WO2021082709A1 - 水下清淤机器人路径规划方法、装置、机器人和存储介质 - Google Patents
水下清淤机器人路径规划方法、装置、机器人和存储介质 Download PDFInfo
- Publication number
- WO2021082709A1 WO2021082709A1 PCT/CN2020/112533 CN2020112533W WO2021082709A1 WO 2021082709 A1 WO2021082709 A1 WO 2021082709A1 CN 2020112533 W CN2020112533 W CN 2020112533W WO 2021082709 A1 WO2021082709 A1 WO 2021082709A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- dredging
- bat
- robot
- path
- underwater
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 68
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 47
- 241000544061 Cuculus canorus Species 0.000 claims abstract description 24
- 239000013598 vector Substances 0.000 claims description 22
- 238000009412 basement excavation Methods 0.000 claims description 20
- 230000003068 static effect Effects 0.000 claims description 11
- 241000288673 Chiroptera Species 0.000 claims description 8
- 229920000535 Tan II Polymers 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims 1
- 238000004140 cleaning Methods 0.000 abstract description 5
- 230000007613 environmental effect Effects 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 description 5
- 235000013601 eggs Nutrition 0.000 description 5
- 238000012360 testing method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/04—Control of altitude or depth
- G05D1/06—Rate of change of altitude or depth
- G05D1/0692—Rate of change of altitude or depth specially adapted for under-water vehicles
Definitions
- the invention relates to the technical field of path planning, in particular to a path planning method, device, robot and storage medium of an underwater dredging robot.
- intelligent mobile robots have been widely used in more and more fields, such as cargo handling, intelligent production, intelligent life, abnormal environment detection, underwater Homework and so on.
- Underwater path planning methods include artificial potential field method, A* search algorithm, visual method and so on. Although they have achieved good results in underwater path planning, most of them are used in the environment of barrier-free or static obstacles. They cannot effectively solve the dynamic obstacles existing under water, and use one type alone. The algorithm will not avoid certain defects in the algorithm, and the path found may not be the global optimum.
- the purpose of the present invention is to provide a path planning method, device, robot and storage medium for an underwater dredging robot, which adopts a method of hybrid cuckoo search and bat algorithm, so that the dredging robot can avoid obstacles while avoiding obstacles. Take the shortest path to reach the target point of dredging. After the dredging robot reaches the target point, it uses an S-shape to clean the dredging area comprehensively, and uses geometric algorithms to complete obstacle avoidance.
- the path planning method of the underwater dredging robot the underwater dredging work with high degree of automation, low labor cost, environmental protection and high efficiency can be completed.
- an embodiment of the present invention proposes a path planning method for an underwater dredging robot, including:
- the dredging robot moves along the global optimal path to the dredging target point, and judges whether there are dynamic obstacles in the process of moving to realize obstacle avoidance;
- the dredging robot After the dredging robot reaches the dredging target point, it determines its own coordinates and the coordinates of the dredging excavation point, and calculates the silt excavation area closest to itself according to the European formula. The remaining silt excavation area completes the dredging according to the S-shaped course. , And use geometric algorithms to avoid obstacles in the dredging process.
- the parameters include the size of the bat population bat population, the frequency f i, r i pulse emission rate, loudness A i, where the frequency f i, r pulse emission of formula i and A i is the loudness of:
- f min and f max are the minimum and maximum frequencies emitted by the bat, and the value range is [0,1]; ⁇ and ⁇ are constants, and the value ranges of ⁇ and ⁇ are [0,1], [0 ,+ ⁇ ], usually 0.9 each.
- the method of using a mixed cuckoo search and bat algorithm to obtain the global optimal path includes:
- the cuckoo search is used to obtain and retain the local path optimal solution of the current random bat nest position, and the local path optimal solution is used as the input of the bat algorithm to update and optimize the bat position. Output the global optimal path.
- cuckoo search to obtain and retain the current local path optimal solution of the current random bat nest position includes:
- ⁇ >0 is the step size scaling factor, Is the original location of the bat nest,
- L(s, ⁇ ) is the Levi random path
- s is the step size
- s 0 is the minimum step size
- ⁇ >0 is the Levi index
- ⁇ is the standard Gamma function, which is The fixed ⁇ is a constant.
- the optimal solution of the local path is used as the input of the bat algorithm, and the bat position is updated and optimized, wherein the following formula is used to update the bat position:
- Is the current position of the bat Is the current position of the bat
- c * is the current best position generated by the Gucuniao search
- Is the current speed of the bat Is the updated bat speed, The best position for the updated bat.
- the optimal solution of the local path is used as the input of the bat algorithm, and the position of the bat is updated and optimized, wherein the following formula is used to optimize the position of the bat:
- ⁇ is between [-1, 1] of a new individual uniformly distributed random number
- a t is the average of all generation t bat loudness
- x old current best individual is generated.
- the dredging robot moves to the dredging target point along the global optimal path, and determines whether there is a dynamic obstacle during its movement to achieve obstacle avoidance, including:
- angle direction a tan 2((Y obs -Y robot ),(X obs -X robot ))
- angle direction is the direction vector of the moving obstacle
- (X obs , Y obs ) is the coordinates of the current obstacle
- (X robot , Y robot ) is the coordinates of the dredging robot
- angle vrobot is the speed vector of the dredging robot
- V j and V i are the speed vectors of the Y-axis and X-axis of the dredging robot respectively
- angle thresh is a judgment threshold, which is used to judge whether a dynamic obstacle is blocking the path of the dredging robot.
- angle Vdiff is the difference between the speed vector of the dredging robot and the speed vector of the moving obstacle.
- an embodiment of the present invention also provides a path planning device for an underwater dredging robot, including:
- the initialization module is used to initialize the parameters of the bat population according to the underwater environment, and initialize the position of the starting point of the dredging robot and the target point of dredging;
- the static obstacle avoidance module is used to judge whether there are static obstacles in the shortest line between the starting point and the dredging target point, and obtain the global optimal path by using the mixed cuckoo search and bat algorithm;
- the dynamic obstacle avoidance module is used for the dredging robot to move to the dredging target point along the global optimal path, and to judge whether there are dynamic obstacles during its movement to realize the obstacle avoidance;
- the dredging route module is used to determine the coordinates of the dredging robot and the coordinates of the dredging excavation point after the dredging robot reaches the dredging target point, and calculate the silt excavation area closest to itself according to the European formula, and the remaining silt excavation The area is dredged according to the S-shaped route, and the geometric algorithm is used to avoid obstacles in the dredging process.
- an embodiment of the present invention also proposes a robot, including:
- At least one processor and,
- a memory communicatively connected with the at least one processor; wherein,
- the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute the method according to the first aspect of the present invention.
- the embodiment of the present invention also provides a computer-readable storage medium, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to make a computer execute the method described in the first aspect of the present invention. The method described.
- the path planning method, device, robot, and storage medium of an underwater dredging robot provided by the present invention are aimed at planning the underwater dredging path, Use the cuckoo search to quickly obtain the local optimal path, and use the local optimal path as the guide to make the bats search purposefully, obtain the global optimal path, realize the shortest path and perform dynamic obstacle avoidance.
