CN111413962A - Search and rescue robot target search method based on path passing probability - Google Patents

Search and rescue robot target search method based on path passing probability Download PDF

Info

Publication number
CN111413962A
CN111413962A CN202010042703.6A CN202010042703A CN111413962A CN 111413962 A CN111413962 A CN 111413962A CN 202010042703 A CN202010042703 A CN 202010042703A CN 111413962 A CN111413962 A CN 111413962A
Authority
CN
China
Prior art keywords
path
search
rescue
probability
nodes
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
CN202010042703.6A
Other languages
Chinese (zh)
Other versions
CN111413962B (en
Inventor
张波涛
鲁玉林
吕强
吴秋轩
仲朝亮
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.)
Hangzhou Dianzi University
Original Assignee
Hangzhou Dianzi University
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 Hangzhou Dianzi University filed Critical Hangzhou Dianzi University
Priority to CN202010042703.6A priority Critical patent/CN111413962B/en
Publication of CN111413962A publication Critical patent/CN111413962A/en
Application granted granted Critical
Publication of CN111413962B publication Critical patent/CN111413962B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0242—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using non-visible light signals, e.g. IR or UV signals
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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 or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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
    • G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • G05D1/0253—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means extracting relative motion information from a plurality of images taken successively, e.g. visual odometry, optical flow
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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
    • G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
    • G05D1/0278—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle using satellite positioning signals, e.g. GPS
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

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

Abstract

The invention discloses a search and rescue robot target search method based on path passing probability, which comprises the following steps: s01: establishing a topological environment model of a working environment of the mobile robot, and recording paths among nodes; s02: establishing an evaluation model of the probability that the path between the nodes can pass through, and carrying out reliability evaluation; s03: performing search and rescue key node sequence planning according to the optimization index; s04: planning paths among nodes according to the path passability of the local environment; s05: searching is executed according to the obtained path, and the path passable probability in the topological data set is updated according to the actual condition; if the target to be rescued is found, sending the real-time image and the target position to rescuers; s06: steps S03 through S05 are repeated until the search task is completed. The invention plans the search path according to the probability of the path, updates the topological model according to the current determined path condition, ensures that the robot passes through an uncertain area with the maximum probability, and efficiently finishes the task.

