CN112947437A - Improved ant colony algorithm for traversing patrol in security robot building - Google Patents
Improved ant colony algorithm for traversing patrol in security robot building Download PDFInfo
- Publication number
- CN112947437A CN112947437A CN202110160597.6A CN202110160597A CN112947437A CN 112947437 A CN112947437 A CN 112947437A CN 202110160597 A CN202110160597 A CN 202110160597A CN 112947437 A CN112947437 A CN 112947437A
- Authority
- CN
- China
- Prior art keywords
- city
- patrol
- colony algorithm
- ant
- ant colony
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 44
- 238000004364 calculation method Methods 0.000 claims abstract description 12
- 239000003016 pheromone Substances 0.000 claims description 25
- 239000011159 matrix material Substances 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 6
- 125000004122 cyclic group Chemical group 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 6
- 238000012546 transfer Methods 0.000 claims description 6
- 241000257303 Hymenoptera Species 0.000 claims description 4
- 238000013461 design Methods 0.000 claims description 3
- 239000005712 elicitor Substances 0.000 claims description 3
- PHTXVQQRWJXYPP-UHFFFAOYSA-N ethyltrifluoromethylaminoindane Chemical compound C1=C(C(F)(F)F)C=C2CC(NCC)CC2=C1 PHTXVQQRWJXYPP-UHFFFAOYSA-N 0.000 claims description 3
- 238000004088 simulation Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 230000007123 defense Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000009024 positive feedback mechanism Effects 0.000 description 1
- 238000011160 research Methods 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
- G05D1/02—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
- G05D1/0276—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)
- 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)
- Manipulator (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses an improved ant colony algorithm for traversing patrol in a security robot building, which analyzes the characteristics of patrol of indoor floors, takes points of a path needing to be patrolled, calls the number of the taken points as the number of cities which the ant colony algorithm needs to traverse, calls each point as a city, determines the number M of the cities in the ant colony algorithm, and calculates the number of the cities in the ant colony algorithmiAnd cityjBefore calculating the probability of ant selecting the path, a judgment statement is added to ensure that only the point with the same abscissa or ordinate as the current calculation point is taken.
Description
Technical Field
The invention relates to an improved ant colony algorithm for traversing and patrolling in a security robot building, and belongs to the technical field of patrolling of robots.
Background
The traditional security system is realized by people's air defense and object defense. With the problems of increased population aging, soaring labor cost, high loss rate of security personnel and the like, the security robot is difficult to adapt to the modern security requirements, and the security robot industry is in a new opportunity of developing. The security robot is still in a starting stage, but under the huge security market demand, the security robot has wide development potential and future prospect. Because the ant colony algorithm adopts a positive feedback mechanism, the search process is continuously converged and finally approaches to an optimal solution, and the method is widely applied to solving the path planning problem of the robot. The security patrol robot is different from a common robot, and besides conventional path planning, the security patrol robot needs to check some dead roads so as to achieve the purpose of traversing patrol.
As shown in fig. 1, the solid line is a main corridor, the dotted line is a channel, and the left and right sides of the main corridor and the channel are rooms; the other white areas are other obstacles such as walls. Under the conventional ant colony algorithm, in order to ensure that both the main corridor and the channel can walk through, the method of fig. 2 is used for taking points, and the security patrol robot moves along the shortest path. In the actual patrol process of the building, the shortest paths often need to be through the wall, namely, the shortest paths do not walk along the straight line of the corridor. The security patrol robot cannot pass through the wall; and the conventional ant colony algorithm cannot process the blind road, and the security robot needs to go through patrol right.
The point is taken according to the mode of fig. 2, and as a result of simulation according to a conventional ant colony algorithm, a simulation result graph has a diagonal line, because the ant colony algorithm does not go around the end of the channel and can only go out of the end of the channel along the diagonal line direction after the robot goes to the dead road at the end of the channel, and the path of the diagonal line is that the robot needs to go through the wall for a floor, which is not in accordance with the objective fact, so that improvement is needed.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides an improved ant colony algorithm for traversing and patrolling in a security robot building.
In order to achieve the above object, the present invention provides an improved ant colony algorithm for traversal patrol in a security robot building, which analyzes the characteristics of indoor floor patrol, takes points for a path to be patrolled to determine the city number M in the ant colony algorithm, and preferentially analyzes the characteristics of indoor floor patrol, comprising the following steps: the patrol mode of the security robot is to patrol in a straight line, only change the direction at a turning position, and no oblique line can appear in the patrol path of the security robot, and if the oblique line appears in the patrol path of the security robot, the security robot is regarded as passing through the wall.
