CN113741416B - Multi-robot full-coverage path planning method based on improved predator prey model and DMPC - Google Patents
Multi-robot full-coverage path planning method based on improved predator prey model and DMPC Download PDFInfo
- Publication number
- CN113741416B CN113741416B CN202110824316.2A CN202110824316A CN113741416B CN 113741416 B CN113741416 B CN 113741416B CN 202110824316 A CN202110824316 A CN 202110824316A CN 113741416 B CN113741416 B CN 113741416B
- Authority
- CN
- China
- Prior art keywords
- robot
- grid
- steps
- path
- sequence
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- GZDFHIJNHHMENY-UHFFFAOYSA-N Dimethyl dicarbonate Chemical compound COC(=O)OC(=O)OC GZDFHIJNHHMENY-UHFFFAOYSA-N 0.000 title claims abstract description 13
- 244000062645 predators Species 0.000 title claims abstract description 11
- 230000005284 excitation Effects 0.000 claims abstract description 16
- 238000011156 evaluation Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 6
- 230000009191 jumping Effects 0.000 claims description 5
- 229920000535 Tan II Polymers 0.000 claims description 4
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 4
- 238000013459 approach Methods 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000007689 inspection Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013529 biological neural network Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000009194 climbing Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0231—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
- G05D1/0238—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors
- G05D1/024—Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using obstacle or wall sensors in combination with a laser
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0223—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving speed control of the vehicle
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0257—Control of position or course in two dimensions specially adapted to land vehicles using a radar
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Aviation & Aerospace Engineering (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Optics & Photonics (AREA)
- Electromagnetism (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
A multi-robot full-coverage path planning method based on an improved predator prey model and a DMPC inputs information such as map space, robot position, motion priority and the like; rasterizing a map space and endowing the map space with a grid state attribute; randomly generating an initial parameter population and population quantity; determining a robot motion model according to the surrounding grid state; entering a dead zone, and backtracking and disengaging by using a; the method includes the steps that a dead zone is not entered, and a grid with the maximum surrounding excitation is found and moved according to an excitation function; introducing a DMPC method, and predicting a moving sequence of the robot according to a motion model; searching an optimal moving sequence by utilizing WOA to solve parameter optimization; through continuous scrolling decision, full coverage of the map is realized. The invention can obtain the full coverage path with low path repetition rate and short total path length.
Description
Technical Field
The invention belongs to the field of full coverage of multiple robots, and particularly relates to a multi-robot full coverage path planning method based on an improved predator prey model and distributed model predictive control (Distributed Model Predictive Control, hereinafter referred to as DMPC).
Background
The full coverage path planning (Coverage Path planning, CPP) of robots has been widely applied to operations of robots, such as inspection robots for substation detection, wall climbing robots for boiler inspection, floor cleaning robots, and the like. The full-coverage path planning of the robot refers to planning a path traversing all working spaces on the premise that the robot avoids obstacles. The single robot cannot rapidly cover a large area due to the constraint of the performance of the single robot, is difficult to process a complex dangerous environment, and has poor system robustness. The robots can complete the full coverage of the map space more quickly than a single robot through mutual cooperation among the robots, meanwhile, the robots have built-in redundancy, and the robustness of the system is good, so that the research on the full coverage method of the robots is necessary.
Since the multiple robots cooperatively cover the same area, collision between the robots is avoided in addition to avoiding obstacles in planning the coverage path of the robots, so that it is necessary for planning the full coverage path of the multiple robots.
In practical robot use, in most cases, the robot often only has part or no a priori knowledge of the environment, so full coverage path planning for unknown maps is necessary. The existing full-coverage method of the unknown map comprises a full-coverage method based on a partition, a full-coverage method based on a biological neural network, a full-coverage method based on a template and a backtracking method, and the like, however, the existing method has the problems that the local optimum is trapped in the later planning stage, the backtracking area is repeated, and the robot coverage area is overlapped.
Disclosure of Invention
In order to overcome the defect that the robot coverage areas overlap due to the fact that the existing technology falls into local optimum in the later planning stage and backtracking areas are repeated, and in order to obtain a full-coverage path with low path repetition rate and short total path length, the invention provides a multi-robot full-coverage path planning method based on an improved predator prey model and a DMPC.