- the dredging route is planned.
- the S-shaped dredging route is used in the dredging process and the geometric algorithm is used to avoid obstacles.
- the S-shaped dredging route can make the silt cleaning more comprehensive, and the use of geometric algorithms to avoid obstacles makes the dredging process safer.
- Figure 1 is a schematic flow chart of a path planning method for an underwater dredging robot in a first embodiment of the present invention
- FIG. 2 is a specific flow chart of the path planning method of the underwater dredging robot in the first embodiment of the present invention
- Fig. 3 is a schematic diagram of a geometric algorithm in a path planning method of an underwater dredging robot in the first embodiment of the present invention
- FIG. 4 is a flow chart of path planning based on geometric algorithms in the path planning method of an underwater dredging robot in the first embodiment of the present invention
- Fig. 5 is a schematic structural diagram of a path planning device for an underwater dredging robot in a second embodiment of the present invention.
- the first embodiment of the present invention provides a path planning method for an underwater dredging robot, including but not limited to the following steps:
- S200 Determine whether the shortest line between the starting point and the dredging target point has static obstacles, and obtain the global optimal path by using the mixed cuckoo search and bat algorithm;
- the dredging robot After the dredging robot reaches the dredging target point, it determines its own coordinates and the coordinates of the dredging excavation point, and calculates the silt excavation area closest to itself according to the European formula, and the remaining silt excavation area is completed according to the S-shaped route Dredging, and use geometric algorithms to avoid obstacles in the dredging process.
- Step 1 Use a sonar device to obtain underwater environment information.
- Step 2 Initialize the size of the random population (the number of bats/nests), the frequency f i , the pulse emission rate r i , and the loudness A i .
- the number of bats/nests is determined according to the actual underwater situation. The required number is different for different underwater environment sizes.
- Frequency f i, r pulse emission of formula i, A i is the loudness:
- f min and f max are the minimum and maximum frequencies emitted by the bat, and the value range is [0,1], which is a random vector subject to uniform distribution; where ⁇ and ⁇ are constants, and the range of values for ⁇ and ⁇ They are [0,1] and [0,+ ⁇ ], and usually take 0.9 for each.
- Step 3 Initialize the position of the starting point and target point of the dredging robot.
- Step 4 The dredging robot judges whether there is a static obstacle in the shortest line between the starting point and the dredging target point.
- the dredging robot will move according to the shortest line between the starting point and the dredging target point. Whether a dynamic obstacle is detected during the movement, if it exists, skip to step 13; if not, move toward the dredging target point.
- the dredging robot completes its movement, it is judged whether it has reached the target point. If it has reached the target point, it will start dredging; if not, it will return to step 3.
- Step 5 The dredging robot generates the number of bats and bat nests according to the actual underwater situation.
- Step 6 Use the cuckoo search to find the optimal solution for the current random bat nest position, and keep the current optimal solution.
- Step 7 Use Levi's flight to update the bat nest position to obtain a new set of bat nest positions, compare this set of bat nest positions with the previous generation bat nest positions, and replace bad bat nest positions with good bat nest positions , Get a better bat nest location.
- the formula for updating the location of the bat's nest is:
- ⁇ >0 is the step size scaling factor, Is the original location of the nest,
- L(s, ⁇ ) is the Levi random path
- s is the step size
- s 0 is the minimum step size
- ⁇ >0 is the Levi index
- ⁇ is the standard Gamma function, which is for a given
- the ⁇ is a constant.
- Step 8 Use the algorithm to simulate that the foreign bird eggs in the nest are found by the owner of the nest, and the nests where the foreign bird eggs are found are updated randomly, and the nest positions of the undiscovered foreign bird eggs are kept, and a set of new nest positions are obtained. Then test the position of this group of nests and compare them with the test values of the previous nest positions, and replace the positions of the nests with poor test values with the positions of the nests with better test values.
- ⁇ >0 is the step size scaling factor
- s>0 is the step size
- H function is a unit step function
- Step 9 Find out the position of the best nest finally obtained in step 8 above. If the iterative stop condition is reached, the local path optimal solution is input into the bat algorithm. If it is not reached, go back to step 7.
- Step 10 The bat algorithm uses the local path optimal solution given by the cuckoo search as input to update its position.
- Is the current position of the bat Is the current position of the bat
- c * is the current best position generated by the Gucuniao search
- Is the current speed of the bat Is the updated bat speed, The best position for the updated bat.
- Step 11 Compare the generated uniformly distributed random number P with the pulse emission rate r i . If the generated random number is greater than the pulse emission rate r i , optimize the position of the best solution. Otherwise, go to the next step.
- ⁇ is a uniformly distributed random number [-1, 1] on
- a t is the average of all generation t bat loudness
- x old to the new current best individual subject x new optimized is generated.
- P is a uniformly distributed random number on [0,1].
- the pulse emission rate r i ⁇ (0,1].
- Step 12 Compare the old and new positions of the bats after flying, and replace the worse values with better values. Then find the optimal solution, and judge whether the maximum number of iterations is reached, if not, then return to step 10, if reached, output the global optimal path.
- Step 13 The dredging robot moves toward the dredging target point according to the planned path. During the walking process of the dredging robot, a detector detects whether there are dynamic obstacles around it within a certain range.
- Case 1 The dredging robot is roughly in the same direction as the dynamic obstacle Movement; Case 2.
- the dredging robot and the dynamic obstacle move roughly face to face; Case 3.
- the dredging robot and the dynamic obstacle move in different directions.
- the dredging robot only needs to follow the obstacle until the obstacle changes direction, or the planned path keeps the robot away from the obstacle.
- the path needs to be re-planned to make the dredging robot bypass the moving obstacles and return to the original path.
- case 3 the dredging robot only needs to move according to the original planned path. If there is no blockage, the dredging robot moves according to the original planned path.
- the dredging robot moves according to the original planned path.
- angle direction a tan 2((Y obs -Y robot ),(X obs -X robot )) 1-10
- angle direction is the direction vector of the moving obstacle
- (X obs , Y obs ) is the coordinates of the current obstacle
- (X robot , Y robot ) is the coordinates of the dredging robot.
- V j, V i are the dredging Y-axis robots, the X-axis velocity vector.
- the angle thresh is a judgment threshold, which is used to judge whether a dynamic obstacle blocks the path of the dredging robot. If the absolute value of the difference between the direction vector of the moving obstacle and the speed vector of the dredging robot is less than the threshold, the dynamic obstacle blocks the forward path of the dredging robot, otherwise no obstruction is caused.
- angle vrobot and angle direction should be processed to make them within the range of (- ⁇ , ⁇ ).
- angle Vdiff is the difference between the speed vector of the dredging robot and the speed vector of the moving obstacle.
- Angle Vobs can be calculated using formula 1-11.