Preferentially, taking points for the path needing patrol to determine the city number M in the ant colony algorithm comprises the following steps:
the real part is a main corridor, the dotted part is a plurality of channels, the white area is an obstacle, the main corridor and the channels are subjected to point extraction, the number of the points extraction is called the number of cities which need to be traversed by the ant colony algorithm, and each point is called a city;
taking points in the channel based on a conventional ant colony algorithm;
adding a point which has the same abscissa as the point taken in the channel and the ordinate of which is in the channel before turning at the T-shaped bend of each channel, wherein the point is named as a turning point, and the robot turns around when patrolling the end of a certain channel, turns the direction at the turning point and enters another channel;
the patrol path of the security robot is optimized in distance calculation, and the optimized distance formula is as follows:
wherein d isi,jIs the distance, x, between any city i and city jiIs the abscissa, x, of city ijIs the ordinate, y, of city jiIs the abscissa of city i, yjIs the ordinate of city j.
Preferably, let τ beij(t) is the pheromone content between city i and city j, the initial time τi,j(0) C is a constant, assumed to be in [ t, t + n [ ]]All ants finish one round trip at the moment, n is a constant, and the pheromone content between the city i and the city j at the moment of t + n is as follows:
wherein: ρ represents a time period [ t, t + n ]]The volatilization coefficient of pheromone content, namely rho value range (0, 1), then (1-rho) represents rhoThe remaining amount of (c);
and (3) expressing the pheromone content of the kth ant between the city i and the city j in the iteration, and calculating the method:
wherein: q is the pheromone addition factor, LkRepresenting the path of ant k in the circum-natal.
Preferentially, a limiting condition is added to the original distance calculation mode based on the distance formula, the limiting condition is that the abscissa of two points is the same or the ordinate is the same, the distance is calculated according to the formula (1), otherwise, the distance is infinite;
for the probability that ant k transfers from city i to city j at time t, the formula for calculating the probability is as follows:
wherein: j. the design is a squarek(i) Represents the set of cities where ant k can choose to go, set Jk(i) The elements in the system only comprise points with the same horizontal coordinates or vertical coordinates as the urban points walking, so that oblique lines are avoided; α is the degree of importance of the pheromone; β is the degree of importance of the elicitor; etai,j(t) is a heuristic, representing the expected degree of ant transfer from city i to city j,
τi,s(t) is the pheromone content between city i and city s, ηi,s(t) is a heuristic factor which is,
from the above formula
It can be known that the higher the pheromone content of the city i and the city j is, the higher the probability that the ant selects the path isThe larger the distance between city i and city j, the smaller the heuristic factor, and the smaller the probability that the ant will select the path.
Preferably, the solution specifically in the ant colony algorithm is: a judgment statement is added before the probability of the ant selecting the path is calculated to ensure that only the point with the same abscissa or ordinate as the currently calculated point is taken,
such calculation results change the dimension of the cyclic matrix, and thus the cyclic matrix does not conform to the previous matrix dimension, and the original set J still remains without satisfying the above-mentioned limitationk(i) To which the value is changed from 0 to the original value
One-tenth of the above, the dimension of the previous matrix is preserved, so that the probability that the point is selected is far lower than the point meeting the above-mentioned constraint.
The invention achieves the following beneficial effects:
the invention overcomes the defect that the channel can only be taken out along the oblique line direction in the prior art, the oblique line path is the path of the robot which needs to walk through the wall for the floor, and the invention does not accord with the objective fact.
Drawings
FIG. 1 is a floor plan of a first embodiment of the present invention;
FIG. 2 is a conventional floor plot according to a first embodiment of the present invention;
fig. 3 is a plot diagram of a floor use optimization method according to a first embodiment of the present invention;
FIG. 4 is a diagram of simulation results of a conventional ant colony algorithm;
FIG. 5 is a diagram of simulation results using only optimized punctuation and distance operations;
FIG. 6 is a diagram of simulation results using only the set of updated cities;
fig. 7 is a simulation result diagram of the operations of updating the city set, optimizing the punctuations and distances according to the first embodiment of the present invention.
Detailed Description
The following examples are only for illustrating the technical solutions of the present invention more clearly, and the protection scope of the present invention is not limited thereby.
An improved ant colony algorithm for traversing patrol in a security robot building analyzes the characteristics of patrol of indoor floors, takes points of paths needing to be patrolled to determine the number M of cities in the ant colony algorithm,
preferably, the characteristics of the indoor floor patrol are analyzed, and the method comprises the following steps: the patrol mode of the security robot is to patrol in a straight line, only change the direction at a turning position, and no oblique line can appear in the patrol path of the security robot, and if the oblique line appears in the patrol path of the security robot, the security robot is regarded as passing through the wall.
Preferentially, taking points for the path needing patrol to determine the city number M in the ant colony algorithm comprises the following steps:
the real part is a main corridor, the dotted part is a plurality of channels, the white area is an obstacle, the main corridor and the channels are subjected to point extraction, the number of the points extraction is called the number of cities which need to be traversed by the ant colony algorithm, and each point is called a city;
taking points in the channel based on a conventional ant colony algorithm;
adding a point which has the same abscissa as the point taken in the channel and the ordinate of which is in the channel before turning at the T-shaped bend of each channel, wherein the point is named as a turning point, and the robot turns around when patrolling the end of a certain channel, turns the direction at the turning point and enters another channel; the robot can be smoothly turned around when running to a dead road, the patrol path of the security robot is optimized in distance calculation, and the optimized distance formula is as follows:
wherein d isi,jIs the distance, x, between any city i and city jiIs the abscissa, x, of city ijIs the ordinate, y, of city jiIs the abscissa of city i, yjIs the ordinate of city j.
Preferably, let τ beij(t) is the pheromone content between city i and city j, the initial time τi,j(0) C is a constant, assumed to be in [ t, t + n [ ]]All ants finish one round trip at the moment, n is a constant, and the pheromone content between the city i and the city j at the moment of t + n is as follows:
wherein: ρ represents a time period [ t, t + n ]]The volatilization coefficient of pheromone content, namely rho value range (0, 1), then (1-rho) represents the residual rho;
and (3) expressing the pheromone content of the kth ant between the city i and the city j in the iteration, and calculating the method:
wherein: q is the pheromone addition factor, LkRepresenting the path of ant k in the circum-natal.
In actual calculation, infinity can influence subsequent judgment results, one hundred million numbers are used for replacing infinity, the point of an operation result is thousands of orders of magnitude, the hundred million orders of magnitude are far greater than thousands of orders of magnitude, and the result is feasible. The results of the simulation performed according to the conventional ant colony algorithm for the points thus obtained are shown in fig. 5. It can be seen that although the algorithm results in a situation that a part of blue paths can go to a 'dead road', oblique paths still exist, and the robot still needs to walk through the wall.
Preferentially, a limiting condition is added to the original distance calculation mode based on the distance formula, the limiting condition is that the abscissa of two points is the same or the ordinate is the same, the distance is calculated according to the formula (1), otherwise, the distance is infinite;
for the probability that ant k transfers from city i to city j at time t, the formula for calculating the probability is as follows:
wherein: j. the design is a squarek(i) Represents the set of cities where ant k can choose to go, set Jk(i) The elements in the system only comprise points with the same horizontal coordinates or vertical coordinates as the urban points walking, so that oblique lines are avoided; α is the degree of importance of the pheromone; β is the degree of importance of the elicitor; etai,j(t) is a heuristic, representing the expected degree of ant transfer from city i to city j,
τi,s(t) is the pheromone content between city i and city s, ηi,s(t) is a heuristic factor which is,
from the above formula
It can be known that the higher the pheromone content of the city i and the city j is, the higher the probability that the ant selects the path is, and the larger the distance between the city i and the city j is, the smaller the heuristic factor is, and the lower the probability that the ant selects the path is. Preferably, the solution specifically in the ant colony algorithm is: a judgment statement is added before the probability of the ant selecting the path is calculated to ensure that only the point with the same abscissa or ordinate as the currently calculated point is taken,
such calculation results change the dimension of the cyclic matrix, and thus the cyclic matrix does not conform to the previous matrix dimension, and the original set J still remains without satisfying the above-mentioned limitationk(i) A point of (1), to which is assignedValue changes from 0 to original assignment
One-tenth of the above, the dimension of the previous matrix is preserved, so that the probability that the point is selected is far lower than the point meeting the above-mentioned constraint.
The simulation result with only the optimized city set is shown in fig. 6, and it can be seen that the walking path of the robot no longer has oblique lines, but the robot has another "wall-through" condition and longitudinally crosses the white area between the solid lines.
Finally, the simulation result of updating the city set and optimizing the punctuations and distance calculation is shown in fig. 7, the walking path of the robot has no oblique line or a straight line through the wall similar to fig. 6, and the shortest path is smaller than the shortest paths of fig. 5 and 6, which shows that the optimization algorithm of the invention is feasible.
Points in the channel are taken based on the conventional ant colony algorithm, see the literature:
[1] the ant colony algorithm principle and its application [ M ]. beijing: science publishers 2005.