In order to achieve the above object, the present invention provides the following technical solutions:
a multi-robot full coverage path planning method based on an improved predator prey model and a DMPC, comprising the steps of:
step 1: inputting a map space, initial positions of multiple robots, detection radius of the robots and movement speed of the robots, and priority of robot movement;
step 2: the map space is rasterized, so that the robot can just cover one grid, different state attributes are given to each grid, the multi-robot system is divided into a plurality of subsystems, and the state attributes I (x, y) of the grids and the task space WS covered by the robot are respectively as follows:
WS＝{(x,y)|I(x,y)＝1,0＜x＜x_l,0＜y＜y_l} (2)
wherein x_l and y_l are the length of the x axis and the length of the y axis after the map space is scattered respectively;
step 3: random generation of initial parameter populationsThe population number is pop;
step 4: the robot determines the state attribute of the surrounding grids according to the information detected by the sensor, so as to judge whether the robot falls into a dead zone or not, and determine the motion model of the robot. If the dead zone is trapped, jumping to step 5, and if the dead zone is trapped, jumping to step 7;
step 5: removing grid coordinates in the radius r of other trace points from the trace list to obtain a search list L search The method comprises the following steps:
L search ＝L return /L back,r (3)
in which L return Representing a backtracking list, L back,r Representing a set of points within the backtracking point radius r;
step 6: finding the free grid coordinate closest to the current robot from the search list, separating from the dead zone by using an A-algorithm, obtaining a moving sequence of the robot, jumping to a step 10, and moving the sequence A of the robot path The method comprises the following steps:
A path ＝{A 1 ,A 2 ,…A i ,…P return } (4)
in which A i Coordinates of the path points defined for the rule of calculation a, P return The coordinates of the backtracking points;
step 7: calculating the excitation values of uncovered grids at the adjacent points of the robot according to the improved predator prey model, and calculating the excitation E avoiding competitors compete The method comprises the following steps:
wherein D represents the Euclidean distance between two grids, O kt,j Representative machineThe position of the person k near the point j at the time t, H represents the communication range H of the robot k max And the number of other robots. R is R k,i ，R k,m Respectively representing the ith and the m-th robot positions in the communication range;
step 8: calculating the movement direction stimulus E direction The method comprises the following steps:
∠O k,t-1 O k,t O kt,j ＝|atan2(y k,j -y k,t ,x k,j -x k,t )-atan2(y k,t -y k,t-1 ,x k,t -x k,t-1 )| (7)
middle +.O k,t-1 O k,t O kt,j Is the included angle between the current moving direction of the robot and the next moving direction, (x) k,t-1 ,y k,t-1 )，(x k,t ,y k,t )，(x k,j ,y k,j ) The coordinate positions of the robot k at the previous moment, the current moment and the next moment are respectively;
step 9: computing boundary excitation E b The method comprises the following steps:
n N (O kt,j ) Representing the number of uncovered grids at the point of approach j of the robot k,representing the maximum number of allowed adjacent points;
step 10: the grid total excitation value E is calculated as:
E(O kt,j )＝ω c E compete (O kt,j )+ω s E direction (O kt,j )+E b (O kt,j ) (9)
omega in c ，ω s Is a weight factor;
step 11: the robot determines the next moving coordinate of the robot according to the maximum excitation or the separation dead zone sequence, when a plurality of robots select the same grid at the same time, the robot with high priority moves preferentially, and the next moving coordinate of the robot is step k,t *：
Step 12: introducing a DMPC method, predicting a robot T-step path sequence according to the steps 4-11, taking the number of covered free grids and the path length as indexes, setting up an evaluation function, and predicting a sequence y k (t) and evaluation function respectively J (T) The method comprises the following steps:
y k (t)＝[y k (t+1|t),y k (t+2|t),…y k (t+T|t)] (11)
in N cover Representing the number of grids covered by the robot, wherein L represents the path length, and alpha and beta represent weight coefficients;
step 13: optimizing ω by WOA s Number of iterations WOA iter Taking the evaluation function of the robot T steps as an adaptability function to obtain an optimal movement sequence L of the robot T steps in the future T ：
L T ＝{Step k,t+1 ,…Step k,t+i ,…Step k,t+T } (13)
Wherein Step k,t+i Representing the position of robot k at time t+i, i=1, 2 … T;
step 14: the robot selects the forefront sequence in the moving sequence and moves, updates the grid map state and the robot position at the same time, adds uncovered grid information into a backtracking list, and deletes covered grid points;
step 15: the current iteration number item reaches the maximum iteration number item max Or (b)When, go to step 16; otherwise, iter=iter+1, returning to step 3;
step 16: and (5) outputting the path, and ending.