Description

Search and rescue robot target search method based on path passing probability
Technical Field
The invention relates to the field of path planning of search and rescue robots, in particular to a search and rescue robot target searching method based on path passing probability.
Background
The mobile robot search and rescue in disaster and dangerous environment can obviously improve the efficiency of rescue workers and reduce the casualties of the rescue workers. The reasonable mobile robot motion planning scheme can provide efficient upper-layer decision for a search and rescue robot with a thoughtful-reaction mixed system structure, so that the robot can find a target to be rescued as soon as possible and provide site environment images and position information. The mobile robot target search and rescue planning under the environment is not determined to belong to a very complex task type, and the reasonable motion planning method can greatly improve the working efficiency of the search and rescue task.
The invention provides a dynamic path planning method for an urban rescue intelligent body, which improves an ant colony algorithm, belongs to the technical field of robot simulation, aims at the path planning problem of a dynamic change environment in robot rescue simulation, improves the classic ant colony algorithm, introduces a target dominance degree, modifies a calculation method of ant state transition probability and an updating rule of pheromone, and adapts to the situations of unknown road conditions, dynamic change, complex task of the rescue intelligent body and inconsistent path planning requirement in the rescue environment.
The evaluation index commonly used in the existing search and rescue robot motion planning method is the shortest path, even the search and rescue robot enters the scene in a remote control mode, and the lagged planning mode cannot be matched with the complex scene environment. In the above search methods, the former is difficult to cope with the real-time change of the path after the problems of temporary collapse, falling of the combustion object and the like are encountered, and the latter completely depends on the judgment of people, so that the efficiency is extremely low. The practical search and rescue task needs are extremely complex in working environment, the working environment is often semi-structured or even completely unstructured, the feasible road of the mobile robot is continuously updated along with disaster changes, if a wall collapses, a path can be permanently blocked, and a path can be blocked in a short time by a small amount of comburent, but the existing path planning technology lacks a search method aiming at such search and rescue conditions.
Disclosure of Invention
The invention provides a search and rescue robot target search method based on path passing probability, which is used for constructing a search and rescue path planning strategy in uncertain environment and mainly used for search tasks which are optimized according to the feasible probability of road conditions and have uncertain search and rescue reliability in search environment. And according to the task characteristics, realizing the real-time optimization and adjustment of the planning scheme.
The technical scheme of the invention is as follows.
A search and rescue robot target search method based on path passing probability comprises the following steps:
s01: establishing a topological environment model of a working environment of the mobile robot, and recording paths among nodes; s02: establishing an evaluation model of probability that a path between nodes can pass through, and carrying out reliability evaluation; s03: performing search and rescue key node sequence planning according to the optimization index; s04: planning paths among nodes according to the path passability of the local environment; s05: searching is carried out according to the obtained path, and the path passable probability in the topological data set is updated according to the actual condition; if the target to be rescued is found, sending the real-time image and the target position to rescuers; s06: steps S03 through S05 are repeated until the search task is completed or an instruction to stop the search is received.
Preferably, the process of step S01 includes: establishing an initial feature map by using the features of an environment to be rescued, manually setting key rescue node areas, automatically generating initial paths among nodes by using a bidirectional regression fast random tree algorithm, and simultaneously recording the path length and the features of the paths;
the mobile robot search and rescue area meets the following conditions:
Figure BDA0002368303520000021
Figure BDA0002368303520000022
Figure BDA0002368303520000023
and
Figure BDA0002368303520000024
a communication path between the first and second substrates;
wherein SiIs the ith delivery point, O, of the robotkIs the kth search and rescue node, RkIs a search and rescue area near the kth search and rescue node, LλThe method comprises the steps of searching and rescuing nodes, M is a regional topological environment model to be searched and rescued, and E is a total region to be searched and rescued.
Preferably, the process of step S02 includes a topological environment model M (O, L) for the mobile robot to work on, including a set of rescue nodes O ═ { O ═ Ok|Ok∈ G, k 1,2, 3.., m } and rescue path set L { L ═ Gλ|Lλ∈M,k＝1,2,3,...,n}；
Probability of path reliability
Figure BDA0002368303520000025
Is used to evaluate OiAnd OjThe probability of smooth passing of the robot is shown, if tau factors possibly blocking the path exist, the passing probability caused by each factor is
Figure BDA0002368303520000026
Then
Figure BDA0002368303520000027
Evaluation by the following model
Figure BDA0002368303520000028
Probability of initial passage
Figure BDA0002368303520000029
The shooting analysis or the manual experience value setting can be carried out through the unmanned aerial vehicle.
M (O, L) has a reliability matrix of
Figure BDA0002368303520000031
Wherein
Figure BDA0002368303520000032
Preferably, the process of step S03 includes, for M (O, L), reserving only the shortest path between the search and rescue nodes, deleting the redundant path, generating M ' (O, L '), L ' being the set of the deleted paths, determining whether M ' (O, L ') is connected and is an Euler diagram, and if the number of vertices is odd, supplementing the Euler diagram by the original M (O, L), and performing the steps according to the method
Figure BDA0002368303520000033
The weighted average value of the weight and the path length in the process is used as the weight, the weight is 0.5, and a Fleury algorithm is used for generating a preliminary tour sequence of the key nodes.
Preferably, the process of step S04 includes reading in the overall topology model M (O, L) and applying the reliability matrix
Figure BDA0002368303520000034
The element and the path length of the robot are weighted, the weight is 0.5 and is used as a topological edge weight, the path between the nodes is searched by utilizing a minimum weight algorithm Dijkstra, and the path from the starting point of the robot to the search and rescue node and the path between the search and rescue nodes are generated; the actual paths among the nodes are automatically generated according to the constraint of the robot by using a bidirectional regression fast random tree algorithm.
Preferably, the process of step S05 includes: tracking the generated path by using a speedometer, an IMU (inertial measurement Unit) and a DGPS (differential global positioning system), and updating the feasibility of the path into a topological environment model by using the feasibility of continuously detecting the front path by using a radar, a panoramic camera, binocular vision and an infrared temperature measurement sensor;
for a safe and reliable path with good detected road condition and extremely low possibility of damage, the reliability is set to 1, and for a front path, unrecoverable damage occurs, such as: when the collapse happens, the passability is set to be 0, and the passability can be recovered only by manual work, so that the update can be realized;
to inRestorative damage such as: the trafficability of the comburent is set to 0, and the feasibility is increased along with the time (the road may be unobstructed again because the comburent is burnt out), and the feasibility is recovered
Figure BDA0002368303520000035
The evaluation formula with respect to time can be calculated by the following formula,
Figure BDA0002368303520000036
Figure BDA0002368303520000041
Figure BDA0002368303520000042
the probability of feasibility at time t +1,
Figure BDA0002368303520000043
setting feasibility probability at the time t and speed coefficient recovery according to the characteristic of recoverable sexual disorder, wherein delta t is the time interval between the updating time and the last updating and has the unit of second;
updating reliability matrix of topological environment model
Figure BDA0002368303520000044
Preferably, the process of performing the search in step S06 includes: according to the key rescue node sequence, IMU, DGP and odometer S are used for moving along a path generated by a bidirectional fast random tree algorithm, a radar and a panoramic camera are used for detecting obstacles, temporary obstacles or unrecoverable obstacles appearing in the path are detected, a target to be searched and rescued is identified by binocular vision, the position of the target and image information are obtained, an infrared temperature measurement sensor is used for detecting flame or high-temperature obstacles, obstacle avoidance and danger are taken as the highest priority, and if the target to be rescued is found, the image and the position of the target are sent to rescuers. And then moving with the next search and rescue node as a target until a search task is completed or an instruction for stopping searching is received.
By updating the reliability topological probability model in real time, the searching paths of the robot are guaranteed to be better schemes, and the schemes can be adjusted in time when the road conditions change, so that the searching efficiency is improved, and the target searching task under the uncertain environment is realized.
The substantial effects of the invention include: planning a search and rescue path of the robot according to the initial topological environment model and the passability information stored in the initial topological environment model, meanwhile, updating the passability information stored in the topological environment model according to road condition information in the execution process of the search and rescue task, and ensuring that the search and rescue path tracked by the robot is a better scheme through updating the passability topological probability model in real time.
Detailed Description
The following description will be given in conjunction with embodiments of the present application. In addition, numerous specific details are set forth below in order to provide a better understanding of the present invention. It will be understood by those skilled in the art that the present invention may be practiced without some of these specific details. In some instances, methods, procedures, components, and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present invention.
Example (b):
a search and rescue robot target search method based on path passable probability plans a search and rescue path of a robot according to an initial topological environment model and passability information stored in the initial topological environment model, meanwhile, in the execution process of a search and rescue task, the passability information stored in the topological environment model is updated according to road condition information, and the search and rescue path tracked by the robot is guaranteed to be a better scheme through real-time updating of the passability topological probability model.
The embodiment comprises the following steps:
s01: establishing a topological environment model of a working environment of the mobile robot, and recording paths among nodes;
the method comprises the steps of establishing an initial feature map by using the features of an environment to be rescued, manually setting key rescue node areas, automatically generating initial paths among nodes by using a bidirectional regression fast random tree algorithm, and simultaneously recording the path length and the features of the paths.
The mobile robot search and rescue area meets the following conditions:
Figure BDA0002368303520000051
Figure BDA0002368303520000052
Figure BDA0002368303520000053
and
Figure BDA0002368303520000054
a communication path between the first and second substrates;
wherein SiIs the ith delivery point, O, of the robotkIs the kth search and rescue node, RkIs a search and rescue area near the kth search and rescue node, LλThe method comprises the steps of searching and rescuing nodes, M is a regional topological environment model to be searched and rescued, and E is a total region to be searched and rescued.
Step S02: establishing an evaluation model of the probability that the path between the nodes can pass through, and carrying out reliability evaluation;
the process comprises the following steps of working a topological environment model M (O, L) for the mobile robot, wherein the topological environment model M comprises a set of rescue nodes, and O is { O ═ Ok|Ok∈ G, k 1,2, 3.., m } and rescue path set L { L ═ Gλ|Lλ∈M,k＝1,2,3,...,n}；
Probability of path reliability