- the angle Vdiff obtained from the calculation formula 1-13 is used to determine the above three situations: if angle Vdiff ⁇ angle thresh, it corresponds to The above case 1; if angle Vdiff ⁇ -angle thresh, it corresponds to the above case 2; if the angle Vdiff is not within the above range, it corresponds to the above case 3.
- the dredging robot predicts the movement of the moving obstacle through the direction vector and the speed vector of the moving obstacle. Invalidate the position coordinates of the moving obstacle. Then take the current position of the dredging robot as the starting position, and take the coordinates on the original path that is closest to the moving obstacle and the dredging robot does not collide with the moving obstacle as the target position, and use the hybrid cuckoo search and bat algorithm for path planning , So that the dredging robot bypasses the moving obstacles, returns to the original path plan, and continues to the dredging target point according to the original path plan.
- Step 14 The dredging robot judges whether it has reached the target point after following the original planned path. If not, it returns to step 3. If it reaches the target point, it starts dredging.
- the dredging robot adopts an S-shaped dredging route when walking in the dredging area. If obstacles are encountered, they will be avoided according to geometric algorithms.
- the specific principles are as follows:
- P i 3 is now points, S is a mining target silt point connection P i S. If there is no obstacle, the aircraft reaches the target point along P i S. Since the route enters the range of the circular obstacle area O j , it must bypass the obstacle area. 3, a circle O j is P i S intersects the line segment from the shortest center circle.
- Step 15 After the dredging robot reaches the dredging area, it determines its own coordinates and the coordinates of the dredging excavation point.
- Step 16 The dredging robot calculates the nearest first silt excavation area according to the European formula.
- Step 17 The remaining area completes the dredging task in this area according to the S-shaped route. Obstacles encountered during the dredging process will be avoided by the robot according to the geometric algorithm.
- Step 18 After the dredging robot completes the task in the first area, it returns to step 3 to step 17 to complete the cleaning of the second area, and so on.
- the path planning first uses the method of hybrid cuckoo search and bat algorithm to reach the dredging target point.
- Cuckoo search can quickly find the path to the target point, but the path found may only be the local optimal path.
- Bat algorithm can find the global best path, but because it is a random iterative method, it may be difficult for the algorithm to converge and the search time is long.
- the hybrid cuckoo search and bat algorithm can make up for the shortcomings and give play to the advantages of the respective algorithms. Use the cuckoo search to quickly get the local optimal path, and use the local optimal path as the guide to make the bat search purposefully and get the global The best path, the shortest path and dynamic obstacle avoidance.
- the dredging route is planned.
- the S-shaped dredging route is used in the dredging process and the geometric algorithm is used to avoid obstacles.
- the S-shaped dredging route can make the silt cleaning more comprehensive, and the use of geometric algorithms to avoid obstacles makes the dredging process safer.
- a second embodiment of the present invention provides a path planning device for an underwater dredging robot, including:
- the initialization module 110 is used to initialize the parameters of the bat population according to the underwater environment, and initialize the positions of the starting point of the dredging robot and the target point of dredging;
- the static obstacle avoidance module 120 is used to determine whether there is a static obstacle in the shortest line between the starting point and the dredging target point, and to obtain the global optimal path by using a mixed cuckoo search and bat algorithm;
- the dynamic obstacle avoidance module 130 is used for the dredging robot to move to the dredging target point along the global optimal path, and determine whether there is a dynamic obstacle during its movement to realize the obstacle avoidance;
- the dredging route module 140 is used to determine the coordinates of the dredging robot and the coordinates of the dredging excavation point after the dredging robot reaches the dredging target point, and calculate the silt excavation area closest to itself according to the European formula, and the remaining silt The excavation area is dredged according to the S-shaped route, and the geometric algorithm is used to avoid obstacles in the dredging process.
- the path planning device of the underwater dredging robot in this embodiment is based on the same inventive concept as the path planning method of the underwater dredging robot in the first embodiment. Therefore, the path planning system of the underwater dredging robot in this embodiment has The same beneficial effect: using the cuckoo search to quickly obtain the local optimal path, and use the local optimal path as a guide to make the bats purposefully search, obtain the global optimal path, realize the shortest path and perform dynamic obstacle avoidance.
- the dredging route is planned.
- the S-shaped dredging route is used in the dredging process and the geometric algorithm is used to avoid obstacles.
- the S-shaped dredging route can make the silt cleaning more comprehensive, and the use of geometric algorithms to avoid obstacles makes the dredging process safer.
- the third embodiment of the present invention also provides a robot, including:
- At least one processor At least one processor
- the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the at least one processor can execute any one of the instructions in the first embodiment.
- the memory can be used to store non-transitory software programs, non-transitory computer-executable programs and modules, such as program instructions/modules corresponding to the virtual image control method in the embodiment of the present invention .
- the processor executes various functional applications and data processing of the three-dimensional imaging processing device by running non-transient software programs, instructions and modules stored in the memory, that is, to realize the path planning of the underwater dredging robot in any of the above-mentioned method embodiments method.
- the memory may include a storage program area and a storage data area, where the storage program area can store an operating system and an application program required by at least one function; the storage data area can store data created according to the use of the stereo imaging processing device, and the like.
- the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices.
- the storage may optionally include storage remotely arranged with respect to the processor, and these remote storages may be connected to the stereoscopic projection device via a network. Examples of the aforementioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.
- the one or more modules are stored in the memory, and when executed by the one or more processors, the path planning method for an underwater dredging robot in any of the foregoing method embodiments is executed, for example, in the first embodiment The method steps S100 to S400.
- the fourth embodiment of the present invention also provides a computer-readable storage medium that stores computer-executable instructions that are executed by one or more control processors to enable the foregoing One or more processors execute a path planning method of an underwater dredging robot in the foregoing method embodiments, for example, the method steps S100 to S400 in the first embodiment.
- the device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the objectives of the solutions of the embodiments.
- each implementation manner can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware.
- a person of ordinary skill in the art can understand that all or part of the processes in the methods of the foregoing embodiments can be implemented by instructing relevant hardware through a computer program.
- the program can be stored in a computer readable storage medium, and the program can be stored in a computer readable storage medium. When executed, it may include the procedures of the above-mentioned method embodiments.
- the storage medium may be a magnetic disk, an optical disc, a read-only memory (Read-Only Memory, ROM), or a random access memory (Random Access Memory, RAM), etc.