The beneficial effects of the invention are mainly represented in the following aspects:
1. the improved prey is used as a motion model, so that the retrospective points of the robot are effectively separated, and overlapping of the coverage areas of the robot is avoided. The robot can effectively cover the boundary area through guidance of boundary excitation in the covering process.
2. Based on rolling decision and WOA optimization solving under a DMPC framework, the method effectively balances short-term benefits and long-term benefits, and avoids local optimization.
3. The invention can realize the full coverage of the unknown map, can avoid obstacles and other robots, and has the coverage rate up to 100 percent and lower repetition rate.
Drawings
Fig. 1 is a flow chart of a robot motion model.
Fig. 2 is a flow chart of a method of planning a full coverage path for multiple robots.
Fig. 3 is a schematic diagram of a map space grid.
FIG. 4 is a full coverage path of multiple robots in a simulation experiment
Detailed Description
The invention is further described below with reference to the accompanying drawings.
Referring to fig. 1-4, a multi-robot full coverage path planning method based on an improved predator prey model and a DMPC, comprising the steps of:
step 1: inputting map space 30 x 30, the number of robots is 4, the initial positions of multiple robots, the detection radius of the robots and the movement speed of the robots, and the movement priority of the robots;
step 2: the map space is rasterized, so that the robot can just cover one grid, different state attributes are given to each grid, the multi-robot system is divided into a plurality of subsystems, and the state attributes of the grids and task spaces covered by the robot are respectively as follows:
WS＝{(x,y)|I(x,y)＝1,0＜x＜x_l,0＜y＜y_l} (2)
wherein x_l and y_l are the length of the x axis and the length of the y axis after the map space is scattered, x_l=30, and y_l=30;
step 3: random generation of initial parameter populationsPopulation number pop=50;
step 4: the robot determines the state attribute of surrounding grids according to the information of the surrounding environment detected by the laser radar, so as to judge whether the robot falls into a dead zone, determine a motion model of the robot, jump to step 4 if the robot falls into the dead zone, and jump to step 5 if the robot falls into the dead zone;
step 5: removing grid coordinates in the radius r of other trace points from the trace list to obtain a search list L search ：
L search ＝L return /L back,r (3)
In which L return Representing a backtracking list, L back,r Represents a set of points within a backtracking point radius r, where r=3;
step 6: finding the free grid coordinate closest to the current robot from the search list, separating from the dead zone by using an A-algorithm, obtaining a moving sequence of the robot, jumping to the step 7, and moving the sequence A of the robot path The method comprises the following steps:
A path ＝{A 1 ,A 2 ,…A i ,…P return } (4)
in which A i The path point coordinates planned for the algorithm A are calculated;
step 7: calculating the sizes of all excitation values of uncovered grids of the robot adjacent points according to the improved predator prey model, and calculating avoidanceCompetitor incentive E compete The method comprises the following steps:
wherein D represents the Euclidean distance between two grids, O kt,j Represents the position of the near point j of the robot k at the moment t, and H represents the communication range H of the robot k max The number of other robots in the system H max ＝3。R k,i ，R k,m Respectively representing the ith and the m-th robot positions in the communication range;
step 8: calculating the movement direction stimulus E direction The method comprises the following steps:
∠O k,t-1 O k,t O kt,j ＝|a tan 2(y k,j -y k,t ,x k,j -x k,t )-a tan 2(y k,t -y k,t-1 ,x k,t -x k,t-1 )| (7)
middle +.O k,t-1 O k,t O kt,j Is the included angle between the current moving direction of the robot and the next moving direction, (x) k,t-1 ,y k,t-1 )，(x k,t ,y k,t )，(x k,j ,y k,j ) The coordinate positions of the robot k at the previous moment, the current moment and the next moment are respectively;
step 9: computing boundary excitation E b The method comprises the following steps:
n N (O kt,j ) Representing the number of free grids at the point of approach j of the robot k,represents the maximum number of allowed proximity points of the robot, < ->
Step 10: the grid total excitation value E is calculated as:
E(O kt,j )＝ω c E compete (O kt,j )+ω s E direction (O kt,j )+E b (O kt,j ) (9)
omega in c ，ω s Is a weight factor omega c ＝0.01，ω s ∈[0,1]；
Step 11: the robot decides the next moving coordinate of the robot according to the maximum excitation or the separation dead zone sequence, when a plurality of robots select the same grid at the same moment, the robot with high priority moves preferentially in the following moving mode:
wherein A is path,0 Represents the forefront path point coordinates, O, in the path planning of the departure dead zone k,j ∈N u (R k ) Representing a set of near points of the robot k;
step 12: introducing a DMPC method, predicting a robot T-step path sequence according to the steps 4-11, taking the number of covered free grids and the path length as indexes, setting up an evaluation function, and predicting a sequence y k (t) and evaluation function respectively J (T) The method comprises the following steps:
y k (t)＝[y k (t+1|t),y k (t+2|t),…y k (t+T|t)] (11)
in N cover Representing the number of grids covered by the robot, L representing the path length, α, β representing the weight coefficient, α=1, β=0.01, t=3;
step 13: optimizing initial populations by WOAThe evaluation function of the T step of the robot is taken as a fitness function, and the iteration times are WOA iter =20, obtaining the optimal movement sequence L of the future T steps of the robot T ：
L T ＝{Step k,t ,Step k,t+1 ,…Step k,t+T-1 } (13)
Wherein Step k,t Representing the position of robot k at time t;
step 14: the robot selects the forefront sequence in the moving sequence and moves, updates the grid map state and the robot position at the same time, adds free grid information into a backtracking list, and deletes the covered grid points;
step 15: the current iteration number item reaches the maximum iteration number item max Or (b)When step 16, item is executed max =350; otherwise, iter=iter+1, returning to step 3;
step 16: outputting the paths of the robots and ending.
Specific examples of the present invention are described above in detail, but the present invention is not limited to the above examples. All variations that can be made by logical reasoning, analysis, and other experiments in light of the present concepts of the invention by those of ordinary skill in the art are considered to be within the scope of the present invention.
Claims (1)
1. A multi-robot full coverage path planning method based on an improved predator prey model and a DMPC, the method comprising the steps of:
step 1: inputting a map space, initial positions of multiple robots, detection radius of the robots and movement speed of the robots, and priority of robot movement;
step 2: the map space is rasterized, so that the robot can just cover one grid, different state attributes are given to each grid, the multi-robot system is divided into a plurality of subsystems, and the state attributes I (x, y) of the grids and the task space WS covered by the robot are respectively as follows:
WS＝{(x,y)|I(x,y)＝1,0＜x＜x_l,0＜y＜y_l} (2)
wherein x_l and y_l are the length of the x axis and the length of the y axis after the map space is scattered respectively;
step 3: random generation of initial parameter populationsThe population number is pop;
step 4: the robot determines the state attribute of surrounding grids according to the information detected by the sensor, so as to judge whether the robot falls into a dead zone, determine a motion model of the robot, jump to step 5 if the robot falls into the dead zone, and jump to step 7 if the robot falls into the dead zone;
step 5: removing grid coordinates in the radius r of other trace points from the trace list to obtain a search list L search The method comprises the following steps:
L search ＝L return /L back,r (3)
in which L return Representing a backtracking list, L back,r Representing a set of points within the backtracking point radius r;
step 6: finding the free grid coordinate closest to the current robot from the search list, separating from the dead zone by using an A-algorithm, obtaining a moving sequence of the robot, jumping to a step 10, and moving the sequence A of the robot path The method comprises the following steps:
A path ＝{A 1 ,A 2 ,…A i ,…P return } (4)
in which A i Coordinates of the path points defined for the rule of calculation a, P return The coordinates of the backtracking points;
step 7: calculating the sizes of all excitation values of uncovered grids of the robot adjacent points according to the improved predator prey model, and calculating to avoid the competitionContention stimulus E compete The method comprises the following steps:
wherein D represents the Euclidean distance between two grids, O kt,j Represents the position of the near point j of the robot k at the moment t, and H represents the communication range H of the robot k max The number of other robots in the robot, R k,i ，R k,m Respectively representing the ith and the m-th robot positions in the communication range;
step 8: calculating the movement direction stimulus E direction The method comprises the following steps:
∠O k,t-1 O k,t O kt,j ＝|a tan 2(y k,j -y k,t ,x k,j -x k,t )-a tan 2(y k,t -y k,t-1 ,x k,t -x k,t-1 )| (7)
middle +.O k,t-1 O k,t O kt,j Is the included angle between the current moving direction of the robot and the next moving direction, (x) k,t-1 ,y k,t-1 )，(x k,t ,y k,t )，(x k,j ,y k,j ) The coordinate positions of the robot k at the previous moment, the current moment and the next moment are respectively;
step 9: computing boundary excitation E b The method comprises the following steps:
n N (O kt,j ) Representing the number of uncovered grids at the point of approach j of the robot k,representing the maximum number of allowed proxels；
Step 10: the grid total excitation value E is calculated as:
E(O kt,j )＝ω c E compete (O kt,j )+ω s E direction (O kt,j )+E b (O kt,j ) (9)
omega in c ，ω s Is a weight factor;
step 11: the robot determines the next moving coordinate of the robot according to the maximum excitation or the separation dead zone sequence, when a plurality of robots select the same grid at the same time, the robot with high priority moves preferentially, and the next moving coordinate of the robot is step k,t *：
Step 12: introducing a DMPC method, predicting a robot T-step path sequence according to the steps 4-11, taking the number of covered free grids and the path length as indexes, setting up an evaluation function, and predicting a sequence y k (t) and evaluation function respectively J (T) The method comprises the following steps:
y k (t)＝[y k (t+1|t),y k (t+2|t),…y k (t+T|t)] (11)
in N cover Representing the number of grids covered by the robot, wherein L represents the path length, and alpha and beta represent weight coefficients;
step 13: optimizing ω by WOA s Number of iterations WOA iter Taking the evaluation function of the robot T steps as an adaptability function to obtain an optimal movement sequence L of the robot T steps in the future T ：
L T ＝{Step k,t+1 ,…Step k,t+i ,…Step k,t+T } (13)
Wherein Step k,t+i Representing the position of robot k at time t + i, i=1,2…T；
step 14: the robot selects the forefront sequence in the moving sequence and moves, updates the grid map state and the robot position at the same time, adds uncovered grid information into a backtracking list, and deletes covered grid points;
step 15: the current iteration number item reaches the maximum iteration number item max Or (b)When, go to step 16; otherwise, iter=iter+1, returning to step 3;
step 16: and (5) outputting the path, and ending.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110824316.2A CN113741416B (en) | 2021-07-21 | 2021-07-21 | Multi-robot full-coverage path planning method based on improved predator prey model and DMPC |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110824316.2A CN113741416B (en) | 2021-07-21 | 2021-07-21 | Multi-robot full-coverage path planning method based on improved predator prey model and DMPC |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113741416A CN113741416A (en) | 2021-12-03 |
| CN113741416B true CN113741416B (en) | 2023-12-26 |
Family
ID=78728867
