CN117806334A - Underwater robot obstacle avoidance path planning method and system based on artificial intelligence - Google Patents
Underwater robot obstacle avoidance path planning method and system based on artificial intelligence Download PDFInfo
- Publication number
- CN117806334A CN117806334A CN202410229235.1A CN202410229235A CN117806334A CN 117806334 A CN117806334 A CN 117806334A CN 202410229235 A CN202410229235 A CN 202410229235A CN 117806334 A CN117806334 A CN 117806334A
- Authority
- CN
- China
- Prior art keywords
- detour
- obstacle
- underwater robot
- sub
- static
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 69
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 230000003068 static effect Effects 0.000 claims abstract description 111
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 40
- 230000004888 barrier function Effects 0.000 claims abstract description 39
- 230000008569 process Effects 0.000 claims abstract description 37
- 238000004088 simulation Methods 0.000 claims description 18
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004458 analytical method Methods 0.000 claims description 13
- 230000005484 gravity Effects 0.000 claims description 6
- 238000007664 blowing Methods 0.000 claims description 3
- 239000006185 dispersion Substances 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 6
- 230000008859 change Effects 0.000 description 4
- 230000007613 environmental effect Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 241000251468 Actinopterygii Species 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
- 239000011435 rock Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an artificial intelligence-based underwater robot obstacle avoidance path planning method and system, which relate to the technical field of robot obstacle avoidance path planning and comprise the following steps: dividing the running water area plane of the underwater robot into a plurality of subareas with equal size, detecting the underwater environment by using a sensor, and counting the number of initial static barriers and the average number of static barriers in each subarea; calculating a detour index of each sub-area according to the distribution condition of each sub-area and the initial static barrier number and the average static barrier number of each sub-area, and adjusting the expected running route of the underwater robot; in the process of executing the cruising task by the underwater robot, if an obstacle which is not detected and is judged to have the possibility of collision is encountered, judging the state of the obstacle, and taking corresponding obstacle avoidance measures. The intelligent planning of the obstacle avoidance path of the underwater robot is realized, and the cruising efficiency of the underwater robot is improved.
Description
Technical Field
The invention relates to the technical field of robot obstacle avoidance path planning, in particular to an underwater robot obstacle avoidance path planning method and system based on artificial intelligence.
Background
An underwater robot (also known as a submersible robot or unmanned submersible) is an autonomous or telerobotic system specifically designed to perform tasks in an underwater environment; with the progress of technology, the application field of the underwater robot is gradually expanded, including ocean scientific exploration, submarine resource investigation, underwater archaeology, ocean environment monitoring, underwater rescue and the like; these applications require that the underwater robot be able to navigate autonomously in complex and diverse underwater environments, effectively avoid obstacles, and accomplish specified tasks.
In recent years, the rapid development of Artificial Intelligence (AI) technology provides strong support for obstacle avoidance path planning of underwater robots; artificial intelligence techniques including machine learning, deep learning, reinforcement learning, etc., can process large amounts of complex data and make intelligent decisions; through training and optimizing algorithm, the AI technology can enable the underwater robot to have autonomous sensing and decision making capability, so that the underwater robot is better adapted to the underwater environment, and efficient obstacle avoidance and path planning are realized.
In the Chinese invention application with the application publication number of CN116659510A, a method, a device and a storage medium for positioning and obstacle avoidance of an underwater robot are disclosed, and initial pose data of the underwater robot before submergence is obtained; acquiring real-time pose data of the underwater robot according to the initial pose data in the submergence process of the underwater robot to obtain first real-time pose data, and constructing a first submarine environment map through sonar; after the underwater robot reaches a working water area, updating the first real-time pose data and the first submarine environment map based on SLAM through a multi-category sensor group to obtain second real-time pose data and a second submarine environment map; carrying out real-time positioning and obstacle avoidance path planning on the underwater robot according to the second real-time pose data and the second submarine environment map;
in the application of the invention, real-time pose data and a submarine environment map are respectively constructed when the underwater robot is submerged and arrives at a working water area, and obstacle avoidance path planning is performed based on the real-time pose data and the submarine environment map, so that the positioning and obstacle avoidance accuracy of the underwater robot is improved; however, in the process of submerging, the situation of the obstacle in the water area to be cruised cannot be comprehensively detected, so that a path for avoiding most of the obstacles cannot be planned before cruising begins, and the analysis of an avoidance strategy is required to be immediately carried out when the underwater robot encounters the obstacle in the process of cruising, so that the working efficiency of the underwater robot is reduced; furthermore, the map of the subsea environment on which the design relies is not capable of detecting in real time an abrupt occurrence of an obstacle, which may lead to a standby behavior of the underwater robot when it encounters an unrecorded obstacle during cruising.
Disclosure of Invention
(one) solving the technical problems
Aiming at the technical problems in the background technology, the invention provides an artificial intelligence-based underwater robot obstacle avoidance path planning method and system, which detect the obstacle condition in the water and carry out the first obstacle avoidance path planning before the underwater robot carries out the cruising task; the method has the advantages that the undetected obstacle possibly occurring in front is detected in real time in the process of executing the cruising task of the underwater robot, and the obstacle avoidance path with the smallest cruising influence on the underwater robot is selected by combining the water flow direction and the avoidance path analysis of the left side and the right side, so that the technical problem recorded in the background technology is solved.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
an artificial intelligence-based underwater robot obstacle avoidance path planning method comprises the following steps:
dividing the running water area plane of the underwater robot into a plurality of subareas with equal size, detecting the underwater environment by using a sensor before the underwater robot executes the cruising task, and counting the number of initial static obstacles in each subarea; periodically detecting static barriers in each subarea in the cruising process of the underwater robot and calculating the average number of the static barriers in each subarea at the end of cruising;
according to the distribution condition of each sub-area and the initial static barrier number of each sub-areaWith the average number of static obstacles per sub-zone for the first 5 cruisesCalculating detour index for each sub-regionThe method comprises the steps of carrying out a first treatment on the surface of the According to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
judging the state of an obstacle when the obstacle which is not detected and is possible to collide is encountered in the process of executing the cruising task by the underwater robot, and taking corresponding obstacle avoidance measures; for a static obstacle, simulating a detour path in the left and right directions, dividing the detour track in each direction according to the current water flow direction to obtain a plurality of line segments, analyzing the sub-areas where the line segments are positioned to obtain detour indexes of each line segment, adding the detour indexes of all the line segments in the left and right directions, and selecting the detour path according to the result.
Specifically, the running water area plane of the underwater robot is divided into a plurality of square subareas with equal size and numbered, each subarea comprises a three-dimensional space from a horizontal plane to the water bottom, the size of each subarea is preset by a manager, and the requirement is not less than 5 times of the top view area of the underwater robot;
and placing a sensor group at the intersection point position among each sub-area, detecting the underwater environment data of each sub-area before the underwater robot performs underwater cruising operation, and updating the detected obstacle into the water area map.
Further, in the cruising process of the underwater robot, the sensor group detects the static obstacle in each sub-area according to a preset interval, and the average value of the number of the detected static obstacles in each sub-area after the cruising of the underwater robot is used as the average number of the static obstacles in each sub-area during cruising;
counting the number of static barriers detected in each sub-area and marking asRepresents the firstAn initial static obstacle count for the sub-region; taking out the average number of static obstacles in each subarea during the first 5 cruises from the history cruising record，Representing the front firstCruising for the second time.
Specifically, the shortest distance between the center of gravity of each sub-area and the expected driving route is usedDescribing the distribution of each sub-area; shortest distance between center of gravity point of each sub-area and expected driving routeWith the initial number of static obstacles per sub-zoneAverage number of static obstaclesCombining to obtain detour index of each sub-regionThe expression is:
wherein,for the weight coefficient of the distance between each sub-area and the desired travel route,for the weight coefficient of the number of barriers in each sub-area, the bypass indexThe larger the bypass priority of the sub-region is, the lower; detour indexThe smaller the bypass priority of the sub-region is, the higher;and (3) withCalculated by the following formula:
wherein,and (3) withRespectively represents taking the maximum value and taking the minimum value, and。
further, traversing a preset expected driving route and combining with the distribution condition of the detected static obstacle to simulate the cruising process of the underwater robot; for static obstacle not on driving route, judging cruisingWhether the distance between the two sides of the underwater robot and the edge of the static obstacle is smaller than the preset safe distance or notIf the distance is smaller than the safety distance, the collision possibility is indicated, and the expected driving route around the static obstacle is required to be adjusted at the moment; if the distance is not smaller than the safety distance, the possibility of collision is not shown, and the expected driving route around the static obstacle does not need to be adjusted.
Further, when it is judged that collision is likely, the underwater robot is subjected to detouring simulation from the left direction and the right direction, a detouring starting point is a position which is a safe distance away from the front of the static obstacle in the direction of the expected driving route, and a detouring ending point is a position which is a safe distance away from the rear of the static obstacle in the direction of the expected driving route; the outline of the static obstacle is detected by the sensor, and the detour track of the underwater robot is simulated, so that the distance between the left side or the right side of the underwater robot and the obstacle is always kept atIs within the range of (2); after simulating left-side detour track and right-side detour track of the underwater robot, respectively obtaining a plurality of sub-areas where the two detour tracks are located and the length of the detour trackAnd (3) withThe method comprises the steps of carrying out a first treatment on the surface of the If a new obstacle appears in the process of line simulation, continuing the line simulation of the detour according to the method until reaching the detour end point and ending the line simulation at the side.
Further, the detour index of the sub-areas where the left detour track is located is calculated from the length of the detour trackCombining to obtain the static barrierLeft hand detour index of obstructionsAnd similarly obtaining the right detour index of the static obstacleThe expression is:
wherein,representing the set of sub-region numbers occupied by the left hand detour track,representing a set of sub-region numbers occupied by the right detour track; comparing left-hand detour index of the obstacleAnd right detour indexTaking the side with smaller detour index as a detour route; and when the expected driving route is traversed, obtaining an adjusted driving route.
Specifically, during the cruising task of the underwater robot, the forward is scanned in real time by the sonar of the head, and when the existence of an obstacle in the forward is detected, the underwater robot still cruises according to the set driving route and drives to the obstacle in the forwardIn the process of the position detection, the position information of the obstacle is detected in real time, and the state of the obstacle in front is judged;
if the front obstacle is detected to be a dynamic obstacle, dispersing the obstacle in a flickering, blowing or grabbing mode, and continuing cruising according to a set driving route after dispersing the obstacle;
if the front obstacle is detected to be a static obstacle, sending an avoidance signal to a control center, and after the control center receives the signal, acquiring real-time data of the current position of the underwater robot and a plurality of sensors nearby; the data of the sensors are combined to carry out detour analysis on the underwater robot from the left direction and the right direction.
Specifically, the control center draws the shape and the position of the static obstacle through the data detected by the sensor, updates the obstacle in the water area map, and simulates the detour route of the underwater robot in the left direction and the right direction respectively; for the detour route in each direction, specifically taking the current water flow direction as a standard, the offset angle of each detour direction and the current water flow direction is measuredDividing the detour route of each direction into a plurality of line segments according to different offset angles, and calculating detour subindex of each line segment according to the subarea of each line segmentAnd (3) withThe expression is:
wherein,representing the first of the left-hand detour routesThe individual line segments occupy a collection of sub-region numbers,representing the right detour routeThe individual line segments occupy a collection of sub-region numbers,and (3) withThe length of each line segment in the occupied subarea is respectively represented;
combining the detour sub-index of each line segment with the corresponding offset angle to obtain detour index of each line segment, and adding the detour indexes of all line segments in the left direction or the right direction to obtain the comprehensive detour index in the directionAnd (3) withThe expression is:
wherein,and (3) withRepresenting the total number of segments divided in the left-hand detour and right-hand detour simulation routes respectively,and (3) withRespectively representing offset angles of each line segment direction split in the left-side detour and right-side detour simulation routes and the current water flow direction; comparing left side comprehensive detour indexComprehensive detour index with right sideThe side with the smaller detour index is taken as the detour route.
An artificial intelligence based underwater robot obstacle avoidance path planning system, comprising:
the data acquisition module equally divides the running water area plane of the underwater robot into a plurality of square subregions with equal size and numbers the square subregions, sets a sensor group at the intersection point position among each subregion, and periodically detects the underwater environment data of each subregion before the underwater robot cruises and in the cruises of the underwater robot; in the process of executing the cruising task of the underwater robot, scanning the front through sonar of the head in real time to acquire the information of the obstacle in front;
the driving route adjustment module is used for adjusting the number of the initial static barriers of each sub-area according to the distribution condition of each sub-area and the number of the initial static barriers of each sub-areaWith the average number of static obstacles per sub-zone for the first 5 cruisesCalculating detour index for each sub-regionThe method comprises the steps of carrying out a first treatment on the surface of the According to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
the cruise obstacle detection module is used for judging the state of an obstacle when the obstacle which is not detected and is possibly collided is encountered in the process of executing the cruise task by the underwater robot, and taking corresponding obstacle avoidance measures, wherein the cruise obstacle detection module comprises an obstacle state detection unit, a dynamic dispersion unit and an avoidance analysis unit.
(III) beneficial effects
The invention provides an artificial intelligence-based underwater robot obstacle avoidance path planning method and system, which have the following beneficial effects:
1. the water area to be cruised is divided into a plurality of equal-sized subareas, and based on statistics and analysis of the number of static barriers in each subarea and periodic detection of each subarea, the robot can evaluate the environmental complexity and safety of different areas more accurately, so that a more reasonable path planning and barrier avoiding strategy is formulated;
2. by comprehensively considering the distribution condition of the subareas, the number of static obstacles and the safe distance between the underwater robot and the obstacles, a safe and efficient cruising route is planned for the underwater robot;
3. when encountering a static obstacle, selecting a route with smaller detour index by simulating different detour schemes, so that the underwater robot can quickly return to an expected route in the detour process, and collision with the obstacle is avoided, and the cruising efficiency is improved;
4. dynamic and static obstacles in the underwater complex environment are effectively treated through real-time sonar scanning, obstacle state judgment and an intelligent obstacle avoidance strategy, so that the cruising safety and efficiency of the underwater robot are improved; when encountering obstacles, the underwater robot can smoothly complete the cruising task by flexibly coping with different obstacle states and carrying out a dispersing or obstacle avoidance detouring strategy according to the different obstacle states, and the real-time recording of the actual cruising route is ensured, so that precious data support is provided for subsequent tasks;
5. when the front obstacle is judged to be a static obstacle, the optimal detour route is selected through intelligent analysis by combining the real-time sensor data, the water flow direction and the obstacle position, so that the underwater robot is ensured to efficiently and safely finish the avoidance action when encountering the static obstacle, and simultaneously, the robot continues to cruise along the set route, thereby improving the autonomous navigation capability and the environmental adaptability of the robot.
Drawings
FIG. 1 is a flow chart of steps of an artificial intelligence based underwater robot obstacle avoidance path planning method provided by the invention;
fig. 2 is a schematic structural diagram of an artificial intelligence-based underwater robot obstacle avoidance path planning system provided by the invention.
Detailed Description
The following description of the embodiments of the present invention 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 invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention provides an artificial intelligence-based underwater robot obstacle avoidance path planning method, which comprises the following steps:
dividing the running water area plane of the underwater robot into a plurality of subareas with equal size, detecting the underwater environment by using a sensor before the underwater robot executes a cruising task, and counting the number of initial static obstacles in each subarea; periodically detecting static barriers in each subarea in the cruising process of the underwater robot and calculating the average number of the static barriers in each subarea at the end of cruising;
the first step comprises the following steps:
step 101, equally dividing the running water area plane of the underwater robot into a plurality of square subareas with equal size and numbering, wherein each subarea comprises a three-dimensional space from a horizontal plane to the water bottom, the size of each subarea is preset by a manager, and the requirement is not less than 5 times of the top view area of the underwater robot;
102, placing a sensor group (an intersection point of four sub-areas) at the intersection point position among each sub-area, and detecting underwater environment data of each sub-area before underwater robot cruises, specifically monitoring whether static obstacles exist in each sub-area; updating the detected obstacle into the water area map;
the sensor group comprises a laser radar and a monocular camera, an optical system in the laser radar is used for receiving light signals reflected from the obstacle, and the distance, the outline and the position information of the obstacle are judged through the reflected signals; the monocular camera is used for identifying the obstacle in the water by capturing a real-time image of the underwater environment based on the result of edge detection and combining the related technology in image processing; combining detection results of the laser radar and the monocular camera to further detect obstacles in each sub-area;
in addition, in the cruising process of the underwater robot, the sensor group can detect the static obstacle in each sub-area according to a certain interval, and the average value of the number of the detected static obstacles in each sub-area after the cruising of the underwater robot is taken as the average number of the static obstacles in each sub-area during cruising; this is because the underwater environment is filled with uncertainty and static obstructions may change due to currents, tides, or other environmental factors;
step 103, counting the number of static barriers detected in each sub-area, and marking asRepresents the firstAn initial static obstacle count for the sub-region; taking out the average number of static obstacles in each subarea during the first 5 cruises from the history cruising record，Representing the front firstCruising for the second time;
in use, the contents of steps 101 to 103 are combined:
based on statistics and analysis of the number of static barriers in each sub-area and periodic detection of each sub-area, the robot can evaluate the environmental complexity and safety of different areas more accurately, so that more reasonable path planning and obstacle avoidance strategies are formulated.
Step two, according to the distribution condition of each sub-area and the initial static barrier number of each sub-areaWith the average number of static obstacles per sub-zone for the first 5 cruisesCalculating detour index for each sub-regionThe method comprises the steps of carrying out a first treatment on the surface of the According to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
the second step comprises the following steps:
step 201, presetting a desired travel route of the underwater robot by a manager, and presetting a safe distance between the underwater robot and an obstacle；
Step 202, the distribution situation of the subareas, namely the distance between each subarea and the expected driving route; using the shortest distance between the center of gravity of each sub-region and the expected travel routeDescribing the distribution of each sub-area; shortest distance between center of gravity point of each sub-area and expected driving routeWith the initial number of static obstacles per sub-zoneAverage number of static obstaclesCombining to obtain detour index of each sub-regionThe expression is:
wherein,for the weight coefficient of the distance between each sub-area and the desired travel route,for the weight coefficient of the number of obstacles in each sub-area,and (3) withCalculated by the following formula:
wherein,and (3) withRespectively represents taking the maximum value and taking the minimum value, and；
the detour priority of each sub-area can be reflected by combining the distance between each sub-area and the expected driving route, the number of the initial static barriers and the average number of the static barriers of each sub-area to obtain a detour index; because the underwater robot needs to cruise according to a specified route, if an obstacle is encountered, the path which takes the least time and winds the shortest path is required to be searched, so that the underwater robot can quickly return to the expected path after the underwater robot bypasses; when more obstacles exist in one subarea, the underwater robot can encounter more obstacles in the bypassing process, the cruise efficiency of the underwater robot can be reduced due to multiple obstacle avoidance, and the bypassing priority can be reduced at the moment; when one sub-area is far away from the expected driving route, the more time it takes for the underwater robot to bypass the sub-area, the lower the cruising efficiency of the underwater robot will be, and the bypass priority will be lowered at this time; according to the upper partThe detour indexThe calculation formula of (1) can be known as the detour indexThe larger the bypass priority of the sub-region is, the lower; detour indexThe smaller the bypass priority of the sub-region is, the higher;
step 203, traversing a preset expected driving route, combining the preset expected driving route with the distribution condition of the detected static obstacle, and simulating the cruising process of the underwater robot; for a static obstacle which is not on a driving route, whether the distance between the two sides of the underwater robot and the edge of the static obstacle is smaller than a preset safety distance in the cruising process is required to be judgedIf the distance is smaller than the safety distance, the collision possibility is indicated, and the expected driving route around the static obstacle needs to be adjusted at the moment; if the distance is not smaller than the safety distance, the possibility of collision is not shown, and the expected driving route around the static obstacle is not required to be adjusted;
when judging that collision is possible, carrying out detour simulation on the underwater robot from the left direction and the right direction, wherein a detour starting point is a position which is a safe distance away from the front of the static obstacle in the direction of the expected driving route, and a detour ending point is a position which is a safe distance away from the rear of the static obstacle in the direction of the expected driving route; the outline of the static obstacle detected by the sensor simulates the detour track of the underwater robot, so that the distance between the left side (or right side) of the underwater robot and the obstacle is always kept atIs within the range of (2); after simulating left-side detour track and right-side detour track of the underwater robot, respectively obtaining the left-side detour track and the right-side detour trackThe multiple sub-areas where the detour track is located and the length of the detour trackAnd (3) with，And (3) withThe lengths of the left-side detour track and the right-side detour track are respectively represented; if a new obstacle appears in the process of line simulation, continuing the line simulation of the detour according to the method until the detour end point is reached to finish the line simulation of the side;
the detour index of the sub-areas where the left detour track is located and the length of the detour trackCombining to obtain the left detour index of the static obstacleAnd similarly obtaining the right detour index of the static obstacleThe expression is:
wherein,representing the set of sub-region numbers occupied by the left hand detour track,representing a set of sub-region numbers occupied by the right detour track; comparing left-hand detour index of the obstacleAnd right detour indexTaking the side with smaller detour index as a detour route; when the expected driving route is traversed, obtaining an adjusted driving route;
in use, the contents of steps 201 to 203 are combined:
the expected running route of the underwater robot is adjusted by comprehensively considering the distribution condition of the subareas, the number of static barriers and the safety requirement of the robot; this adjustment ensures that the robot can safely and efficiently avoid obstacles when performing cruising tasks, and reduces unnecessary detours and delays as much as possible.
Step three, judging the state of an obstacle when the obstacle which is not detected and is possible to collide is encountered in the process of executing the cruising task of the underwater robot, and taking corresponding obstacle avoidance measures;
the third step comprises the following steps:
step 301, in the process of performing a cruising task by the underwater robot, scanning the front through sonar of the head in real time to cope with obstacles which may suddenly appear; requiring sonar to scan a distance greater than the safe distance；
Step 302, when detecting that an obstacle exists in front, the underwater robot still cruises according to the set driving route and drives to the obstacle in frontIn the process of the position detection, the position information of the obstacle is detected in real time, and if the position change of the front obstacle is detected, the front obstacle is judged to be a dynamic obstacle; if the position change of the front obstacle is not detected, judging that the front obstacle is a static obstacle;
dynamic obstacles include fish shoals, pasture or floating plastic bags or bottles, etc., which can be dispersed by taking corresponding measures; static obstacles comprise reefs or rocks and the like which change positions due to water flow, and the obstacles need to avoid obstacle detouring;
step 303, if the front obstacle is detected to be a dynamic obstacle, dispersing the obstacle in a flickering, blowing or grabbing mode, and continuing to cruise according to a set driving route after the obstacle is dispersed;
if the front obstacle is detected to be a static obstacle, sending an avoidance signal to a control center, and after the control center receives the signal, acquiring real-time data of the current position of the underwater robot and a plurality of sensors nearby; the data of the sensors are combined to carry out detour analysis on the underwater robot from the left direction and the right direction, and the detour analysis is specifically as follows:
the control center draws the shape and the position of the static obstacle through the data detected by the sensor, updates the obstacle in the water area map, and simulates the detour route of the underwater robot in the left direction and the right direction respectively; for the detour route in each direction, specifically taking the current water flow direction as a standard, the offset angle of each detour direction and the current water flow direction is measuredDividing the detour route of each direction into a plurality of line segments according to different offset angles, and calculating detour subindex of each line segment according to the subarea of each line segmentAnd (3) withThe expression is:
wherein,representing the first of the left-hand detour routesThe individual line segments occupy a collection of sub-region numbers,representing the right detour routeThe individual line segments occupy a collection of sub-region numbers,and (3) withThe length of each line segment in the occupied subarea is respectively represented;
combining the detour sub-index of each line segment with the corresponding offset angle to obtain detour index of each line segment, and adding the detour indexes of all line segments in the left direction (or right direction) to obtain the comprehensive detour index in the directionAnd (3) withThe expression is:
wherein,and (3) withRepresenting the total number of segments divided in the left-hand detour and right-hand detour simulation routes respectively,and (3) withRespectively representing offset angles of each line segment direction split in the left-side detour and right-side detour simulation routes and the current water flow direction;comparing left side comprehensive detour indexComprehensive detour index with right sideTaking the side with smaller detour index as a detour route;
step 304, in the process of cruising the underwater robot, if the situation that the obstacle exists in front is encountered again, the obstacle analysis and avoidance are continuously performed according to steps 302 to 303 until the whole cruising task is completed, and an actual cruising route is recorded.
In use, the contents of steps 301 to 304 are combined:
through real-time sonar scanning, the robot can detect obstacles which can suddenly appear in advance and take proper obstacle avoidance measures; dynamic and static obstacles can be distinguished, and different obstacle avoidance strategies are adopted for different types of obstacles, so that the adaptability and the flexibility of the robot in the face of changeable underwater environments are enhanced; by sending an avoidance signal to a control center and planning a detour route by combining sensor data, the robot can reduce detour distance and time as much as possible while ensuring safety, so that the cruising efficiency is optimized; the control center evaluates the advantages and disadvantages of different detour routes through a complex algorithm according to the shape, the position, the water flow direction and other factors of the obstacle, and selects an optimal route. The intelligent decision mechanism improves the autonomous navigation capability of the robot.
Referring to fig. 2, the invention further provides an artificial intelligence-based underwater robot obstacle avoidance path planning system, which comprises:
the data acquisition module equally divides the running water area plane of the underwater robot into a plurality of square subregions with equal size and numbers the square subregions, sets a sensor group at the intersection point position among each subregion, and periodically detects the underwater environment data of each subregion before the underwater robot cruises and in the cruises of the underwater robot; in the process of executing the cruising task of the underwater robot, scanning the front through sonar of the head in real time to acquire the information of the obstacle in front;
the driving route adjustment module is used for adjusting the number of the initial static barriers of each sub-area according to the distribution condition of each sub-area and the number of the initial static barriers of each sub-areaWith the average number of static obstacles per sub-zone for the first 5 cruisesCalculating detour index for each sub-regionThe method comprises the steps of carrying out a first treatment on the surface of the According to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
the cruise obstacle detection module is used for judging the state of an obstacle when the obstacle which is not detected and is possibly collided is encountered in the process of executing the cruise task by the underwater robot, and taking corresponding obstacle avoidance measures, wherein the cruise obstacle detection module comprises an obstacle state detection unit, a dynamic dispersion unit and an avoidance analysis unit.
In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the processes or functions described in accordance with embodiments of the present invention are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable devices. The computer instructions may be stored in or transmitted across a computer storage medium.
The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by a wired (e.g., coaxial cable, fiber optic, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). Computer storage media may be any available media that can be accessed by a computer or data storage devices, such as servers, data centers, etc. that contain an integration of one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a Solid State Disk (SSD)), or the like.
The foregoing is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think about changes or substitutions within the technical scope of the present disclosure, and all changes and substitutions are intended to be covered by the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. An artificial intelligence-based underwater robot obstacle avoidance path planning method is characterized in that: comprising the following steps:
dividing the running water area plane of the underwater robot into a plurality of subareas with equal size, detecting the underwater environment by using a sensor before the underwater robot executes the cruising task, and counting the number of initial static obstacles in each subarea; periodically detecting static barriers in each subarea in the cruising process of the underwater robot and calculating the average number of the static barriers in each subarea at the end of cruising;
calculating a detour index of each sub-area according to the distribution condition of each sub-area, the initial static obstacle number of each sub-area and the average static obstacle number of each sub-area during the previous 5 cruising; according to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
judging the state of an obstacle when the obstacle which is not detected and is possible to collide is encountered in the process of executing the cruising task by the underwater robot, and taking corresponding obstacle avoidance measures; for a static obstacle, simulating a detour path in the left and right directions, dividing the detour track in each direction according to the current water flow direction to obtain a plurality of line segments, analyzing the sub-areas where the line segments are positioned to obtain detour indexes of each line segment, adding the detour indexes of all the line segments in the left and right directions, and selecting the detour path according to the result.
2. The artificial intelligence-based underwater robot obstacle avoidance path planning method as set forth in claim 1, wherein: dividing the running water area plane of the underwater robot into a plurality of square subareas with equal size, numbering the square subareas, wherein each subarea comprises a three-dimensional space from a horizontal plane to the water bottom, and the subareas are not smaller than 5 times of the top view area of the underwater robot;
and placing a sensor group at the intersection point position among each sub-area, detecting the underwater environment data of each sub-area before the underwater robot performs underwater cruising operation, and updating the detected obstacle into the water area map.
3. The artificial intelligence-based underwater robot obstacle avoidance path planning method as set forth in claim 2, wherein: in the cruising process of the underwater robot, the sensor group detects static barriers in each sub-area according to preset intervals, and the average value of the number of the detected static barriers in each sub-area after the cruising of the underwater robot is taken as the average number of the static barriers in each sub-area during cruising;
counting the number of static barriers detected in each sub-area and marking asRepresents->An initial static obstacle count for the sub-region; taking out the average number of static obstacles in each sub-zone at the first 5 cruises from the history of cruising>，/>Indicate the%>Cruising for the second time.
4. The underwater robot obstacle avoidance path planning method based on artificial intelligence as set forth in claim 3, wherein: using the shortest distance between the center of gravity of each sub-region and the expected travel routeDescribing the distribution of each sub-area; shortest distance of the center of gravity of each sub-region to the desired travel route +.>Number of initial static barriers to each sub-region +.>Average number of static barriers->Combining to obtain detour index of each sub-region>The expression is:
；
wherein,weight coefficient for the distance between each sub-area and the desired driving route, +.>For the weight coefficient of the number of barriers in each sub-area, detour index +.>The larger the bypass priority of the sub-region is, the lower; detour index->The smaller the bypass priority of the sub-region is, the higher; />And->Calculated by the following formula:
；
wherein,and->Respectively represent maximum and minimum, and +.>。
5. The artificial intelligence based underwater robot obstacle avoidance path planning method as set forth in claim 4, wherein: traversing a preset expected driving route and simulating the cruising process of the underwater robot by combining the preset expected driving route with the detected distribution condition of the static obstacle; for a static obstacle which is not on a driving route, judging whether the distance between the two sides of the underwater robot and the edge of the static obstacle is smaller than a preset safety distance in the cruising processIf the distance is smaller than the safety distance, the collision possibility is indicated, and the expected driving route around the static obstacle is required to be adjusted at the moment; if the distance is not smaller than the safety distance, the expected driving route around the static obstacle is not adjusted.
6. The artificial intelligence based underwater robot obstacle avoidance path planning method as set forth in claim 5, wherein: when judging that collision is possible, carrying out detour simulation on the underwater robot from the left direction and the right direction, wherein a detour starting point is a position which is a safe distance away from the front of the static obstacle in the direction of the expected driving route, and a detour ending point is a position which is a safe distance away from the rear of the static obstacle in the direction of the expected driving route;
the outline of the static obstacle is detected by the sensor, and the detour track of the underwater robot is simulated, so that the distance between the left side or the right side of the underwater robot and the obstacle is always kept atIs within the range of (2); after simulating left-side detour track and right-side detour track of the underwater robot, respectively obtaining a plurality of sub-areas where the two detour tracks are located and the length of the detour track +.>And->The method comprises the steps of carrying out a first treatment on the surface of the If a new obstacle appears in the process of line simulation, continuing the line simulation of the detour according to the method until reaching the detour end point and ending the line simulation at the side.
7. The artificial intelligence based underwater robot obstacle avoidance path planning method as set forth in claim 6, wherein: the detour index and detour track of the sub-areas where the left detour track is locatedLength of trackIn combination, the left detour index of the static obstacle is obtained>The right detour index of a static obstacle is obtained in the same way>The expression is:
；
wherein,representing the set of sub-area numbers occupied by the left detour track,/->Representing a set of sub-region numbers occupied by the right detour track; comparing left detour index of said obstacle>And right detour index->Taking the side with smaller detour index as a detour route; and when the expected driving route is traversed, obtaining an adjusted driving route.
8. The artificial intelligence based underwater robot obstacle avoidance path planning method of claim 7, wherein: in the process of the underwater robot executing the cruising task, the front is scanned in real time through the sonar of the head, and when the front obstacle is detected, the underwater robot still cruises according to the set driving route and drives to the obstacle in frontIn the process of the position detection, the position information of the obstacle is detected in real time, and the state of the obstacle in front is judged;
if the front obstacle is detected to be a dynamic obstacle, dispersing the obstacle in a flickering, blowing or grabbing mode, and continuing cruising according to a set driving route after dispersing the obstacle;
if the front obstacle is detected to be a static obstacle, sending an avoidance signal to a control center, and after the control center receives the signal, acquiring real-time data of the current position of the underwater robot and a plurality of sensors nearby; the data of the sensors are combined to carry out detour analysis on the underwater robot from the left direction and the right direction.
9. The artificial intelligence-based underwater robot obstacle avoidance path planning method as set forth in claim 8, wherein: the control center draws the shape and the position of the static obstacle through the data detected by the sensor, updates the obstacle in the water area map, and simulates the detour route of the underwater robot in the left direction and the right direction respectively; for the detour route in each direction, specifically taking the current water flow direction as a standard, the offset angle of each detour direction and the current water flow direction is measuredDividing the detour route of each direction into a plurality of line segments according to different offset angles, and calculating detour subindex ++of each line segment according to the subregion where each line segment is located>And->The expression is:
；
wherein,indicating the +.>A set of sub-region numbers occupied by the line segments, +.>Indicating the +.>A set of sub-region numbers occupied by the line segments, +.>And->The length of each line segment in the occupied subarea is respectively represented;
combining the detour sub-index of each line segment with the corresponding offset angle to obtain detour index of each line segment, and adding the detour indexes of all line segments in the left direction or the right direction to obtain the comprehensive detour index in the directionAnd->The expression is:
；
wherein,and->Respectively representing the total number of segments divided in the left-hand detour and right-hand detour simulation routes,/>And->Respectively representing offset angles of each line segment direction split in the left-side detour and right-side detour simulation routes and the current water flow direction; comparison of left comprehensive detour index +.>And right comprehensive detour index->The side with the smaller detour index is taken as the detour route.
10. An artificial intelligence-based underwater robot obstacle avoidance path planning system, which is characterized by comprising:
the data acquisition module equally divides the running water area plane of the underwater robot into a plurality of square subregions with equal size and numbers the square subregions, sets a sensor group at the intersection point position among each subregion, and periodically detects the underwater environment data of each subregion before the underwater robot cruises and in the cruises of the underwater robot; in the process of executing the cruising task of the underwater robot, scanning the front through sonar of the head in real time to acquire the information of the obstacle in front;
the driving route adjustment module is used for adjusting the number of the initial static barriers of each sub-area according to the distribution condition of each sub-area and the number of the initial static barriers of each sub-areaAverage number of static obstacles per sub-zone with the first 5 cruises +.>Calculating detour index of each sub-region +.>The method comprises the steps of carrying out a first treatment on the surface of the According to the distribution condition of static barriers before the underwater robot cruises and the detour index of the adjacent subareas, the expected running route of the underwater robot is adjusted;
the cruise obstacle detection module is used for judging the state of an obstacle when the obstacle which is not detected and is possibly collided is encountered in the process of executing the cruise task by the underwater robot, and taking corresponding obstacle avoidance measures, wherein the cruise obstacle detection module comprises an obstacle state detection unit, a dynamic dispersion unit and an avoidance analysis unit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410229235.1A CN117806334B (en) | 2024-02-29 | 2024-02-29 | Underwater robot obstacle avoidance path planning method and system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410229235.1A CN117806334B (en) | 2024-02-29 | 2024-02-29 | Underwater robot obstacle avoidance path planning method and system based on artificial intelligence |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117806334A true CN117806334A (en) | 2024-04-02 |