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
一种水下清淤机器人路径规划方法、装置、机器人和存储介质，采用混合布谷鸟搜索和蝙蝠算法的方法，使清淤机器人在避障的同时能够以最短路径到达清淤目标点（S）。清淤机器人到达目标点（S）后，采用"S"字型对清淤区域进行全面清扫，并且利用几何算法完成避障。通过水下清淤机器人的路径规划方法，完成自动化程度高，人力成本低，环保高效的水下清淤工作。
Description
本发明涉及路径规划技术领域，尤其是一种水下清淤机器人路径规划方法、装置、机器人和存储介质。
近年来随着智能化技术的迅速发展和产业智慧级的不断推进,智能移动机器人在越来越多的领域里得到了广泛应用,如货物搬运、智慧生产、智能生活、异常环境探测、水下作业等等。
目前，在海洋或河道活动中，由于人自身的局限性，利用自主移动机器人来完成水下作业已经成为必然的趋势了，由于水下清淤机器人携带资源有限，且水下的工作环境复杂，不可预测。为使得水下清淤机器人能够有效的避开障碍物并且高效的完成清淤任务，其水下路径规划技术研究显得十分关键了。
水下路径规划方法有人工势场法、A*搜寻算法、可视图法等。虽然它们在水下路径规划中都取得了不错的成效，但大多数都是应用在无障碍或者静态障碍物的环境下，对于水下存在的动态障碍物未能有效解决，并且单独使用一种算法会避免不了该算法中存在的某种缺陷，寻找到的路径可能不是全局最优。
发明内容
为解决上述问题，本发明的目的在于提供一种水下清淤机器人路径规划方法、装置、机器人和存储介质，采用混合布谷鸟搜索和蝙蝠算法的方法，使清淤机器人在避障的同时能够以最短路径到达清淤目标点。清淤机器人到达目标点后，采用S形对清淤区域进行全面清扫，并且利用几何算法完成避障。通过此水下清淤机器人的路径规划方法，从而完成自动化程度高，人力成本低，环保高效的水下清淤工作。
本发明解决其问题所采用的技术方案是：
第一方面，本发明实施例提出了一种水下清淤机器人路径规划方法，包括：
根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；
判断起始点和清淤目标点之间的最短连线是否有静态障碍物，并通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；
清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；
清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
进一步，所述蝙蝠种群的参数包括蝙蝠种群的大小、频率f
i、脉冲发射率r
i、响度A
i，其中频率f
i、脉冲发射率r
i以及响度A
i的计算公式为：
f
i＝f
min+(f
max-f
min)β
其中，f
min和f
max为蝙蝠发出的最小频率和最大频率，取值范围为[0,1]；α和γ是常数，α和γ的取值范围分别为[0,1]、[0,+∞],通常各取0.9。
进一步，所述通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径，包括：
根据水下环境产生蝙蝠以及蝙蝠巢穴的数量，运用布谷鸟搜索得出当前随机蝙蝠巢穴位置的局部路径最优解并保留，将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，输出全局最优路径。
进一步，所述运用布谷鸟搜索得出当前随机蝙蝠巢穴位置的局部路径最优解并保留，包括：
运用莱维飞行对蝙蝠巢穴位置进行更新，得到一组新的蝙蝠巢穴位置，对这组蝙蝠巢穴位置与上一代的蝙蝠巢穴位置进行对比，用好的蝙蝠巢穴位置替换差的蝙蝠巢穴位置，得到优化的蝙蝠巢穴位置，其中，蝙蝠巢穴位置更新的公式为：
其中，α>0是步长缩放因子，
为蝙蝠巢穴原位置，
为更新之后的蝙蝠巢穴位置，L(s,λ)是莱维随机路径；s是步长，s
0是最小步长，λ>0为莱维指数；Г为标准的Gamma函数,其对于给定的λ是一个常数。
进一步，所述将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，其中更新蝙蝠位置采用以下公式：
其中，
为蝙蝠当前位置，c
*是由谷布鸟搜索产生的当前最佳位置，
为蝙蝠当前速度，
为更新后的蝙蝠速度，
为更新后的蝙蝠最佳位置。
进一步，所述将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，其中优化蝙蝠位置采用以下公式：
x
new＝x
old+εA
t
其中，ε为介于[-1,1]的均匀分布随机数，A
t是第t代所有蝙蝠响度的平均值，x
old为当前最优个体，x
new是优化后产生的新个体。
进一步，所述清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障，包括：
判断动态障碍物与清淤机器人与之间的阻塞情况，由以下公式产生：
angle
direction＝a tan 2((Y
obs-Y
robot),(X
obs-X
robot))
angle
Vrbbot＝a tan 2(V
j,V
i)
|angle
direction-angle
Vrobot|＜angle
thresh
angle
Vdiff＝|angle
Vrobot-angle
Vobs|
其中，angle
direction为移动障碍物的方向向量，(X
obs,Y
obs)为当前障碍物的坐标，(X
robot,Y
robot)为清淤机器人的坐标；angle
vrobot为清淤机器人的速度矢量，V
j,V
i分别是清淤机器人Y轴、X轴的速度矢量；angle
thresh为一判断阈值，用来判断动态障碍物是否阻塞清淤机器人前进的路径，若移动障碍物方向向量与清淤机器人速度矢量之差的绝对值小于该阈值，则该动态障碍物阻塞了清淤机器人的前进路径，否则没有造成阻塞；在进行绝对值计算之前，应将angle
vrobot和angle
direction进行处理，使其在(-π，π)范围之内；angle
Vdiff为清淤机器人的速度矢量与移动障碍物的速度矢量的绝对值之差。
第二方面，本发明实施例还提出了一种水下清淤机器人路径规划装置，包括：
初始化模块，用于根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；
静态避障模块，用于判断起始点和清淤目标点之间的最短连线是否有静态障碍物，并通 过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；
动态避障模块，用于清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；
清淤航线模块，用于对清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
第三方面，本发明实施例还提出了一种机器人，包括：
至少一个处理器；以及，
与所述至少一个处理器通信连接的存储器；其中，
所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行本发明第一方面所述的方法。
第四方面，本发明实施例还提出了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行本发明第一方面所述的方法。
本发明实施例中提供的一个或多个技术方案，至少具有如下有益效果：本发明提供的一种水下清淤机器人路径规划方法、装置、机器人和存储介质，针对水下清淤路径规划，利用布谷鸟搜索迅速得出局部最优路径，以此局部最优路径为引导使蝙蝠有目的进行搜索，得出全局最佳路径，实现最短路径及进行动态避障。清淤机器人到达清淤区域后，对清淤路线进行规划，清淤过程采用S形清淤路线，并用几何算法进行避障。采用S形清淤路线可以使得淤泥清理更全面，且使用几何算法进行规避障碍物，使得清淤过程更安全。
下面结合附图和实例对本发明作进一步说明。
图1是本发明第一实施例中水下清淤机器人路径规划方法的流程简图；
图2是本发明第一实施例中水下清淤机器人路径规划方法的具体流程图；
图3是本发明第一实施例中水下清淤机器人路径规划方法中几何算法原理图；
图4是本发明第一实施例中水下清淤机器人路径规划方法中基于几何算法的路径规划流程图；
图5是本发明第二实施例中水下清淤机器人路径规划装置的结构简图。
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅用以解释本发明，并不用于限定本发明。