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110824316.2A Active CN113741416B (en) | 2021-07-21 | 2021-07-21 | Multi-robot full-coverage path planning method based on improved predator prey model and DMPC |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113741416B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114740840A (en) * | 2022-03-21 | 2022-07-12 | 同济大学 | Group robot double-environment area coverage method based on herd foraging behavior |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| CN106843216A (en) * | 2017-02-15 | 2017-06-13 | 北京大学深圳研究生院 | A kind of complete traverse path planing method of biological excitation robot based on backtracking search |
| CN106979785A (en) * | 2017-03-24 | 2017-07-25 | 北京大学深圳研究生院 | A kind of complete traverse path planing method of multi-robot system |
| WO2017173990A1 (en) * | 2016-04-07 | 2017-10-12 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
-
2021
- 2021-07-21 CN CN202110824316.2A patent/CN113741416B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016045615A1 (en) * | 2014-09-25 | 2016-03-31 | 科沃斯机器人有限公司 | Robot static path planning method |
| WO2017173990A1 (en) * | 2016-04-07 | 2017-10-12 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
| CN106843216A (en) * | 2017-02-15 | 2017-06-13 | 北京大学深圳研究生院 | A kind of complete traverse path planing method of biological excitation robot based on backtracking search |
| CN106979785A (en) * | 2017-03-24 | 2017-07-25 | 北京大学深圳研究生院 | A kind of complete traverse path planing method of multi-robot system |
Non-Patent Citations (1)
| Title |
|---|
| 移动机器人全覆盖路径规划算法研究;刘晶;姚维;章玮;;工业控制计算机(第12期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113741416A (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tai et al. | Virtual-to-real deep reinforcement learning: Continuous control of mobile robots for mapless navigation | |
| CN109506655B (en) | Improved ant colony path planning algorithm based on non-uniform modeling | |
| Grigorescu et al. | Neurotrajectory: A neuroevolutionary approach to local state trajectory learning for autonomous vehicles | |
| CN111780777A (en) | Unmanned vehicle route planning method based on improved A-star algorithm and deep reinforcement learning | |
| CN112148008B (en) | Real-time unmanned aerial vehicle path prediction method based on deep reinforcement learning | |
| CN109597425B (en) | Unmanned aerial vehicle navigation and obstacle avoidance method based on reinforcement learning | |
| Tao et al. | SEER: Safe efficient exploration for aerial robots using learning to predict information gain | |
| CN116804879B (en) | Robot path planning framework method for improving dung beetle algorithm and fusing DWA algorithm | |
| Guo et al. | A fusion method of local path planning for mobile robots based on LSTM neural network and reinforcement learning | |
| CN115826586B (en) | Path planning method and system integrating global algorithm and local algorithm | |
| Xue et al. | Multi-agent deep reinforcement learning for UAVs navigation in unknown complex environment | |
| CN113885567B (en) | Collaborative path planning method for multiple unmanned aerial vehicles based on conflict search | |
| CN112484732A (en) | IB-ABC algorithm-based unmanned aerial vehicle flight path planning method | |
| CN115729238A (en) | Dynamic path planning method for autonomous obstacle avoidance of mobile robot | |
| CN113741416B (en) | Multi-robot full-coverage path planning method based on improved predator prey model and DMPC | |
| CN115933637A (en) | Path planning method and device for substation equipment inspection robot and storage medium | |
| Zheng et al. | A hierarchical approach for mobile robot exploration in pedestrian crowd | |
| Katona et al. | Obstacle Avoidance and Path Planning Methods for Autonomous Navigation of Mobile Robot | |
| Chen et al. | STExplorer: A hierarchical autonomous exploration strategy with spatio-temporal awareness for aerial robots | |
| CN116448134B (en) | Vehicle path planning method and device based on risk field and uncertain analysis | |
| Raiesdana | A hybrid method for industrial robot navigation | |
| Shi et al. | Coverage path planning for cleaning robot based on improved simulated annealing algorithm and ant colony algorithm | |
| Liu et al. | Improved gray wolf optimization algorithm integrating A* algorithm for path planning of mobile charging robots | |
| CN110779526A (en) | Path planning method, device and storage medium | |
| Chen et al. | GVD-Exploration: An Efficient Autonomous Robot Exploration Framework Based on Fast Generalized Voronoi Diagram Extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |