CN118131778B - Intelligent emergency disposal robot and obstacle avoidance method thereof - Google Patents
Intelligent emergency disposal robot and obstacle avoidance method thereof Download PDFInfo
- Publication number
- CN118131778B CN118131778B CN202410551713.0A CN202410551713A CN118131778B CN 118131778 B CN118131778 B CN 118131778B CN 202410551713 A CN202410551713 A CN 202410551713A CN 118131778 B CN118131778 B CN 118131778B
- Authority
- CN
- China
- Prior art keywords
- obstacle
- channel
- emergency
- robot
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000033001 locomotion Effects 0.000 claims abstract description 41
- 230000001105 regulatory effect Effects 0.000 claims abstract description 10
- 230000004888 barrier function Effects 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 230000015654 memory Effects 0.000 claims description 14
- 238000012937 correction Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 8
- 230000001276 controlling effect Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004891 communication Methods 0.000 description 7
- 238000002955 isolation Methods 0.000 description 6
- 230000008569 process Effects 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000004075 alteration Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012550 audit Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application provides an intelligent emergency disposal robot and an obstacle avoidance method thereof, wherein an emergency disposal area is divided into a channel safety area and an emergency obstacle area through obstacle distribution data; determining the obstacle convergence entropy of the channel when passing through each obstacle point according to the emergency obstacle region, determining an initial safety channel according to the channel safety region, and correcting by the channel corner of the initial safety channel and all the obstacle convergence entropy, so as to obtain the obstacle density of the corrected channel; determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of emergency treatment at the current moment; the obstacle avoidance direction of the robot at the next moment is regulated and controlled based on the predicted result by predicting the channel direction through the obstacle density and the emergency urgent factors, the obstacle avoidance control of the robot is completed, the intelligent real-time adjustment of the obstacle avoidance direction of the intelligent emergency treatment robot is realized, and therefore the autonomous obstacle avoidance efficiency of the intelligent emergency treatment robot is improved.
Description
Technical Field
The application relates to the technical field of automatic control of robots, in particular to an intelligent emergency disposal robot and an obstacle avoidance method thereof.
Background
The technical field of automation control of robots covers a series of knowledge and techniques related to the design of automation systems, control algorithms, sensor technology, actuator design and the like. The aim of the field is to realize the automatic control of a system, a process or equipment so as to improve the efficiency, reduce the cost and improve the quality, and the system can be operated under the supervision of no or few persons, and the automatic control of an intelligent emergency treatment robot is equipment combining artificial intelligence and robot technology and has the functions of autonomous navigation, environment sensing, task execution and the like.
In general, an intelligent emergency disposal robot can rapidly respond in emergency situations and disaster events, perform tasks such as fire suppression, rescue search and rescue, chemical leakage processing and the like, real-time monitoring and disposal of site situations are achieved through remote control and autonomous decision making, so that emergency response efficiency and safety are improved, casualties and property loss are reduced, the time for the intelligent emergency disposal robot to reach an emergency disposal target is a key factor for improving emergency response efficiency and safety, reasonable planning of a channel to the robot is crucial, the prior art generally adopts an obstacle avoidance method of an optimal path for the channel planning of the robot, the obstacle avoidance method does not consider complex changes of external environments where the intelligent emergency disposal robot is located, the problem of obstacle delay exists when the intelligent emergency disposal robot adopts the obstacle avoidance method is possibly caused, and accordingly safety problems caused by untimely emergency disposal are caused, wherein the obstacle delay refers to how the intelligent emergency disposal robot still uses the set channel when the intelligent emergency disposal robot changes in a moving midway obstacle, and therefore, the problem of the intelligent emergency disposal robot in the real-time is solved by considering the changes of the external environment where the obstacle is predicted by the intelligent emergency disposal robot, and the problem of the intelligent emergency disposal robot is avoided in the industry.
Disclosure of Invention
The application provides an intelligent emergency treatment robot and an obstacle avoidance method thereof, which can realize intelligent real-time prediction of the obstacle avoidance direction of the intelligent emergency treatment robot, thereby improving the autonomous obstacle avoidance efficiency of the intelligent emergency treatment robot.
In a first aspect, the present application provides an obstacle avoidance method of an intelligent emergency handling robot, including:
after the intelligent emergency treatment robot is started, acquiring obstacle information in a robot sensor at the current moment to obtain an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area;
Dividing the emergency treatment area into a channel safety area and an emergency obstacle area through the obstacle distribution data;
Determining the obstacle convergence entropy of the channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, determining an initial safety channel according to the channel safety area, and correcting the initial safety channel through the channel corner of the initial safety channel and all the obstacle convergence entropy, so as to obtain the obstacle density of the corrected channel;
Acquiring a historical movement record of a robot, and determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of the emergency treatment at the current moment;
and predicting the channel direction of the robot through the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a predicted result, and repeating the steps to finish the obstacle avoidance control of the robot.
In some embodiments, dividing the emergency treatment area into the lane safety zone and the emergency obstacle zone by the obstacle distribution data specifically includes:
determining an obstacle distribution domain of an emergency treatment area of the robot according to the obstacle distribution data;
The emergency treatment area is divided into a channel safety area and an emergency obstacle area through the obstacle distribution area.