[1] Plum soldier courage, chengyang, plum research, ant colony algorithm and its application [ M ]. harbin: harbin university of Industrial university Press 2004.
The above description is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, several modifications and variations can be made without departing from the technical principle of the present invention, and these modifications and variations should also be regarded as the protection scope of the present invention.
Claims (6)
1. An improved ant colony algorithm for traversing patrol in a security robot building is characterized in that the characteristics of indoor floor patrol are analyzed, points are taken for a path needing patrol, the number of the points taken is called as the number of cities needing to be traversed by the ant colony algorithm, each point is called as a city, the number M of the cities in the ant colony algorithm is determined, the pheromone content between the city i and the city j is calculated, and a judgment statement is added before the probability that ants select the path is calculated to ensure that only the points with the same horizontal coordinates or vertical coordinates as the current calculated points are taken.
2. The improved ant colony algorithm for traversal patrols in a security robot building as claimed in claim 1, wherein analyzing the characteristics of indoor floor patrols comprises the following steps: the patrol mode of the security robot is to patrol in a straight line, only change the direction at a turning position, and no oblique line can appear in the patrol path of the security robot, and if the oblique line appears in the patrol path of the security robot, the security robot is regarded as passing through the wall.
3. The improved ant colony algorithm for traversal patrol in a security robot building as claimed in claim 1, wherein the step of taking points of the path to be patrolled to determine the number of cities M in the ant colony algorithm comprises the steps of:
the real part is a main corridor, the dotted part is a plurality of channels, the white area is an obstacle, the main corridor and the channels are subjected to point extraction, and the number of the point extraction is called as the number of cities which need to be traversed by the ant colony algorithm;
taking points in the channel based on a conventional ant colony algorithm;
adding a point which has the same abscissa as the point taken in the channel and the ordinate of which is in the channel before turning at the T-shaped bend of each channel, wherein the point is named as a turning point, and the robot turns around when patrolling the end of a certain channel, turns the direction at the turning point and enters another channel;
the patrol path of the security robot is optimized in distance calculation, and the optimized distance formula is as follows:
wherein d isi,jIs the distance, x, between any city i and city jiIs the abscissa, x, of city ijIs the ordinate, y, of city jiIs the abscissa of city i, yjIs the ordinate of city j.
4. The improved ant colony algorithm for traversal patrol in the building of the security robot as claimed in claim 3, wherein let τij(t) is the pheromone content between city i and city j, the initial time τi,j(0) C is a constant, assumed to be in [ t, t + n [ ]]All ants finish one round trip at the moment, n is a constant, and the pheromone content between the city i and the city j at the moment of t + n is as follows:
wherein: ρ represents a time period [ t, t + n ]]The volatilization coefficient of pheromone content, namely rho value range (0, 1), then (1-rho) represents the residual rho;
and (3) expressing the pheromone content of the kth ant between the city i and the city j in the iteration, and calculating the method:
wherein: q is the pheromone addition factor, LkRepresenting the path of ant k in the circum-natal.
5. The improved ant colony algorithm for traversing patrol in a security robot building as claimed in claim 4, wherein a restriction condition is added to the original distance calculation mode based on the distance formula, the restriction condition is that the distance is calculated according to the formula (1) when the abscissa and the ordinate of the two points are the same or the ordinate of the two points are the same, otherwise, the distance is infinite;
for the probability that ant k transfers from city i to city j at time t, the formula for calculating the probability is as follows:
wherein: j. the design is a squarek(i) Represents the set of cities where ant k can choose to go, set Jk(i) The elements in the system only comprise points with the same horizontal coordinates or vertical coordinates as the urban points walking, so that oblique lines are avoided; α is the degree of importance of the pheromone; β is the degree of importance of the elicitor; etai,j(t) is a heuristic, representing the expected degree of ant transfer from city i to city j,
τi,s(t) is the pheromone content between city i and city s, ηi,s(t) is a heuristic factor which is,
from the above formula
It can be known that the higher the pheromone content of the city i and the city j is, the higher the probability that the ant selects the path is, and the larger the distance between the city i and the city j is, the smaller the heuristic factor is, and the lower the probability that the ant selects the path is.
6. The improved ant colony algorithm for traversing patrol in a security robot building as claimed in claim 5, wherein the solution in the ant colony algorithm is: a judgment statement is added before the probability of the ant selecting the path is calculated to ensure that only the point with the same abscissa or ordinate as the currently calculated point is taken,
such calculation results change the dimension of the cyclic matrix, and thus the cyclic matrix does not conform to the previous matrix dimension, and the original set J still remains without satisfying the above-mentioned limitationk(i) To which the value is changed from 0 to the original value
One-tenth of the above, the dimension of the previous matrix is preserved, so that the probability that the point is selected is far lower than the point meeting the above-mentioned constraint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160597.6A CN112947437B (en) | 2021-02-05 | 2021-02-05 | Improved ant colony algorithm for traversing patrol in security robot building |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110160597.6A CN112947437B (en) | 2021-02-05 | 2021-02-05 | Improved ant colony algorithm for traversing patrol in security robot building |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112947437A true CN112947437A (en) | 2021-06-11 |
| CN112947437B CN112947437B (en) | 2022-07-19 |
Family
ID=76242432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110160597.6A Active CN112947437B (en) | 2021-02-05 | 2021-02-05 | Improved ant colony algorithm for traversing patrol in security robot building |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112947437B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872432A (en) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | Ant colony optimization method by introducing curiosity factor |
| CN104317293A (en) * | 2014-09-19 | 2015-01-28 | 南京邮电大学 | City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm |
| WO2016095692A1 (en) * | 2014-12-15 | 2016-06-23 | 江南大学 | Method for improving ant colony optimization sensor-network cluster head |
| CN105717926A (en) * | 2015-11-09 | 2016-06-29 | 江苏理工学院 | Mobile robot traveler optimization method based on improved ant colony algorithm |
| CN110989612A (en) * | 2019-12-17 | 2020-04-10 | 哈工大机器人（合肥）国际创新研究院 | Robot path planning method and device based on ant colony algorithm |
-
2021
- 2021-02-05 CN CN202110160597.6A patent/CN112947437B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101872432A (en) * | 2010-05-21 | 2010-10-27 | 杭州电子科技大学 | Ant colony optimization method by introducing curiosity factor |
| CN104317293A (en) * | 2014-09-19 | 2015-01-28 | 南京邮电大学 | City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm |
| WO2016095692A1 (en) * | 2014-12-15 | 2016-06-23 | 江南大学 | Method for improving ant colony optimization sensor-network cluster head |
| CN105717926A (en) * | 2015-11-09 | 2016-06-29 | 江苏理工学院 | Mobile robot traveler optimization method based on improved ant colony algorithm |
| CN110989612A (en) * | 2019-12-17 | 2020-04-10 | 哈工大机器人（合肥）国际创新研究院 | Robot path planning method and device based on ant colony algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112947437B (en) | 2022-07-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105426992B (en) | Mobile robot traveler optimization method | |
| CN104298239B (en) | A kind of indoor mobile robot strengthens map study paths planning method | |
| CN113821029B (en) | Path planning method, device, equipment and storage medium | |
| CN110147099A (en) | A kind of multiple no-manned plane collaboratively searching method based on improvement dove group's optimization | |
| CN108413976A (en) | A kind of climbing robot intelligence paths planning method and system towards multi-state | |
| CN109828578B (en) | Instrument inspection robot optimal route planning method based on YOLOv3 | |
| CN114167865B (en) | Robot path planning method based on countermeasure generation network and ant colony algorithm | |
| CN109186619B (en) | Intelligent navigation algorithm based on real-time road condition | |
| CN104317293A (en) | City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm | |
| CN114815802A (en) | Unmanned overhead traveling crane path planning method and system based on improved ant colony algorithm | |
| CN110207706A (en) | A kind of automatic homing chair path planning algorithm based on grating map | |
| CN112330068A (en) | Transformer substation power transmission line planning method based on ant colony algorithm and geographic information system | |
| CN114967680B (en) | Mobile robot path planning method based on ant colony algorithm and convolutional neural network | |
| CN114089760A (en) | AGV path planning method based on hybrid ant colony algorithm | |
| CN115355922A (en) | Travel path planning method and system based on improved ant colony algorithm | |
| CN110095788A (en) | A kind of RBPF-SLAM improved method based on grey wolf optimization algorithm | |
| CN112950934A (en) | Road congestion reason identification method | |
| CN110263905A (en) | Robot localization based on firefly optimized particle filter and build drawing method and device | |
| CN111524345B (en) | Induction control method for multi-objective optimization under constraint of real-time queuing length of vehicle | |
| CN112947437B (en) | Improved ant colony algorithm for traversing patrol in security robot building | |
| CN113156964A (en) | Unmanned ground vehicle path planning method based on improved dynamic window method | |
| CN109902391B (en) | Oil gas pipeline planning method based on random volatilization coefficient ant colony algorithm | |
| CN117711173A (en) | Vehicle path planning method and system based on reinforcement learning | |
| CN112539751A (en) | Robot path planning method | |
| CN117522078A (en) | Method and system for planning transferable tasks under unmanned system cluster environment coupling |
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 |