Figure BDA0002368303520000055
Is used to evaluate OiAnd OjThe probability of smooth passing of the robot is shown, if tau factors possibly blocking the path exist, the passing probability caused by each factor is
Figure BDA0002368303520000056
Then
Figure BDA0002368303520000057
Evaluation by the following model
Figure BDA0002368303520000058
Probability of initial passage
Figure BDA0002368303520000059
The shooting analysis or the manual experience value setting can be carried out through the unmanned aerial vehicle.
M (O, L) has a reliability matrix of
Figure BDA0002368303520000061
Wherein
Figure BDA0002368303520000062
Step S03: performing search and rescue key node sequence planning according to the optimization index;
the process comprises the steps of only reserving the shortest path among search and rescue nodes for M (O, L), deleting redundant paths, generating M '(O, L') and L 'which are the deleted path sets, judging whether M' (O, L ') is communicated and is an Euler diagram, if the vertex degree is an odd number, supplementing the M' (O, L) into the Euler diagram through the original M (O, L), and obtaining the basis of the following steps
Figure BDA0002368303520000063
The weighted average value of the weight and the path length in the process is used as the weight, the weight is 0.5, and a Fleury algorithm is used for generating a preliminary tour sequence of the key nodes.
S04: planning paths among nodes according to the path passability of the local environment;
the process includes reading in the global topology model M (O, L), and applying a reliability matrix
Figure BDA0002368303520000064
The element and the path length of the robot are weighted, the weight values are all 0.5 and are used as topological edge weights, the path between nodes is searched by utilizing a minimum weight algorithm Dijkstra, and the path from the starting point of the robot to the search and rescue node and the path between the search and rescue nodes are generated; the actual paths among the nodes are automatically generated by a bidirectional regression fast random tree algorithm according to the constraint of the robot.
S05: searching is executed according to the obtained path, and the path passable probability in the topological data set is updated according to the actual condition; if the target to be rescued is found, sending the real-time image and the target position to rescuers;
the process comprises the following steps: tracking the generated path by using a speedometer, an IMU (inertial measurement Unit) and a DGPS (differential global positioning system), and updating the feasibility of the path into a topological environment model by using the feasibility of continuously detecting the front path by using a radar, a panoramic camera, binocular vision and an infrared temperature measurement sensor;
for a safe and reliable path with good detected road condition and extremely low possibility of damage, the reliability is set to 1, and for a front path, unrecoverable damage occurs, such as: when the collapse happens, the passability is set to be 0, and the passability can be recovered only by manual work, so that the update can be realized;
for recoverable damage, such as: the trafficability of the comburent is set to 0, and the feasibility is increased along with the time (the road may be unobstructed again because the comburent is burnt out), and the feasibility is recovered
Figure BDA0002368303520000071
The evaluation formula with respect to time can be calculated by the following formula,
Figure BDA0002368303520000072
Figure BDA0002368303520000073
Figure BDA0002368303520000074
the probability of feasibility at time t +1,
Figure BDA0002368303520000075
setting feasibility probability at the time t and speed coefficient recovery according to the characteristic of recoverable sexual disorder, wherein delta t is the time interval between the updating time and the last updating and has the unit of second;
updating reliability matrix of topological environment model
Figure BDA0002368303520000076
S06: repeating the steps S03 to S05 until the search task is completed or an instruction to stop the search is received;
the process comprises the following steps: according to a key rescue node sequence, IMU, DGP and a speedometer S are used for moving along a path generated by a bidirectional fast random tree algorithm, a radar and a panoramic camera are used for detecting obstacles, temporary obstacles or unrecoverable obstacles appearing in the path are detected, a target to be searched and rescued is identified by binocular vision, the position and image information of the target are obtained, a flame or high-temperature obstacle is detected by an infrared temperature measuring sensor, obstacle avoidance and danger are taken as the highest priority, and if the target to be rescued is found, the image and the position of the target are sent to rescuers. And then moving with the next search and rescue node as a target until a search task is completed or an instruction for stopping searching is received.
The effect of the embodiment includes: planning a search and rescue path of the robot according to the initial topological environment model and the passability information stored in the initial topological environment model, simultaneously updating the passability information stored in the topological environment model according to road condition information in the execution process of the search and rescue task, and ensuring that the search and rescue path tracked by the robot is a better scheme through updating the passability topological probability model in real time.
Through the description of the above embodiments, those skilled in the art will understand that, for convenience and simplicity of description, only the division of the above functional modules is used as an example, and in practical applications, the above function distribution may be performed by different functional modules according to needs, that is, the internal structure of a specific device may be divided into different functional modules to perform all or part of the above described functions.
In the embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways. The technical solution of the embodiments of the present application may be essentially or partially contributed to the prior art, or all or part of the technical solution may be embodied in the form of a software product, where the software product is stored in a storage medium, and includes several instructions to enable a device (which may be a single chip, a chip, or the like) or a processor (processor) to execute all or part of the steps of the method of the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and all the changes or substitutions should be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims (6)

1. A search and rescue robot target search method based on path passing probability is characterized by comprising the following steps:
s01: establishing a topological environment model of a working environment of the mobile robot, and recording paths among nodes;
s02: establishing an evaluation model of the probability that the path between the nodes can pass through, and carrying out reliability evaluation;
s03: performing search and rescue key node sequence planning according to the optimization index;
s04: planning paths among nodes according to the path passability of the local environment;
s05: searching is executed according to the obtained path, and the path passable probability in the topological data set is updated according to the actual condition; if the target to be rescued is found, sending the real-time image and the target position to rescuers;
s06: steps S03 through S05 are repeated until the search task is completed or an instruction to stop the search is received.
2. The search and rescue robot target search method based on the path passable probability as claimed in claim 1, wherein the process of step S01 includes:
establishing an initial feature map by using the features of an environment to be rescued, manually setting key rescue node areas, automatically generating initial paths among nodes by using a bidirectional regression fast random tree algorithm, and simultaneously recording the path length and the features of the paths;
the mobile robot search and rescue area meets the following conditions:
Figure FDA0002368303510000011
Figure FDA0002368303510000012
Figure FDA0002368303510000013
and
Figure FDA0002368303510000014
a communication path between the first and second substrates;
wherein SiIs the ith delivery point, O, of the robotkIs the kth search and rescue node, RkIs a search and rescue area near the kth search and rescue node, LλThe method is characterized in that the method is a path among search and rescue nodes, M is a regional topological environment model to be searched and rescued, and E is a total region to be searched and rescued.
3. The search and rescue robot target search method based on the path passable probability as claimed in claim 2, wherein the process of step S02 includes:
a topological environment model M (O, L) for the mobile robot to work comprises a set of rescue nodes:
O＝{Ok|Ok∈G,k＝1,2,3,...,m}
and set of rescue paths
L＝{Lλ|Lλ∈M,k＝1,2,3,...,n}.
Probability of path reliability
Figure FDA0002368303510000015
Is used to evaluate OiAnd OjThe probability of smooth passing of the robot is shown, if tau factors possibly blocking the path exist, the passing probability caused by each factor is
Figure FDA0002368303510000021
Then
Figure FDA0002368303510000022
Evaluation with the following model
Figure FDA0002368303510000023
Probability of initial passage
Figure FDA0002368303510000024
Shooting analysis or manual experience value setting can be carried out through an unmanned aerial vehicle;
m (O, L) has a reliability matrix of
Figure FDA0002368303510000025
Wherein
Figure FDA0002368303510000026
4. The search and rescue robot target search method based on the path passable probability as claimed in claim 3, wherein the process of step S03 includes:
for M (O, L), only the shortest path between search and rescue nodes is reserved, redundant paths are deleted, M ' (O, L ') is generated, L ' is the deleted path set, whether M ' (O, L ') is connected and is an Euler diagram is judged, if the vertex degree is an odd number, the original M (O, L) is supplemented into the Euler diagram, and the method is based on the principle that
Figure FDA0002368303510000027
The weighted average value of the weight and the path length in the process is used as the weight, the weight is 0.5, and a Fleury algorithm is used for generating a preliminary tour sequence of the key nodes.
5. The method as claimed in claim 4, wherein the step S04 includes reading in the overall topology model M (O, L), and applying a reliability matrix
Figure FDA0002368303510000028
The element and the path length of the robot are weighted, the weight is 0.5 and is used as a topological edge weight, the path between the nodes is searched by utilizing a minimum weight algorithm Dijkstra, and the path from the starting point of the robot to the search and rescue node and the path between the search and rescue nodes are generated; the actual paths among the nodes are automatically generated according to the constraint of the robot by using a bidirectional regression fast random tree algorithm.
6. The search and rescue robot target search method based on the path passable probability as claimed in claim 5, wherein the process of step S05 includes:
tracking the generated path by using a speedometer, an IMU (inertial measurement Unit) and a DGPS (differential global positioning system), and updating the feasibility of the path into a topological environment model by using the feasibility of continuously detecting the front path by using a radar, a panoramic camera, binocular vision and an infrared temperature measurement sensor;
for a safe and reliable path with good detected road conditions, the device can be set to be 1,
when the front path is irrecoverable and damaged, the passability is set to 0;
for recoverable impairments, then passability is set to 0, and passability is incremented over time, passability recovery
Figure FDA0002368303510000031
The evaluation formula with respect to time can be calculated by the following formula,
Figure FDA0002368303510000032
Figure FDA0002368303510000033
Figure FDA0002368303510000034
the passability probability at time t +1,
Figure FDA0002368303510000035
setting the passability probability at the time t and the recovery speed coefficient according to the characteristics of the recoverable obstacle, wherein delta t is the time interval between the updating time and the last updating and has the unit of second;
updating reliability matrix of topological environment model
Figure FDA0002368303510000036
CN202010042703.6A 2020-01-15 2020-01-15 Search and rescue robot target search method based on path passing probability Active CN111413962B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010042703.6A CN111413962B (en) 2020-01-15 2020-01-15 Search and rescue robot target search method based on path passing probability