| CN117806334B CN117806334B (en) | 2024-05-14 |
Family
ID=90428233
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410229235.1A Active CN117806334B (en) | 2024-02-29 | 2024-02-29 | Underwater robot obstacle avoidance path planning method and system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117806334B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317302A (en) * | 2014-09-28 | 2015-01-28 | 江苏华宏实业集团有限公司 | Intellectualized underwater robot system |
| CN108594847A (en) * | 2018-03-27 | 2018-09-28 | 广东电网有限责任公司 | A kind of autocontrol method of power transmission line unmanned machine laser radar modeling |
| CA3067576A1 (en) * | 2019-01-14 | 2020-07-14 | Harbin Engineering University | Cooperative autonomous navigation systems and methods for multiple unmanned surface vehicles considering communication |
| CN112085376A (en) * | 2020-09-04 | 2020-12-15 | 东南大学 | Traffic demand analysis method based on longitude and latitude coordinates and k-means clustering algorithm |
| CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
| CN115220444A (en) * | 2022-06-28 | 2022-10-21 | 中国科学院自动化研究所 | Underwater robot obstacle avoidance control method based on fuzzy artificial potential field technology |
| CN115924035A (en) * | 2022-11-29 | 2023-04-07 | 盛东如东海上风力发电有限责任公司 | Intelligent underwater robot and motion control method thereof |
| CN115953414A (en) * | 2022-11-30 | 2023-04-11 | 北京百度网讯科技有限公司 | Semantic segmentation-based short obstacle detection method and automatic driving vehicle |
-
2024
- 2024-02-29 CN CN202410229235.1A patent/CN117806334B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104317302A (en) * | 2014-09-28 | 2015-01-28 | 江苏华宏实业集团有限公司 | Intellectualized underwater robot system |
| CN108594847A (en) * | 2018-03-27 | 2018-09-28 | 广东电网有限责任公司 | A kind of autocontrol method of power transmission line unmanned machine laser radar modeling |
| CA3067576A1 (en) * | 2019-01-14 | 2020-07-14 | Harbin Engineering University | Cooperative autonomous navigation systems and methods for multiple unmanned surface vehicles considering communication |
| CN112085376A (en) * | 2020-09-04 | 2020-12-15 | 东南大学 | Traffic demand analysis method based on longitude and latitude coordinates and k-means clustering algorithm |
| CN114111825A (en) * | 2021-11-19 | 2022-03-01 | 广西柳工机械股份有限公司 | Path planning method and device, electronic equipment, engineering machinery and storage medium |
| CN115220444A (en) * | 2022-06-28 | 2022-10-21 | 中国科学院自动化研究所 | Underwater robot obstacle avoidance control method based on fuzzy artificial potential field technology |
| CN115924035A (en) * | 2022-11-29 | 2023-04-07 | 盛东如东海上风力发电有限责任公司 | Intelligent underwater robot and motion control method thereof |
| CN115953414A (en) * | 2022-11-30 | 2023-04-11 | 北京百度网讯科技有限公司 | Semantic segmentation-based short obstacle detection method and automatic driving vehicle |
Non-Patent Citations (1)
| Title |
|---|
| XIE XIAOLI;YANG TIANTIAN;LIU ZHIYUAN: "Feedback Stabilization of Nonholonomic Mobile Robots with Obstacle Avoidance", 2006 CHINESE CONTROL CONFERENCE, 31 December 2006 (2006-12-31), pages 1615 - 1620 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117806334B (en) | 2024-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11567502B2 (en) | Autonomous exploration framework for indoor mobile robotics using reduced approximated generalized Voronoi graph | |
| CN110262518B (en) | Vehicle navigation method, system and medium based on track topological map and obstacle avoidance | |
| KR102296507B1 (en) | Method for tracking object by using convolutional neural network including tracking network and computing device using the same | |
| US9836653B2 (en) | Systems and methods for capturing images and annotating the captured images with information | |
| CN104536445B (en) | Mobile navigation method and system | |
| Kim et al. | Traversability classification using unsupervised on-line visual learning for outdoor robot navigation | |
| CN113485375B (en) | Indoor environment robot exploration method based on heuristic bias sampling | |
| KR102279376B1 (en) | Learning method, learning device for detecting lane using cnn and test method, test device using the same | |
| CN109163722B (en) | Humanoid robot path planning method and device | |
| JP6980289B2 (en) | Learning method and learning device that can detect lanes using a lane model, and test method and test device using this {LEARNING METHOD, LEARNING DEVICE FOR DETECTING LANE USING LANE MODEL AND TEST METHOD, TEST DEVICE | |
| CN111604898B (en) | Livestock retrieval method, robot, terminal equipment and storage medium | |
| CN114034299B (en) | Navigation system based on active laser SLAM | |
| CN110610130A (en) | Multi-sensor information fusion power transmission line robot navigation method and system | |
| CN114879660B (en) | Robot environment sensing method based on target drive | |
| CN115147790A (en) | Vehicle future trajectory prediction method based on graph neural network | |
| JP6865342B2 (en) | Learning method and learning device for CNN base lane detection, and test method and test device using this | |
| CN115933715A (en) | Marine garbage cleaning robot and path planning method, device and medium thereof | |
| CN113867336B (en) | Mobile robot path navigation and planning method suitable for complex scene | |
| CN117806334B (en) | Underwater robot obstacle avoidance path planning method and system based on artificial intelligence | |
| CN111652118B (en) | Marine product autonomous grabbing and guiding method based on underwater target neighbor distribution | |
| CN117055557A (en) | Robot avoiding method and device and electronic equipment | |
| CN115469662B (en) | Environment exploration method, device and application | |
| Jiang et al. | Underwater loop-closure detection for mechanical scanning imaging sonar by filtering the similarity matrix with probability hypothesis density filter | |
| CN113252861B (en) | Water quality detection method and device, electronic equipment and storage medium | |
| CN113721615B (en) | Navigation path planning method and system based on machine vision |
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 |