In some embodiments, determining the obstacle distribution domain of the contingency treatment zone of the robot from the obstacle distribution data specifically comprises:
rasterizing the emergency treatment area to obtain an emergency grid domain;
preprocessing the obstacle distribution data;
And acquiring the obstacle information of each emergency grid block in the emergency grid domain from the preprocessed obstacle distribution data, so as to determine the obstacle distribution domain.
In some embodiments, determining the obstacle convergence entropy of the channel when the robot passes each obstacle point according to the emergency obstacle region and the current position of the robot specifically includes:
selecting an obstacle point and determining the effective cross-sectional area of the obstacle point;
Determining a cost adjustment coefficient passing through the obstacle point according to the position distance from the current position of the robot to the position of the obstacle point and the effective cross-sectional area;
determining an obstacle avoidance channel from the current position to the position of the obstacle point according to the emergency obstacle region;
And determining the obstacle convergence entropy of the channel when the robot passes through the obstacle point according to the obstacle avoidance channel and the cost adjustment coefficient, and continuously determining the obstacle convergence entropy of the channel when the robot passes through the rest obstacle points.
In some embodiments, correcting the initial safe channel through the channel corner and all obstacle convergence entropy of the initial safe channel, so as to obtain the obstacle density of the corrected channel specifically includes:
Selecting one channel corner of the initial safe channel, and determining a cost factor of the channel corner;
determining a correction coefficient through the obstacle convergence entropy of the obstacle point where the channel corner is located and the cost factor;
correcting the channel corners according to the correction coefficients, and continuously correcting the remaining channel corners, so as to determine a corrected safe channel through all the channel corners and the initial safe channel;
and carrying out density statistics on the corrected safe channel to obtain the barrier density of the corrected channel.
In some embodiments, determining the emergency urgency factor for the emergency treatment from the historical movement record and an emergency limit time for the emergency treatment at the current time specifically comprises:
determining a defined correlation coefficient from the historical movement record;
And determining an emergency urgency factor according to the emergency limiting time and the limiting correlation coefficient.
In some embodiments, predicting the lane direction of the robot from the obstacle density and the contingency factor specifically includes:
Determining an obstacle avoidance adjustment value from the obstacle density and the emergency urgency factor;
and predicting the channel direction of the robot through the obstacle avoidance adjusting value.
In a second aspect, the present application provides an intelligent emergency treatment robot, including an obstacle avoidance unit, the obstacle avoidance unit includes:
The acquisition module is used for acquiring obstacle information in the robot sensor at the current moment after the intelligent emergency treatment robot is started to obtain an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area;
the processing module is used for dividing the emergency treatment area into a channel safety area and an emergency obstacle area through the obstacle distribution data;
The processing module is also used for determining the obstacle convergence entropy of the channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, determining an initial safety channel according to the channel safety area, and correcting the initial safety channel through the channel corner of the initial safety channel and all obstacle convergence entropy so as to obtain the obstacle density of the corrected channel;
the processing module is also used for acquiring a historical movement record of the robot, and determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of the emergency treatment at the current moment;
And the execution module is used for predicting the channel direction of the robot through the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a predicted result, and repeating the steps to finish the obstacle avoidance control of the robot.
In a third aspect, the present application provides a computer device, the computer device including a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that the computer device executes the obstacle avoidance method of the intelligent emergency treatment robot.
In a fourth aspect, the present application provides a computer readable storage medium, in which instructions or codes are stored, which when executed on a computer, cause the computer to implement the obstacle avoidance method of the intelligent emergency handling robot.
The technical scheme provided by the embodiment of the application has the following beneficial effects:
According to the intelligent emergency treatment robot and the obstacle avoidance method thereof, after the intelligent emergency treatment robot is started, obstacle information in a robot sensor at the current moment is acquired, and an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area are obtained; dividing the emergency treatment area into a channel safety area and an emergency obstacle area through the obstacle distribution data; determining obstacle convergence entropy of a channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, wherein the obstacle value is used for measuring obstacle passing difficulty of the robot from the current position to each obstacle point, an initial safety channel is determined according to the channel safety area, the initial safety channel is corrected through channel corners and all obstacle convergence entropy of the initial safety channel, and further, the obstacle density of the corrected channel is obtained, wherein the obstacle density represents the distribution condition of obstacles in a unit area, the obstacle density is used for measuring the obstacle passing difficulty parameter from the current position to the target position, the obstacle density is larger, the obstacle passing from the current position to the target position is more complex, and the obstacle passing difficulty from the current position to the target position is larger; acquiring a historical movement record of a robot, and determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of the emergency treatment at the current moment, wherein the emergency urgent factor represents the emergency degree used for describing each emergency treatment; and predicting the channel direction of the robot through the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a predicted result, and repeating the steps to finish the obstacle avoidance control of the robot.
According to the application, firstly, the channel corner of the initial safety channel and the convergence entropy of all obstacles are used for determining the obstacle density of the corrected channel, when the channel corner is smaller than a certain value, the influence on the movement of the robot is small, but the channel smoothness can be improved to a certain extent, and the efficiency of passing the obstacle can be effectively improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the application, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
FIG. 1 is an exemplary flow chart of an obstacle avoidance method for an intelligent emergency handling robot, according to some embodiments of the application;
FIG. 2 is a schematic flow chart illustrating determining obstacle convergence entropy in accordance with some embodiments of the application;
FIG. 3 is a schematic flow chart of predicting channel directions shown in some embodiments according to the application;
FIG. 4 is a schematic diagram of exemplary hardware and/or software of an obstacle avoidance unit, shown in accordance with some embodiments of the present application;
fig. 5 is a schematic structural view of a computer device to which an obstacle avoidance method of an intelligent emergency handling robot is applied, according to some embodiments of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiment of the application provides an intelligent emergency disposal robot and an obstacle avoidance method thereof, and the intelligent emergency disposal robot is characterized in that an emergency disposal area is divided into a channel safety area and an emergency obstacle area through obstacle distribution data; determining the obstacle convergence entropy of the channel when passing through each obstacle point according to the emergency obstacle region, determining an initial safety channel according to the channel safety region, and correcting by the channel corner of the initial safety channel and all the obstacle convergence entropy, so as to obtain the obstacle density of the corrected channel; determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of emergency treatment at the current moment; the obstacle avoidance direction of the robot at the next moment is regulated and controlled based on the predicted result by predicting the channel direction through the obstacle density and the emergency urgent factors, the obstacle avoidance control of the robot is completed, the intelligent real-time adjustment of the obstacle avoidance direction of the intelligent emergency treatment robot is realized, and therefore the autonomous obstacle avoidance efficiency of the intelligent emergency treatment robot is improved.
In order to better understand the above technical solutions, the following detailed description will refer to the accompanying drawings and specific embodiments. Referring to fig. 1, which is an exemplary flowchart of an obstacle avoidance method of an intelligent emergency handling robot according to some embodiments of the present application, the obstacle avoidance method of the intelligent emergency handling robot mainly includes the steps of:
In step 101, after the intelligent emergency treatment robot is started, obstacle information in a robot sensor at the current moment is acquired, and an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area are obtained.
The emergency treatment area is an area in which an activity of the robot is required to be performed when performing emergency treatment, and when specifically implemented, the range of emergency treatment of the robot at the current time may be defined as an emergency treatment area.
In particular, in the present application, the obstacle information represents information of an object or an environmental characteristic of the robot, which is obstructed by the robot when the robot moves in a two-dimensional area, the obstacle information includes an obstacle position and an obstacle grade, wherein the obstacle grade represents the capability of the obstacle to obstruct the robot, the obstacle grade is related to the object volume and the environmental severity, the obstacle grade can be directly obtained in an obstacle grade standard of the sensor of the robot, the obstacle grade is classified into 10 grades (namely, 1-10), and the greater the obstacle grade is, the greater the capability of the obstacle to obstruct the robot is, and 10 is an impenetrable obstacle.
At step 102, the emergency treatment area is divided into a lane safety area and an emergency obstacle area by the obstacle distribution data.
It should be noted that, the channel safety zone represents a zone where the robot motion is not affected at all at the current moment; the emergency obstacle area represents an area where the robot motion needs to consider obstacle avoidance when emergency treatment is performed at the current moment.
In some embodiments, the division of the emergency treatment area into the lane safety zone and the emergency obstacle zone by the obstacle distribution data may be accomplished by:
determining an obstacle distribution domain of an emergency treatment area of the robot according to the obstacle distribution data;
The emergency treatment area is divided into a channel safety area and an emergency obstacle area through the obstacle distribution area.
The obstacle distribution field is a block for describing obstacle level distribution information of an obstacle in the surrounding environment of the robot, and is composed of a plurality of obstacle level blocks, wherein the default level of the obstacle level block is 0 (i.e., no obstacle is present).
In the above embodiment, determining the obstacle distribution field of the emergency treatment area of the robot from the obstacle distribution data may be implemented by:
rasterizing the emergency treatment area to obtain an emergency grid domain;
preprocessing the obstacle distribution data;
And acquiring the obstacle information of each emergency grid block in the emergency grid domain from the preprocessed obstacle distribution data, so as to determine the obstacle distribution domain.
The emergency grid field is a block for describing the segmentation information of the robot surroundings, and is composed of a plurality of emergency grids.
When the method is specifically implemented, firstly, a remote sensing image rasterization tool (for example, ENVI) in the prior art is used for dividing an emergency treatment area into a preset number of small areas, each small area is used as an emergency grid block, each emergency grid block is arranged according to the position corresponding to the emergency treatment area to obtain an emergency grid domain, wherein the preset number can be determined according to the area of the emergency treatment area and the area occupied by a robot during movement, in other embodiments, the ratio of the area of the emergency treatment area to the area occupied by the robot during movement can be used as the preset number, the method is not limited, and each emergency grid block is ensured to be larger than the area occupied by the robot during movement, and the method is not limited; secondly, preprocessing obstacle distribution data by adopting denoising processing and data smoothing processing in the prior art so as to ensure the accuracy and reliability of obstacle information in the obstacle distribution data; and finally, selecting one piece of obstacle information (comprising an obstacle grade and an obstacle position) in the preprocessed obstacle distribution data, filling the obstacle grade into an emergency grid block corresponding to the obstacle position in an emergency grid domain, obtaining an obstacle grade block corresponding to the obstacle information, continuously determining the obstacle grade blocks corresponding to the rest obstacle information, and arranging all the obstacle grade blocks according to the obstacle position to be used as an obstacle distribution domain.
In the above embodiment, the division of the emergency treatment area into the channel safety area and the emergency obstacle area by the obstacle distribution area may be achieved by:
performing marginalization treatment on the obstacle distribution domain to determine a channel isolation boundary;
the emergency treatment area is divided into a channel safety area and an emergency obstacle area by the channel isolation boundary.
The lane isolation boundary represents a boundary for dividing a safe area from an obstacle area in an emergency treatment area, and is used when the safe area is too small or the lane of the safe area is insufficient to satisfy an emergency treatment demand.
When the method is specifically implemented, firstly, obstacle grade blocks with the value of 0 and the adjacent value (namely, the value of adjacent grade is fast) larger than 0 are screened out from an obstacle distribution domain, and all the screened obstacle grade blocks are connected to be used as channel isolation boundaries; and then, selecting one emergency grid on two sides of the channel isolation boundary, if the value of the emergency grid is larger than 0, taking the emergency grid as one emergency barrier sub-block in an emergency barrier zone, if the value of the emergency grid is 0, taking the emergency grid as one channel safety sub-block in a channel safety zone, continuously judging the rest emergency grids on two sides of the channel isolation boundary, and obtaining all the emergency barrier sub-blocks and channel safety sub-blocks, taking all the emergency barrier sub-blocks as the emergency barrier zone and taking all the channel safety sub-blocks as the channel safety zone.
In step 103, determining the obstacle convergence entropy of the channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, determining an initial safety channel according to the channel safety area, and correcting the initial safety channel by the channel corner of the initial safety channel and all the obstacle convergence entropy, thereby obtaining the obstacle density of the corrected channel.
It should be noted that, in the present application, the obstacle convergence entropy refers to an obstacle value that the robot passes from the current position to each obstacle point, and the obstacle value is a parameter for measuring the difficulty of the robot passing through the obstacle; the obstacle point represents a point formed by emergency obstacle sub-blocks with adjacent obstacle levels in the emergency treatment area, and the obstacle sub-blocks with adjacent obstacle positions and obstacle level differences of 1 in the emergency obstacle area can be combined into one obstacle point.
In some embodiments, the obstacle convergence entropy of the channel when the robot passes through each obstacle point is determined according to the emergency obstacle area and the current position of the robot, and the description is given with reference to fig. 2, which is a schematic flow chart of determining the obstacle convergence entropy in some embodiments of the present application, where the determining the obstacle convergence entropy may be implemented by adopting the following steps:
in step 1031, selecting an obstacle point, and determining an effective cross-sectional area of the obstacle point;
in step 1032, determining a cost adjustment factor through the obstacle point from the position spacing of the current position of the robot to the position of the obstacle point and the effective cross-sectional area;
in step 1033, determining an obstacle avoidance channel from the current position to the position of the obstacle point according to the emergency obstacle region;
In step 1034, determining the obstacle convergence entropy of the channel when the robot passes through the obstacle point according to the obstacle avoidance channel and the cost adjustment coefficient, and continuing to determine the obstacle convergence entropy of the channel when the robot passes through the rest obstacle points.
When the method is specifically implemented, firstly, one obstacle point is selected, the number of obstacle grade sub-blocks in the obstacle point is used as an effective cross-sectional area, and the effective cross-sectional area is used for describing the size of the obstacle point; and secondly, taking the linear distance from the current position of the robot to the position of the obstacle point as a position distance, taking the ratio of the position distance to the effective cross section area as a cost adjustment coefficient, taking the ratio of the position distance to the effective cross section area as the cost adjustment coefficient, modeling an emergency obstacle area to obtain an emergency obstacle model, determining an obstacle avoidance channel from the current position to the position of the obstacle point by using the emergency obstacle model, determining the values of all emergency obstacle sub-blocks passing through the obstacle avoidance channel, summing the sum, taking the product of the sum result and the cost adjustment coefficient as the obstacle convergence entropy of the obstacle point, and continuously determining the obstacle convergence entropy of the obstacle point.
In some embodiments, determining an initial safe channel from the channel safe zone may be accomplished by: the shortest path from the current position to the target position is acquired in the safe area of the channel by using a path search algorithm (for example, RRT algorithm) in the prior art, and the shortest path can be used as an initial safe channel, and it should be noted that the initial safe channel represents the shortest path when the robot completely passes through the safe area of the channel, the initial safe channel facilitates the subsequent determination of the worst time cost of the obstacle path, and if the initial safe channel does not exist, the obstacle rating standard of the robot sensor in step 101 is adjusted upwards until the initial safe channel is obtained.
It should be noted that, the obstacle density refers to the distribution condition of the obstacles in the unit area, the obstacle density is used to measure the parameter of obstacle avoidance difficulty from the current position to the target position, the greater the obstacle density, the more complex the obstacle passes from the current position to the target position, the greater the obstacle avoidance difficulty from the current position to the target position, and the magnitude of the obstacle density is related to the number density, the distribution condition and the obstacle distance of the obstacles; the lane corner represents the steering angle of the robot in the lane process from the current position to the target position, all steering angles of the robot in the lane process from the current position to the target position can be used as the lane corner, when the lane corner is smaller than the calibrated steering angle, the influence on the movement of the robot is smaller, but the smoothness of the lane can be improved to a certain extent, the efficiency of passing through obstacles can be effectively improved, wherein the calibrated steering angle can be preset according to the steering performance of the robot, the range of the calibrated steering angle is 0 degree to the maximum steering angle of the robot, the maximum steering angle is one of parameters describing the steering performance of the robot, the larger the maximum steering angle is, the better the steering performance of the robot is, and the larger the calibrated steering angle can be preset.
In some embodiments, the initial safe channel is corrected by the channel angle and all obstacle convergence entropy of the initial safe channel, so as to obtain the obstacle density of the corrected channel, which can be achieved by the following steps:
Selecting one channel corner of the initial safe channel, and determining a cost factor of the channel corner;
determining a correction coefficient through the obstacle convergence entropy of the obstacle point where the channel corner is located and the cost factor;
correcting the channel corners according to the correction coefficients, and continuously correcting the remaining channel corners, so as to determine a corrected safe channel through all the channel corners and the initial safe channel;
and carrying out density statistics on the corrected safe channel to obtain the barrier density of the corrected channel.
When the method is specifically implemented, firstly, one channel corner of the initial safety channel is selected, if the channel corner is larger than 0 and smaller than one third of the nominal steering angle, the cost factor is 0.8, if the channel corner is larger than one third of the nominal steering angle and smaller than two thirds of the nominal steering angle, the cost factor is 0.9, and if the channel corner is larger than two thirds of the nominal steering angle and smaller than the nominal steering angle, the cost factor is 1; secondly, determining a barrier point through the position of the channel corner, obtaining the barrier convergence entropy of the barrier point, and taking the product of the barrier convergence entropy and the cost factor as a correction coefficient, wherein the correction coefficient is a proportional coefficient for smoothly correcting the channel corner; and then taking the product of the correction coefficient and the channel corner downstream correction coefficient as a corrected channel corner, continuously determining the channel corner after the correction of the residual channel corner in the initial safety channel, connecting the corrected channel corner in the initial safety channel with the original channel in the initial safety channel to obtain a corrected safety channel, wherein the corrected safety channel represents the channel obtained after the correction of the channel corner of the initial safety channel, finally selecting one obstacle grade block in the corrected channel, taking the average value of the obstacle grade block and the values of the obstacle grade blocks at the left side and the right side of the obstacle grade block as the density of the obstacle grade block, continuously determining the density of the residual obstacle grade block in the corrected channel, and taking the sum of all densities as the obstacle density.
In step 104, a historical movement record of the robot is obtained, and an emergency urgency factor of emergency treatment is determined according to the historical movement record and an emergency limit time of emergency treatment at the current moment.
In specific implementation, all movement information from the beginning to the current moment of emergency treatment at the current moment is acquired, and all movement information can be used as a history movement record, and it is to be noted that each movement information represents complete one movement process information in one emergency treatment, and the movement information comprises an initial position of the emergency treatment, a target position of the emergency treatment, an emergency limiting time and a completion time.
It should be noted that the emergency urgency factor is used to describe the degree of urgency of each emergency treatment; the emergency limiting time is the time limited by completing emergency treatment at the current moment; the emergency limit time is used to ensure the response speed to disasters so as to avoid larger negative effects, and in specific implementation, the emergency limit time for emergency treatment at the current moment can be obtained by evaluating the emergent disasters through a disaster evaluation tool (for example: HAZUS).
In some embodiments, determining the contingency urgency factor for the contingency treatment from the historical movement record and a contingency limit time for the contingency treatment at the current time may be accomplished by:
determining a defined correlation coefficient from the historical movement record;
And determining an emergency urgency factor according to the emergency limiting time and the limiting correlation coefficient.
When the method is specifically implemented, firstly, one piece of movement information in a history movement record is selected, the ratio of the completion time to the emergency limiting time in the movement information is used as the treatment completion degree, the treatment completion degree is used for measuring the completion progress condition of emergency treatment, the ratio of the distance from the initial position to the target position of emergency treatment in the movement information to the treatment completion degree is used as the correlation coefficient of the movement information, the correlation coefficient represents the ratio coefficient of the emergency progress to the completion distance in each emergency treatment, and the average value of all the correlation coefficients is used as the limiting correlation coefficient; then, the ratio of the limit correlation coefficient to the emergency limit time is taken as an emergency urgency factor.
In step 105, the channel direction of the robot is predicted by the obstacle density and the emergency urgent factor, and then the obstacle avoidance channel direction of the robot at the next moment is regulated and controlled based on the predicted result, and the steps are repeated, so that the obstacle avoidance control of the robot is completed.
In some embodiments, the obstacle density and the emergency forcing factor are used to predict the channel direction of the robot, and the figure is described with reference to fig. 3, which is a schematic flow chart of predicting the channel direction in some embodiments of the present application, where the predicting the channel direction may be implemented by the following steps:
in step 1051, determining an obstacle avoidance adjustment value from the obstacle density and the contingency factor;
In step 1052, the channel direction of the robot is predicted by the obstacle avoidance adjustment.
When the method is specifically implemented, firstly, taking the product of the obstacle density and the emergency urgent factor as an obstacle avoidance adjustment value, wherein the obstacle avoidance adjustment value is used for measuring the deviation degree of the obstacle avoidance direction relative to the target direction; then, the channel direction of the robot at the current moment is obtained; finally, the existing obstacle avoidance model can be used for predicting the obstacle avoidance at the next moment of the robot by taking the obstacle avoidance adjustment value as a parameter of the obstacle avoidance model.
In some embodiments, the regulation and control of the obstacle avoidance channel direction of the robot at the next moment based on the predicted result may be implemented in the following manner, that is: and taking the predicted result as the obstacle avoidance channel direction of the robot at the next moment.
When the method is specifically implemented, the steps are repeated, the obstacle avoidance channel direction of the robot in the subsequent moment is continuously regulated and controlled until the robot reaches the target position, and the channel formed by all the obstacle avoidance channel directions is used as the obstacle avoidance channel of the robot, so that the obstacle avoidance control of the robot is completed.
According to the application, firstly, the channel corner of the initial safety channel and the convergence entropy of all obstacles are used for determining the obstacle density of the corrected channel, when the channel corner is smaller than a certain value, the influence on the movement of the robot is small, but the channel smoothness can be improved to a certain extent, and the efficiency of passing the obstacle can be effectively improved.
Additionally, in another aspect of the present application, in some embodiments, the present application provides an intelligent contingency treatment robot further including an obstacle avoidance unit, referring to fig. 4, which is a schematic diagram of exemplary hardware and/or software of the obstacle avoidance unit, according to some embodiments of the present application, including: the acquisition module 201, the processing module 202, and the execution module 203 are respectively described as follows:
the acquisition module 201 is mainly used for acquiring obstacle information in a robot sensor at the current moment after the intelligent emergency treatment robot is started to obtain an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area;
The processing module 202 is used for dividing the emergency treatment area into a channel safety area and an emergency obstacle area according to the obstacle distribution data by the processing module 202 in the application;
It should be noted that, in the present application, the processing module 202 is further configured to determine, according to the emergency obstacle area and the current position of the robot, an obstacle convergence entropy of the channel when the robot passes through each obstacle point, determine an initial safe channel according to the channel safety area, and correct the initial safe channel according to the channel angle of the initial safe channel and all the obstacle convergence entropies, so as to obtain an obstacle density of the corrected channel;
In addition, the processing module 202 is further configured to obtain a historical movement record of the robot, and determine an emergency urgent factor for emergency treatment according to the historical movement record and an emergency limiting time for emergency treatment at the current moment;
And the execution module 203, wherein the execution module 203 is mainly used for predicting the channel direction of the robot according to the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a predicted result, and repeating the steps to finish the obstacle avoidance control of the robot.
The foregoing describes in detail examples of the intelligent emergency handling robot and the obstacle avoidance method thereof provided by the embodiments of the present application, and it may be understood that, in order to implement the foregoing functions, the corresponding devices include corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as hardware or combinations of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In some embodiments, the present application further provides a computer device, where the computer device includes a memory and a processor, where the memory is configured to store a computer program, and the processor is configured to call and run the computer program from the memory, so that the computer device performs the obstacle avoidance method of the intelligent emergency treatment robot.
In some embodiments, reference is made to fig. 5, in which the dashed line indicates that the unit or the module is optional, which is a schematic structural diagram of a computer device implementing the obstacle avoidance method of the intelligent emergency handling robot according to an embodiment of the present application. The obstacle avoidance method of the intelligent emergency handling robot in the above embodiment may be implemented by a computer device shown in fig. 5, where the computer device includes at least one processor 301, a memory 302, and at least one communication unit 305, and the computer device may be a terminal device or a server or a chip.
Processor 301 may be a general purpose processor or a special purpose processor. For example, the processor 301 may be a central processing unit (central processing unit, CPU) which may be used to control, execute and process data of a software program for a computer device, which may further comprise a communication unit 305 for enabling input (reception) and output (transmission) of signals.
For example, the computer device may be a chip, the communication unit 305 may be an input and/or output circuit of the chip, or the communication unit 305 may be a communication interface of the chip, which may be an integral part of a terminal device or a network device or other devices.
For another example, the computer device may be a terminal device or a server, the communication unit 305 may be a transceiver of the terminal device or the server, or the communication unit 305 may be a transceiver circuit of the terminal device or the server.
The computer device may include one or more memories 302 having a program 304 stored thereon, the program 304 being executable by the processor 301 to generate instructions 303 such that the processor 301 performs the methods described in the method embodiments described above in accordance with the instructions 303. Optionally, data (e.g., a goal audit model) may also be stored in memory 302. Alternatively, the processor 301 may also read data stored in the memory 302, which may be stored at the same memory address as the program 304, or which may be stored at a different memory address than the program 304.
The processor 301 and the memory 302 may be provided separately or may be integrated together, for example, on a System On Chip (SOC) of the terminal device.
It should be understood that the steps of the above-described method embodiments may be accomplished by logic circuitry in hardware or instructions in software in the processor 301, and the processor 301 may be a CPU, digital signal processor (DIGITAL SIGNAL processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field programmable gate array (field programmable GATE ARRAY, FPGA), or other programmable logic device, such as discrete gates, transistor logic, or discrete hardware components.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
For example, in some embodiments, the present application further provides a computer readable storage medium having instructions or code stored therein, which when executed on a computer, cause the computer to implement the obstacle avoidance method of the intelligent emergency handling robot described above.
While preferred embodiments of the present application 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. It is therefore intended that the following claims be interpreted as including the preferred embodiments and all such alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the spirit or scope of the application. Thus, it is intended that the present application also include such modifications and alterations insofar as they come within the scope of the appended claims or the equivalents thereof.
Claims (10)
1. The obstacle avoidance method of the intelligent emergency disposal robot is characterized by comprising the following steps of:
after the intelligent emergency treatment robot is started, acquiring obstacle information in a robot sensor at the current moment to obtain an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area;
Dividing the emergency treatment area into a channel safety area and an emergency obstacle area through the obstacle distribution data;
Determining the obstacle convergence entropy of the channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, determining an initial safety channel according to the channel safety area, and correcting the initial safety channel through the channel corner of the initial safety channel and all the obstacle convergence entropy, so as to obtain the obstacle density of the corrected channel;
Acquiring a historical movement record of a robot, and determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of the emergency treatment at the current moment;
Predicting the channel direction of the robot according to the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a predicted result, and repeating the steps to finish the obstacle avoidance control of the robot;
The obstacle convergence entropy refers to an obstacle value which is passed by the robot from the current position to each obstacle point, and the obstacle value is a parameter used for measuring the difficulty of the robot passing the obstacle; the emergency urgency factor is a quantized value that is used to describe the degree of urgency of each emergency treatment.
2. The method of claim 1, wherein dividing the emergency treatment area into a channel safety zone and an emergency barrier zone by the barrier distribution data specifically comprises:
determining an obstacle distribution domain of an emergency treatment area of the robot according to the obstacle distribution data;
The emergency treatment area is divided into a channel safety area and an emergency obstacle area through the obstacle distribution area.
3. The method of claim 2, wherein determining the obstacle distribution domain of the contingency treatment zone of the robot from the obstacle distribution data comprises:
rasterizing the emergency treatment area to obtain an emergency grid domain;
preprocessing the obstacle distribution data;
And acquiring the obstacle information of each emergency grid block in the emergency grid domain from the preprocessed obstacle distribution data, so as to determine the obstacle distribution domain.
4. The method of claim 1, wherein determining the obstacle convergence entropy of the channel as the robot passes each obstacle point based on the emergency obstacle region and the current position of the robot comprises:
selecting an obstacle point and determining the effective cross-sectional area of the obstacle point;
Determining a cost adjustment coefficient passing through the obstacle point according to the position distance from the current position of the robot to the position of the obstacle point and the effective cross-sectional area;
determining an obstacle avoidance channel from the current position to the position of the obstacle point according to the emergency obstacle region;
And determining the obstacle convergence entropy of the channel when the robot passes through the obstacle point according to the obstacle avoidance channel and the cost adjustment coefficient, and continuously determining the obstacle convergence entropy of the channel when the robot passes through the rest obstacle points.
5. The method of claim 1, wherein correcting the initial safe channel by the channel rotation angle and all obstacle convergence entropies of the initial safe channel, and further obtaining the obstacle density of the corrected channel comprises:
Selecting one channel corner of the initial safe channel, and determining a cost factor of the channel corner;
determining a correction coefficient through the obstacle convergence entropy of the obstacle point where the channel corner is located and the cost factor;
correcting the channel corners according to the correction coefficients, and continuously correcting the remaining channel corners, so as to determine a corrected safe channel through all the channel corners and the initial safe channel;
and carrying out density statistics on the corrected safe channel to obtain the barrier density of the corrected channel.
6. The method of claim 1, wherein determining an emergency urgency factor for the emergency treatment based on the historical movement record and an emergency limit time for the emergency treatment at the current time comprises:
determining a defined correlation coefficient from the historical movement record;
And determining an emergency urgency factor according to the emergency limiting time and the limiting correlation coefficient.
7. The method of claim 1, wherein predicting the lane direction of the robot from the obstacle density and the emergency urgency factor specifically comprises:
Determining an obstacle avoidance adjustment value from the obstacle density and the emergency urgency factor;
and predicting the channel direction of the robot through the obstacle avoidance adjusting value.
8. The utility model provides an emergent robot of handling of intelligence, this emergent robot of handling of intelligence is including keeping away the barrier unit, its characterized in that, keep away the barrier unit and include:
The acquisition module is used for acquiring obstacle information in the robot sensor at the current moment after the intelligent emergency treatment robot is started to obtain an emergency treatment area of the robot and obstacle distribution data of the emergency treatment area;
the processing module is used for dividing the emergency treatment area into a channel safety area and an emergency obstacle area through the obstacle distribution data;
The processing module is also used for determining the obstacle convergence entropy of the channel when the robot passes through each obstacle point according to the emergency obstacle area and the current position of the robot, determining an initial safety channel according to the channel safety area, and correcting the initial safety channel through the channel corner of the initial safety channel and all obstacle convergence entropy so as to obtain the obstacle density of the corrected channel;
the processing module is also used for acquiring a historical movement record of the robot, and determining an emergency urgent factor of emergency treatment according to the historical movement record and the emergency limiting time of the emergency treatment at the current moment;
the execution module is used for predicting the channel direction of the robot according to the obstacle density and the emergency urgent factor, regulating and controlling the obstacle avoidance channel direction of the robot at the next moment based on a prediction result, and repeating the steps to finish the obstacle avoidance control of the robot;
The obstacle convergence entropy refers to an obstacle value which is passed by the robot from the current position to each obstacle point, and the obstacle value is a parameter used for measuring the difficulty of the robot passing the obstacle; the emergency urgency factor is a quantized value that is used to describe the degree of urgency of each emergency treatment.
9. A computer device, characterized in that the computer device comprises a memory for storing a computer program and a processor for calling and running the computer program from the memory, so that the computer device performs the obstacle avoidance method of the intelligent emergency treatment robot according to any one of claims 1 to 7.
10. A computer readable storage medium having instructions or code stored therein which, when run on a computer, cause the computer to perform the obstacle avoidance method of the intelligent emergency handling robot of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410551713.0A CN118131778B (en) | 2024-05-07 | 2024-05-07 | Intelligent emergency disposal robot and obstacle avoidance method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410551713.0A CN118131778B (en) | 2024-05-07 | 2024-05-07 | Intelligent emergency disposal robot and obstacle avoidance method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118131778A CN118131778A (en) | 2024-06-04 |
| CN118131778B true CN118131778B (en) | 2024-07-12 |
Family
ID=91232921
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410551713.0A Active CN118131778B (en) | 2024-05-07 | 2024-05-07 | Intelligent emergency disposal robot and obstacle avoidance method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118131778B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069075A (en) * | 2019-04-19 | 2019-07-30 | 北京航空航天大学 | A kind of cluster super maneuver barrier-avoiding method of imitative dove group emergency avoidance mechanism |
| CN116243727A (en) * | 2023-03-17 | 2023-06-09 | 厦门大学 | Unmanned carrier countermeasure and obstacle avoidance method for progressive deep reinforcement learning |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016033795A1 (en) * | 2014-09-05 | 2016-03-10 | SZ DJI Technology Co., Ltd. | Velocity control for an unmanned aerial vehicle |
| US11927965B2 (en) * | 2016-02-29 | 2024-03-12 | AI Incorporated | Obstacle recognition method for autonomous robots |
| CN114384920B (en) * | 2022-03-23 | 2022-06-10 | 安徽大学 | Dynamic obstacle avoidance method based on real-time construction of local grid map |
-
2024
- 2024-05-07 CN CN202410551713.0A patent/CN118131778B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110069075A (en) * | 2019-04-19 | 2019-07-30 | 北京航空航天大学 | A kind of cluster super maneuver barrier-avoiding method of imitative dove group emergency avoidance mechanism |
| CN116243727A (en) * | 2023-03-17 | 2023-06-09 | 厦门大学 | Unmanned carrier countermeasure and obstacle avoidance method for progressive deep reinforcement learning |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118131778A (en) | 2024-06-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113176776B (en) | Unmanned ship weather self-adaptive obstacle avoidance method based on deep reinforcement learning | |
| KR102236678B1 (en) | Method and device for forecasting flood based on data analyzing | |
| CN110780663B (en) | Automatic driving state switching method, device, equipment and storage medium | |
| CN111026115A (en) | Robot obstacle avoidance control method and device based on deep learning | |
| CN118362131B (en) | Route data processing method and system based on dynamic programming verification | |
| CN114239974B (en) | Multi-agent position prediction method and device, electronic equipment and storage medium | |
| CN118131778B (en) | Intelligent emergency disposal robot and obstacle avoidance method thereof | |
| CN113507118A (en) | Wind power prediction method and system | |
| KR101632986B1 (en) | Wavelet-based Time delayed adaptive neuro fuzzy inference system for predicting nonlinear behavior of smart concrete structure equipped with MR-dampers | |
| CN117249832A (en) | Method, device and storage medium for robot indoor navigation | |
| CN112308337A (en) | Prediction method, prediction device and processor for probabilistic short-term load of power system | |
| CN117132575A (en) | Improved PointNet++ based three-dimensional detection method for defects of drainage pipeline | |
| CN116958529A (en) | Robot remote control method, system and medium | |
| CN116628836A (en) | Data-driven supercritical airfoil performance prediction method, system and medium | |
| EP4199498A1 (en) | Site model updating method and system | |
| Al-Ashmori et al. | Comparison of Optimisation Solvers for Model Predictive Control-Based Motion Cueing Algorithm | |
| CN117351449B (en) | Polar coordinate weighting-based road passable region boundary optimization method | |
| KR102698899B1 (en) | Method, system and non-transitory computer-readable recording medium for providing a reward function for reinforcement learning | |
| CN117381805B (en) | Mechanical arm operation control method and system for conflict handling | |
| CN116911560B (en) | Ship task system decision planning method based on multi-objective optimization | |
| CN113903170B (en) | Large-scale road network traffic flow prediction method based on structure self-adaptive self-evolution deep learning | |
| CN117131465B (en) | Single-pipe tower damage identification method and device, electronic equipment and readable storage medium | |
| CN117893691B (en) | Structure intelligent three-dimensional reconstruction method based on three-plane feature representation and visual angle conditional diffusion model | |
| WO2024047793A1 (en) | Video processing system, video processing device, and video processing method | |
| CN117270385A (en) | Weight self-adaptive adjustment human-robot fusion decision-making method |
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 |