需要说明的是，如果不冲突，本发明实施例中的各个特征可以相互结合，均在本发明的保护范围之内。另外，虽然在装置示意图中进行了功能模块划分，在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于装置中的模块划分，或流程图中的顺序执行所示出或描述的步骤。
下面结合附图，对本发明实施例作进一步阐述。
如图1所示，本发明的第一实施例提供了一种水下清淤机器人路径规划方法，包括但不限于以下步骤：
S100:根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；
S200:判断起始点和清淤目标点之间的最短连线是否有静态障碍物，并通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；
S300:清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；
S400:清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
优选地，本发明具体实施步骤可以进一步细分如下，如图2所示：
步骤1：采用声纳装置获取水下环境信息。
步骤2：初始化随机种群的大小(蝙蝠/巢的数量)，频率f
i，脉冲发射率r
i，响度A
i。
其中蝙蝠/巢的数量是根据水下的实际情况来确定的，不同的水下环境大小，所需数量是不同的。频率f
i、脉冲发射率r
i，响度A
i的计算公式为：
f
i＝f
min+(f
max-f
min)β 1-1
其中，其中f
min和f
max为蝙蝠发出的最小频率和最大频率，取值范围为[0,1]，是服从均匀分布的随机向量；其中α和γ是常数，α和γ的取值范围分别为[0,1]、[0,+∞]，通常各 取0.9。
步骤3：初始化清淤机器人起始点和目标点的位置。
步骤4：清淤机器人判断起始点和清淤目标点之间的最短连线是否有静态障碍物。
若无，则清淤机器人按照起始点和清淤目标点之间的最短连线进行移动。移动期间是否检测到动态障碍物，若存在则跳到步骤13；若无，则朝着清淤目标点前进。当清淤机器人完成移动后，判断其是否已经到达了目标点，若到达了，则开始清淤，若无，则返回步骤3。
若存在障碍，则启用混合布谷鸟搜索和蝙蝠算法。
步骤5：清淤机器人根据水下实际情况产生蝙蝠以及蝙蝠巢穴的数量。
步骤6：运用布谷鸟搜索得出当前随机蝙蝠巢穴位置最优解，保留当前最优解。
步骤7：运用莱维飞行对蝙蝠巢穴位置进行更新，得到一组新的蝙蝠巢穴位置，对这组蝙蝠巢穴位置与上一代蝙蝠巢穴位置进行对比，用好的蝙蝠巢穴位置替换差的蝙蝠巢穴位置，得到较优的蝙蝠巢穴位置。蝙蝠巢穴位置更新的公式为:
其中，α>0是步长缩放因子，
为巢穴原位置，
为更新之后的巢穴位置，L(s,λ)是莱维随机路径；s是步长，s
0是最小步长，λ>0为莱维指数；Г为标准的Gamma函数,其对于给定的λ是一个常数。
步骤8：运用算法去模拟巢穴的外来鸟蛋被鸟窝主人发现，被发现外来鸟蛋的巢穴进行随机位置更新，保留未被发现外来鸟蛋巢穴的位置，得到一组新的巢穴的位置。再将这组巢穴位置进行测试，与之前的巢穴位置的测试值进行对比，用测试值较好的巢穴的位置替换测试值较差的巢穴的位置。
进行模拟外来鸟蛋被发现，并进行位置更新的公式为：
其中，
为原被发现外来鸟蛋巢穴的位置，
为更新后巢穴的位置，α>0是步长缩放因子，s>0是步长，H函数是一个单位阶跃函数，
和
是通过随机置换选择的两个不同的解。
步骤9：找出上述步骤8中最后得出的最优巢穴的位置。若到达迭代停止条件，则将局部路径最优解输入到蝙蝠算法中。若没有达到，则返回步骤7。
步骤10：蝙蝠算法通过布谷鸟搜索给出的局部路径最优解作为输入，更新自身的位置。
其中
为蝙蝠当前位置，c
*是由谷布鸟搜索产生的当前最佳位置，
为蝙蝠当前速度，
为更新后的蝙蝠速度，
为更新后的蝙蝠最佳位置。
步骤11：由生成的均匀分布随机数P与脉冲发射率进行比较r
i，若生成的随机数大于脉冲发射率r
i，对最佳解的位置进行优化。否则，进入下一步。
对最佳解进行优化的公式为：
x
new＝x
old+εA
t 1-9
其中ε为[-1,1]上的均匀分布随机数，A
t是第t代所有蝙蝠响度的平均值，x
old为当前最优个体，x
new是优化后产生的新个体。
P为[0，1]上的均匀分布随机数。脉冲发射率r
i∈(0,1]。
步骤12：对蝙蝠的飞行后的新旧位置进行比较，用较好的值去替换较差的值。然后找出最优解，判断是否达到最大迭代次数，若没有达到，则返回步骤10，若达到则输出全局最优路径。
步骤13：清淤机器人根据规划好的路径朝着清淤目标点进行移动。清淤机器人在行走过程中，有一探测仪在一定范围内探测周围是否存在动态障碍物。
若存在动态障碍物，则判断该动态障碍物是否阻塞清淤机器人要前进的路径，若造成了阻塞，则清淤机器人将进入下一步判断：情况1、清淤机器人与动态障碍物大致同向运动；情况2、清淤机器人与动态障碍物大致面对面进行移动；情况3、清淤机器人与动态障碍物朝着不同的方向运动。对于情况1，清淤机器人只需跟随障碍物，直至障碍物改变方向，或者规划好的路径使机器人远离障碍物。对于情况2，则需要重新规划路径，使清淤机器人绕开移动障碍物并且回到原路径上。对于情况3，清淤机器人只需按照原规划路径进行移动即可。若没有造成阻塞，清淤机器人按照原规划路径进行移动。
若没有动态障碍物，清淤机器人按照原规划路径进行移动。
判断动态障碍物是否造成阻塞及造成阻塞后清淤机器人与动态障碍物的三种情况，由如下计算公式产生：
angle
direction＝a tan 2((Y
obs-Y
robot),(X
obs-X
robot)) 1-10
其中angle
direction为移动障碍物的方向向量，(X
obs,Y
obs)为当前障碍物的坐标，(X
robot,Y
robot)为清淤机器人的坐标。
angle
Vrbbot＝a tan 2(V
j,V
i) 1-11
其中angle
vrobot为清淤机器人的速度矢量，V
j,V
i分别是清淤机器人Y轴、X轴的速度矢量。
|angle
direction-angle
Vrobot|＜angle
thresh 1-12
其中angle
thresh为一判断阈值，用来判断动态障碍物是否阻塞清淤机器人前进的路径。若移动障碍物方向向量与清淤机器人速度矢量之差的绝对值小于该阈值，则该动态障碍物阻塞了清淤机器人的前进路径，否则没有造成阻塞。在进行绝对值计算之前，应将angle
vrobot和angle
direction进行处理，使其在(-π，π)范围之内。
angle
Vdiff＝|angle
Vrobot-angle
Vobs| 1-13
其中angle
Vdiff为清淤机器人的速度矢量与移动障碍物的速度矢量的绝对值之差。angle
Vobs可利用计算公式1-11得出。
若利用计算公式1-12进行判断得出动态障碍物阻塞清淤机器人前进的路径后，利用计算公式1-13得出的angle
Vdiff进行上述三种情况判断：若angle
Vdiff＜angle
thresh则对应于上述情况1；若angle
Vdiff＜π-angle
thresh则对应于上述情况2；若angle
Vdiff不在上述范围内，则对应于上述情况3。
针对上述情况2所要进行的路径重新规划给出了如下方法：清淤机器人通过移动障碍物的方向向量和速度矢量，对移动障碍物的运动进行预测。将移动障碍物所要经过的位置坐标进行无效化。然后以清淤机器人当前位置为起点位置，以距离移动障碍物最近，且清淤机器人不与移动障碍物发生碰撞的原路径上的坐标为目标位置，利用混合布谷鸟搜索和蝙蝠算法进行路径规划，使得清淤机器人绕开移动障碍物，并回到原路径规划上，按原路径规划向清淤目标点继续前进。
步骤14：清淤机器人按照原规划路径走完后判断是否到达了目标点，若无，则返回步骤3，若到达目标点则开始进行清淤。
清淤机器人在清淤区域行走过程采用S形清淤路线，若遇到障碍物则根据几何算法来规避，具体原理如下：
如图3所示,P
i是现在点,S是淤泥挖掘目标点,连接P
iS。若没有障碍物则航行器沿着P
iS到达目标点,由于航线进入了圆形障碍区域O
j的范围,则必须绕过障碍区。图3中,圆O
j是与线段P
iS相交且圆心距最短的圆。过P
i作圆O
j的切线,得P
iQ
j和P
iQ′
j,由于∠Q
jP
jS＜∠Q′
jP
jS,取线段P
jQ
j作为航经路段,过S作圆O
j的切线,取切点距O
j近的切点H
j。若线段P
iQ
j没有与圆相交,则以H
j为现在点继续判断P
i+1＝H
j,路径为P
iQ
j和劣弧Q
jH
j。若线段P
iQ
j与圆相交,且距圆最近的圆为O
k，则P
i+1＝H
k。
路径为P
iQ
k和劣弧Q
kH
k,路径规划算法的整体流程如图4所示。若∠Q
jP
iS＝∠Q′
jP
iS,则保留路径,直至两条路径重合到一点,保留长度短的路径,再按图4所示方法执行。
步骤15：清淤机器人达到清淤区域后，确定自身的坐标和清淤挖掘点的坐标。
步骤16：清淤机器人根据欧式公式计算得出其距离最近的第一淤泥挖掘区域。
步骤17：剩下的区域按照S形航线完成该区域的清淤任务，清淤过程中遇到障碍物，机器人将根据几何算法规避。
步骤18：清淤机器人完成第一区域任务后，返回执行步骤3到步骤17，完成第二区域的清理，往后，以此类推。
综上所述，针对清淤机器人对水下清淤路径的规划，该路径规划先采用混合布谷鸟搜索和蝙蝠算法的方法到达清淤目标点。布谷鸟搜索可以迅速找到到达目标点的路径，但找到的路径可能只是局部最佳路径。蝙蝠算法可以找到全局最佳路径，但由于其是随机迭代的方式，可能算法难以收敛，搜索时间久。而混合布谷鸟搜索和蝙蝠算法可以拟补缺点，发挥出各自算法的优势，利用布谷鸟搜索迅速得出局部最优路径，以此局部最优路径为引导使蝙蝠有目的进行搜索，得出全局最佳路径，实现最短路径及进行动态避障。清淤机器人到达清淤区域后，对清淤路线进行规划，清淤过程采用S形清淤路线，并用几何算法进行避障。采用S形清淤路线可以使得淤泥清理更全面，且使用几何算法进行规避障碍物，使得清淤过程更安全。
另外，如图5所示，本发明的第二实施例提供了一种水下清淤机器人路径规划装置，包括：
初始化模块110，用于根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；
静态避障模块120，用于判断起始点和清淤目标点之间的最短连线是否有静态障碍物， 并通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；
动态避障模块130，用于清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；
清淤航线模块140，用于对清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
本实施例中的水下清淤机器人路径规划装置与第一实施例中的水下清淤机器人路径规划方法基于相同的发明构思，因此，本实施例中的水下清淤机器人路径规划系统具有相同的有益效果：利用布谷鸟搜索迅速得出局部最优路径，以此局部最优路径为引导使蝙蝠有目的进行搜索，得出全局最佳路径，实现最短路径及进行动态避障。清淤机器人到达清淤区域后，对清淤路线进行规划，清淤过程采用S形清淤路线，并用几何算法进行避障。采用S形清淤路线可以使得淤泥清理更全面，且使用几何算法进行规避障碍物，使得清淤过程更安全。
本发明的第三实施例还提供了一种机器人，包括：
至少一个处理器；
以及与所述至少一个处理器通信连接的存储器；
其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如上述第一实施例中任意一种水下清淤机器人路径规划方法。
存储器作为一种非暂态计算机可读存储介质，可用于存储非暂态软件程序、非暂态性计算机可执行程序以及模块，如本发明实施例中的虚拟影像控制方法对应的程序指令/模块。处理器通过运行存储在存储器中的非暂态软件程序、指令以及模块，从而执行立体成像处理装置的各种功能应用以及数据处理，即实现上述任一方法实施例的水下清淤机器人路径规划方法。
存储器可以包括存储程序区和存储数据区，其中，存储程序区可存储操作系统、至少一个功能所需要的应用程序；存储数据区可存储根据立体成像处理装置的使用所创建的数据等。此外，存储器可以包括高速随机存取存储器，还可以包括非暂态存储器，例如至少一个磁盘存储器件、闪存器件、或其他非暂态固态存储器件。在一些实施例中，存储器可选包括相对于处理器远程设置的存储器，这些远程存储器可以通过网络连接至该立体投影装置。上述网络的实例包括但不限于互联网、企业内部网、局域网、移动通信网及其组合。
所述一个或者多个模块存储在所述存储器中，当被所述一个或者多个处理器执行时，执行上述任意方法实施例中的水下清淤机器人路径规划方法，例如第一实施例中的方法步骤S100至S400。
本发明的第四实施例还提供了一种计算机可读存储介质，所述计算机可读存储介质存储有计算机可执行指令，该计算机可执行指令被一个或多个控制处理器执行，可使得上述一个或多个处理器执行上述方法实施例中的一种水下清淤机器人路径规划方法，例如第一实施例中的方法步骤S100至S400。
以上所描述的装置实施例仅仅是示意性的，其中所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部模块来实现本实施例方案的目的。
通过以上的实施方式的描述，本领域普通技术人员可以清楚地了解到各实施方式可借助软件加通用硬件平台的方式来实现，当然也可以通过硬件。本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程是可以通过计算机程序来指令相关的硬件来完成，所述的程序可存储于一计算机可读取存储介质中，该程序在执行时，可包括如上述各方法的实施例的流程。其中，所述的存储介质可为磁碟、光盘、只读存储记忆体(Read-Only Memory,ROM)或随机存储记忆体(Random Access Memory,RAM)等。
以上是对本发明的较佳实施进行了具体说明，但本发明并不局限于上述实施方式，熟悉本领域的技术人员在不违背本发明精神的前提下还可作出种种的等同变形或替换，这些等同的变形或替换均包含在本申请权利要求所限定的范围内。
Claims (10)
- 一种水下清淤机器人路径规划方法，其特征在于，包括：根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；判断起始点和清淤目标点之间的最短连线是否有静态障碍物，并通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
- 根据权利要求1所述的一种水下清淤机器人路径规划方法，其特征在于，所述蝙蝠种群的参数包括蝙蝠种群的大小、频率f i、脉冲发射率r i、响度A i，其中频率f i、脉冲发射率r i以及响度A i的计算公式为：f i＝f min+(f max-f min)β
其中，f min和f max为蝙蝠发出的最小频率和最大频率，取值范围为[0,1]；α和γ是常数，α和γ的取值范围分别为[0,1]、[0,+∞]。 - 根据权利要求1所述的一种水下清淤机器人路径规划方法，其特征在于，所述通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径，包括：根据水下环境产生蝙蝠以及蝙蝠巢穴的数量，运用布谷鸟搜索得出当前随机蝙蝠巢穴位置的局部路径最优解并保留，将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，输出全局最优路径。
- 根据权利要求3所述的一种水下清淤机器人路径规划方法，其特征在于，所述运用布谷鸟搜索得出当前随机蝙蝠巢穴位置的局部路径最优解并保留，包括：运用莱维飞行对蝙蝠巢穴位置进行更新，得到一组新的蝙蝠巢穴位置，对这组蝙蝠巢穴位置与上一代的蝙蝠巢穴位置进行对比，用好的蝙蝠巢穴位置替换差的蝙蝠巢穴位置，得到优化的蝙蝠巢穴位置，其中，蝙蝠巢穴位置更新的公式为：
其中，α>0是步长缩放因子，为蝙蝠巢穴原位置，
为更新之后的蝙蝠巢穴位置，L(s,λ)是莱维随机路径；s是步长，s 0是最小步长，λ>0为莱维指数；Γ为标准的Gamma函数,其对于给定的λ是一个常数。
- 根据权利要求3所述的一种水下清淤机器人路径规划方法，其特征在于，所述将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，其中更新蝙蝠位置采用以下公式：
其中，为蝙蝠当前位置，c *是由谷布鸟搜索产生的当前最佳位置，
为蝙蝠当前速度，
为更新后的蝙蝠速度，
为更新后的蝙蝠最佳位置。
- 根据权利要求3所述的一种水下清淤机器人路径规划方法，其特征在于，所述将局部路径最优解作为蝙蝠算法的输入，更新蝙蝠位置并优化，其中优化蝙蝠位置采用以下公式：x new＝x old+εA t其中，ε为介于[-1,1]的均匀分布随机数，A t是第t代所有蝙蝠响度的平均值，x old为当前最优个体，x new是优化后产生的新个体。
- 根据权利要求1所述的一种水下清淤机器人路径规划方法，其特征在于，所述清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障，包括：判断动态障碍物与清淤机器人与之间的阻塞情况，由以下公式产生：angle direction＝a tan 2((Y obs-Y robot),(X obs-X robot))angle Vrbbot＝a tan 2(V j,V i)|angle direction-angle Vrobot|＜angle threshangle Vdiff＝|angle Vrobot-angle Vobs|其中，angle direction为移动障碍物的方向向量，(X obs,Y obs)为当前障碍物的坐标，(X robot,Y robot)为清淤机器人的坐标；angle vrobot为清淤机器人的速度矢量，V j,V i分别是清淤机器人Y轴、X轴的速度矢量；angle thresh为一判断阈值，用来判断动态障碍物是否阻塞清淤机器 人前进的路径；angle Vdiff为清淤机器人的速度矢量与移动障碍物的速度矢量的绝对值之差。
- 一种水下清淤机器人路径规划装置，其特征在于，包括：初始化模块，用于根据水下环境初始化蝙蝠种群的参数，并初始化清淤机器人起始点和清淤目标点的位置；静态避障模块，用于判断起始点和清淤目标点之间的最短连线是否有静态障碍物，并通过采用混合后的布谷鸟搜索和蝙蝠算法来得出全局最优路径；动态避障模块，用于清淤机器人沿着全局最优路径向清淤目标点移动，并在其移动过程中判断是否存在动态障碍物以实现避障；清淤航线模块，用于对清淤机器人到达清淤目标点后，确定其自身的坐标和清淤挖掘点的坐标，并根据欧式公式计算出距离其自身最近的淤泥挖掘区域，其余的淤泥挖掘区域按照S形航线完成清淤，且在清淤过程中利用几何算法进行避障。
- 一种机器人，其特征在于，包括：至少一个处理器；以及，与所述至少一个处理器通信连接的存储器；其中，所述存储器存储有可被所述至少一个处理器执行的指令，所述指令被所述至少一个处理器执行，以使所述至少一个处理器能够执行如权利要求1-7任一项所述的方法。
- 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质存储有计算机可执行指令，所述计算机可执行指令用于使计算机执行如权利要求1-7任一项所述的方法。
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911051780.1 | 2019-10-31 | ||
| CN201911051780.1A CN110764518B (zh) | 2019-10-31 | 2019-10-31 | 水下清淤机器人路径规划方法、装置、机器人和存储介质 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2021082709A1 true WO2021082709A1 (zh) | 2021-05-06 |
Family
ID=69334954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/CN2020/112533 WO2021082709A1 (zh) | 2019-10-31 | 2020-08-31 | 水下清淤机器人路径规划方法、装置、机器人和存储介质 |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN110764518B (zh) |
| WO (1) | WO2021082709A1 (zh) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110764518B (zh) * | 2019-10-31 | 2021-05-11 | 五邑大学 | 水下清淤机器人路径规划方法、装置、机器人和存储介质 |
| CN111930121B (zh) * | 2020-08-10 | 2022-10-25 | 哈尔滨工程大学 | 一种室内移动机器人的混合路径规划方法 |
| CN112100824B (zh) * | 2020-08-26 | 2024-02-27 | 西安工程大学 | 一种改进的布谷鸟算法及优化机器人结构参数的方法 |
| CN114237240B (zh) * | 2021-12-07 | 2023-10-27 | 内蒙古黄陶勒盖煤炭有限责任公司 | 智能清淤机器人及其行走控制方法 |
| CN117966876B (zh) * | 2024-04-02 | 2024-05-31 | 福建巨联环境科技股份有限公司 | 一种基于机器人技术的管网清淤检测方法及系统 |
| CN118226861B (zh) * | 2024-05-24 | 2024-07-16 | 广州市城市排水有限公司 | 基于智能算法的水下智能机器人巡航控制方法及系统 |
| CN118464027B (zh) * | 2024-07-15 | 2024-09-20 | 广东赛威赢环境技术工程有限公司 | 用于清淤机器人的清淤路径规划系统及方法 |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101048098B1 (ko) * | 2008-09-03 | 2011-07-11 | 한국과학기술원 | 로봇의 경로계획 장치 및 방법 |
| CN103760907A (zh) * | 2013-12-30 | 2014-04-30 | 哈尔滨工程大学 | 一种基于布谷鸟搜索算法的水下潜器三维路径规划方法 |
| CN107272705A (zh) * | 2017-07-31 | 2017-10-20 | 中南大学 | 一种智能环境下机器人路径的多神经网络控制规划方法 |
| CN107368076A (zh) * | 2017-07-31 | 2017-11-21 | 中南大学 | 一种智能环境下机器人运动路径深度学习控制规划方法 |
| CN108415434A (zh) * | 2018-03-29 | 2018-08-17 | 五邑大学 | 一种机器人调度方法 |
| CN110764518A (zh) * | 2019-10-31 | 2020-02-07 | 五邑大学 | 水下清淤机器人路径规划方法、装置、机器人和存储介质 |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP5112666B2 (ja) * | 2006-09-11 | 2013-01-09 | 株式会社日立製作所 | 移動装置 |
| BE1018564A4 (nl) * | 2009-01-12 | 2011-03-01 | Dredging Int | Werkwijze en inrichting voor het aansturen van een mobiele grondbehandelinrichting. |
| CN105640443B (zh) * | 2014-12-03 | 2018-09-04 | 小米科技有限责任公司 | 自动清洁设备的静音工作方法及装置、电子设备 |
| CN106826834B (zh) * | 2016-12-26 | 2019-02-15 | 南京熊猫电子股份有限公司 | 一种机器人焊接自动寻位方法 |
| CN106647808B (zh) * | 2017-01-05 | 2020-02-14 | 台州施特自动化有限公司 | 一种基于模糊控制算法的AUVs搜索和围捕任务分配控制方法 |
| CN107168309B (zh) * | 2017-05-02 | 2020-02-14 | 哈尔滨工程大学 | 一种基于行为的多水下机器人路径规划方法 |
| CN207281588U (zh) * | 2017-05-25 | 2018-04-27 | 扬州大学 | 一种清淤机器人的清淤路径勘探系统 |
| US10795377B2 (en) * | 2018-01-03 | 2020-10-06 | AI Incorporated | Method for autonomously controlling speed of components and functions of a robot |
| CN108303092B (zh) * | 2018-01-12 | 2020-10-16 | 浙江国自机器人技术有限公司 | 一种自行规划路径的清洗方法 |
| CN108301456A (zh) * | 2018-01-16 | 2018-07-20 | 广东联芯智能科技有限公司 | 水底清污机器人及其使用方法 |
| CN108829137A (zh) * | 2018-05-23 | 2018-11-16 | 中国科学院深圳先进技术研究院 | 一种机器人目标追踪的避障方法及装置 |
| CN109183884A (zh) * | 2018-09-30 | 2019-01-11 | 苏州凯财速诚电子科技有限公司 | 一种基于疏浚机器人的智能控制及效率协同优化系统 |
| CN109782807B (zh) * | 2019-03-08 | 2021-10-01 | 哈尔滨工程大学 | 一种回形障碍物环境下的auv避障方法 |
-
2019
- 2019-10-31 CN CN201911051780.1A patent/CN110764518B/zh active Active
-
2020
- 2020-08-31 WO PCT/CN2020/112533 patent/WO2021082709A1/zh active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101048098B1 (ko) * | 2008-09-03 | 2011-07-11 | 한국과학기술원 | 로봇의 경로계획 장치 및 방법 |
| CN103760907A (zh) * | 2013-12-30 | 2014-04-30 | 哈尔滨工程大学 | 一种基于布谷鸟搜索算法的水下潜器三维路径规划方法 |
| CN107272705A (zh) * | 2017-07-31 | 2017-10-20 | 中南大学 | 一种智能环境下机器人路径的多神经网络控制规划方法 |
| CN107368076A (zh) * | 2017-07-31 | 2017-11-21 | 中南大学 | 一种智能环境下机器人运动路径深度学习控制规划方法 |
| CN108415434A (zh) * | 2018-03-29 | 2018-08-17 | 五邑大学 | 一种机器人调度方法 |
| CN110764518A (zh) * | 2019-10-31 | 2020-02-07 | 五邑大学 | 水下清淤机器人路径规划方法、装置、机器人和存储介质 |
Non-Patent Citations (1)
| Title |
|---|
| ZHU, YUNLONG ET AL.: "Research Status and Development Trends of the Bio-inspired Computation", INFORMATION AND CONTROL, vol. 45, no. 5, 31 December 2016 (2016-12-31), pages 600 - 614,640, XP055809985, ISSN: 1002-0411 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110764518A (zh) | 2020-02-07 |
| CN110764518B (zh) | 2021-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2021082709A1 (zh) | 水下清淤机器人路径规划方法、装置、机器人和存储介质 | |
| US20210109537A1 (en) | Autonomous exploration framework for indoor mobile robotics using reduced approximated generalized voronoi graph | |
| US10466058B2 (en) | Navigation for vehicles | |
| Lolla et al. | Time-optimal path planning in dynamic flows using level set equations: theory and schemes | |
| Pandey et al. | Three-dimensional path planning for unmanned aerial vehicles using glowworm swarm optimization algorithm | |
| WO2021082710A1 (zh) | 无人船路径规划方法、装置、设备和存储介质 | |
| Gan et al. | Multi-UAV target search using explicit decentralized gradient-based negotiation | |
| US10365110B2 (en) | Method and system for determining a path of an object for moving from a starting state to an end state set avoiding one or more obstacles | |
| US20170168488A1 (en) | Autonomous visual navigation | |
| CN110986953B (zh) | 路径规划方法、机器人及计算机可读存储介质 | |
| KR102531197B1 (ko) | 무인 비행체의 최적 경로 생성 방법 및 장치 | |
| Han | An efficient approach to 3D path planning | |
| CN111158353A (zh) | 用于多个机器人的移动控制方法以及其系统 | |
| CN114705196A (zh) | 一种用于机器人的自适应启发式全局路径规划方法与系统 | |
| CN109341698B (zh) | 一种移动机器人的路径选择方法及装置 | |
| CN112947594A (zh) | 一种面向无人机的航迹规划方法 | |
| US20240239484A1 (en) | Fast path planning for dynamic avoidance in partially known environments | |
| CN117389305A (zh) | 一种无人机巡检路径规划方法、系统、设备及介质 | |
| CN115143970A (zh) | 一种基于威胁度评估的水下航行器避障方法和系统 | |
| US20220382286A1 (en) | Managing conflicting interactions between a movable device and potential obstacles | |
| JP2018120482A (ja) | ロボットおよびその制御方法 | |
| Shvets | Stochastic Multi-Agent Patrolling Using Social Potential Fields. | |
| Kumar et al. | Area exploration by flocking of multi robot | |
| Cruz-Bernal | Meta-heuristic optimization techniques and its applications in robotics | |
| CN111984032B (zh) | 无人机路径规划方法、装置、电子设备及存储介质 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 20883554 Country of ref document: EP Kind code of ref document: A1 |
|
| NENP | Non-entry into the national phase |
Ref country code: DE |
|
| 122 | Ep: pct application non-entry in european phase |
Ref document number: 20883554 Country of ref document: EP Kind code of ref document: A1 |