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010042703.6A CN111413962B (en) 2020-01-15 2020-01-15 Search and rescue robot target search method based on path passing probability

Publications (2)

Publication Number Publication Date
CN111413962A true CN111413962A (en) 2020-07-14
CN111413962B CN111413962B (en) 2022-11-11

Family

ID=71490866

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010042703.6A Active CN111413962B (en) 2020-01-15 2020-01-15 Search and rescue robot target search method based on path passing probability

Country Status (1)

Country Link
CN (1) CN111413962B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113298940A (en) * 2021-05-25 2021-08-24 中南大学 3D topological map construction method, system and storage medium for rescue area
CN114397894A (en) * 2021-12-29 2022-04-26 杭州电子科技大学 Mobile robot target searching method simulating human memory
CN114955455A (en) * 2022-06-14 2022-08-30 乐聚(深圳)机器人技术有限公司 Robot control method, server, robot, and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004298975A (en) * 2003-03-28 2004-10-28 Sony Corp Robot device and obstacle searching method
JP2005032196A (en) * 2003-07-11 2005-02-03 Japan Science & Technology Agency System for planning path for moving robot
US20110035087A1 (en) * 2009-08-10 2011-02-10 Samsung Electronics Co., Ltd. Method and apparatus to plan motion path of robot
CN104317293A (en) * 2014-09-19 2015-01-28 南京邮电大学 City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm
CN105203097A (en) * 2015-10-14 2015-12-30 中国矿业大学 Multi-robot multi-target point rescue route planning method fit for after-calamity environment
CN108596382A (en) * 2018-04-18 2018-09-28 中国地质大学（武汉） Rescue path planing method based on a lot of points, point more to be rescued, multiple terminals
CN109405828A (en) * 2018-07-30 2019-03-01 浙江工业大学 Mobile robot global optimum path planning method based on LTL-A* algorithm

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004298975A (en) * 2003-03-28 2004-10-28 Sony Corp Robot device and obstacle searching method
JP2005032196A (en) * 2003-07-11 2005-02-03 Japan Science & Technology Agency System for planning path for moving robot
US20110035087A1 (en) * 2009-08-10 2011-02-10 Samsung Electronics Co., Ltd. Method and apparatus to plan motion path of robot
CN104317293A (en) * 2014-09-19 2015-01-28 南京邮电大学 City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm
CN105203097A (en) * 2015-10-14 2015-12-30 中国矿业大学 Multi-robot multi-target point rescue route planning method fit for after-calamity environment
CN108596382A (en) * 2018-04-18 2018-09-28 中国地质大学（武汉） Rescue path planing method based on a lot of points, point more to be rescued, multiple terminals
CN109405828A (en) * 2018-07-30 2019-03-01 浙江工业大学 Mobile robot global optimum path planning method based on LTL-A* algorithm

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
李晓静等: "煤炭勘探及救援机器人最优路径规划研究", 《工矿自动化》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113298940A (en) * 2021-05-25 2021-08-24 中南大学 3D topological map construction method, system and storage medium for rescue area
CN113298940B (en) * 2021-05-25 2022-08-09 中南大学 3D topological map construction method, system and storage medium for rescue area
CN114397894A (en) * 2021-12-29 2022-04-26 杭州电子科技大学 Mobile robot target searching method simulating human memory
CN114955455A (en) * 2022-06-14 2022-08-30 乐聚(深圳)机器人技术有限公司 Robot control method, server, robot, and storage medium

Also Published As

Publication number Publication date
CN111413962B (en) 2022-11-11

Similar Documents

Publication Publication Date Title
CN111413962B (en) Search and rescue robot target search method based on path passing probability
CN106840148B (en) Wearable positioning and path guiding method based on binocular camera under outdoor working environment
WO2020237996A1 (en) Vehicle pose correction method and device
Berger et al. Autonomous driving-5 years after the urban challenge: The anticipatory vehicle as a cyber-physical system
JP6790417B2 (en) Information processing equipment and information processing server
EP2169503B1 (en) Multi-vehicle high intensity perception
EP2169498B1 (en) Vehicle with high integrity perception system
US8478493B2 (en) High integrity perception program
US8818567B2 (en) High integrity perception for machine localization and safeguarding
CN103576686B (en) Automatic guide and obstacle avoidance method for robot
CN104714555B (en) Three-dimensional independent exploration method based on edge
WO2020048623A1 (en) Estimation of a pose of a robot
CN106767791A (en) A kind of inertia/visual combination air navigation aid using the CKF based on particle group optimizing
JP6935947B2 (en) Methods and devices for providing advanced pedestrian assistance systems to protect pedestrians using smartphones
CN110782095A (en) Fire fighting route planning method and device, electronic equipment and storage medium
JP2020123346A (en) Method and device for performing seamless parameter switching by using location based algorithm selection to achieve optimized autonomous driving in each of regions
CN104931051A (en) Indoor electronic map drawing and navigating method and system based on big data
KR20160048530A (en) Method and apparatus for generating pathe of autonomous vehicle
CN113686347A (en) Method and device for generating robot navigation path
CN115639823A (en) Terrain sensing and movement control method and system for robot under rugged and undulating terrain
CN107783554A (en) UAV Flight Control method and device
CN108282221B (en) Multi-unmanned aerial vehicle safety communication strategy for reducing unsafe area
Baudoin et al. View-finder: robotics assistance to fire-fighting services and crisis management
CN114234991A (en) Navigation path planning method and device, computer equipment and storage medium
KR102289752B1 (en) A drone for performring route flight in gps blocked area and methed therefor

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