 北京全路通信信号研究设计院集团有限公司 | Route planning method and system of inspection robot based on fusion networking technology |
| CN113791617A (en) * | 2021-08-31 | 2021-12-14 | 金华市浙工大创新联合研究院 | Global path planning method based on physical dimension of fire-fighting robot |
| CN113777500A (en) * | 2021-09-29 | 2021-12-10 | 东方电气集团科学技术研究院有限公司 | Method for identifying battery parameters and optimizing precision by adopting simulated annealing method |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115328146A (en) * | 2022-08-30 | 2022-11-11 | 安徽机电职业技术学院 | Self-adaptive path inspection method of inspection robot |
| CN115328146B (en) * | 2022-08-30 | 2024-04-02 | 安徽机电职业技术学院 | Self-adaptive path inspection method of inspection robot |
| CN116520853A (en) * | 2023-06-08 | 2023-08-01 | 江苏商贸职业学院 | Agricultural inspection robot based on artificial intelligence technology |
| CN116777187A (en) * | 2023-08-25 | 2023-09-19 | 山东道万电气有限公司 | Multi-path inspection intelligent central control scheduling method and platform |
| CN116777187B (en) * | 2023-08-25 | 2024-01-16 | 山东道万电气有限公司 | Multi-path inspection intelligent central control scheduling method and platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114756034B (en) | 2022-09-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115226B (en) | Route planning method for avoiding multi-robot conflict based on jumping point search | |
| CN114756034B (en) | Robot real-time obstacle avoidance path planning method and device | |
| CN112000754B (en) | Map construction method, device, storage medium and computer equipment | |
| WO2021208143A1 (en) | Method and system for planning and sampling mobile robot path in human-machine integration environment | |
| CN107703945A (en) | A kind of intelligent farm machinery paths planning method of multiple targets fusion | |
| CN113821029B (en) | Path planning method, device, equipment and storage medium | |
| CN110411454B (en) | Mobile robot path planning method for improving random path diagram method | |
| CN110320919B (en) | Method for optimizing path of mobile robot in unknown geographic environment | |
| CN112114584A (en) | Global path planning method of spherical amphibious robot | |
| CN115167408A (en) | Route planning system patrols and examines based on photovoltaic power plant | |
| CN113867336B (en) | Mobile robot path navigation and planning method suitable for complex scene | |
| CN111427341B (en) | Robot shortest expected time target searching method based on probability map | |
| García et al. | An efficient multi-robot path planning solution using A* and coevolutionary algorithms | |
| CN115560771A (en) | Sampling-based path planning method and device and automatic driving equipment | |
| CN116203970A (en) | Intelligent obstacle avoidance method and system for inspection robot | |
| CN116777187A (en) | Multi-path inspection intelligent central control scheduling method and platform | |
| CN112828883B (en) | Robot environment exploration method and system in unknown environment | |
| CN113848560A (en) | Dam surface image unmanned aerial vehicle rapid and safe acquisition method and system | |
| CN117075613A (en) | Unmanned vehicle sensing and obstacle avoidance method, system, computer equipment and storage medium | |
| US11898869B2 (en) | Multi-agent map generation | |
| CN115019275A (en) | Heuristic determination and model training methods, electronic device, and computer storage medium | |
| CN113485378B (en) | Mobile robot path planning method, system and storage medium based on traffic rules | |
| CN113885494A (en) | Path planning method for electric power system robot | |
| CN114690728B (en) | Bidirectional adjustable AGV path planning method for rapid material transportation | |
| Chen et al. | Rapid scan-to-building information modeling using robotics and artificial intelligence for construction applications |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220922 Address after: 201107 room 108, block a, building 8, No. 1879, jiangxinsha Road, Pudong New Area, Shanghai Patentee after: Shanghai mengpa Intelligent Technology Co.,Ltd. Patentee after: Beijing mengpa Xinchuang Technology Co.,Ltd. Address before: 100124 1110, floor 1, building a, No. 98, Guangqu Road, Chaoyang District, Beijing Patentee before: Beijing mengpa Xinchuang Technology Co.,Ltd. |