CN106708063A - Route planning method for search and rescue robot in chemical disaster scene - Google Patents
Route planning method for search and rescue robot in chemical disaster scene Download PDFInfo
- Publication number
- CN106708063A CN106708063A CN201710172949.3A CN201710172949A CN106708063A CN 106708063 A CN106708063 A CN 106708063A CN 201710172949 A CN201710172949 A CN 201710172949A CN 106708063 A CN106708063 A CN 106708063A
- Authority
- CN
- China
- Prior art keywords
- toxic gas
- path
- grid
- planning method
- rescue robot
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 239000000126 substance Substances 0.000 title claims abstract description 19
- 239000002341 toxic gas Substances 0.000 claims abstract description 51
- 230000002068 genetic effect Effects 0.000 claims abstract description 14
- 239000003016 pheromone Substances 0.000 claims description 17
- 238000009792 diffusion process Methods 0.000 claims description 11
- 238000004387 environmental modeling Methods 0.000 claims description 8
- 239000007789 gas Substances 0.000 claims description 4
- 230000004083 survival effect Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 claims description 2
- 230000007547 defect Effects 0.000 abstract 1
- 210000000349 chromosome Anatomy 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 238000009825 accumulation Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 230000035772 mutation Effects 0.000 description 3
- 241000257303 Hymenoptera Species 0.000 description 2
- 230000004888 barrier function Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 230000007096 poisonous effect Effects 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 210000004709 eyebrow Anatomy 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000000630 rising effect Effects 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
- G05D1/0212—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
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)
- Feedback Control In General (AREA)
Abstract
The invention relates to a route planning method for a search and rescue robot in a chemical disaster scene. The route planning method comprises the following steps: s-1, performing environment modeling on the disaster scene by virtue of a grid method; s-2, finally obtaining an initial optimum route by virtue of a genetic ant colony algorithm; s-3, in each unit time, detecting whether the initial optimum path enters a continuously diffusing toxic gas range or not; s-4, if so, performing route planning again on two points of a line section in the toxic gas range so as to avoid toxic gas; and otherwise, following the current route. The route planning method for the search and rescue robot provided by the invention sets the toxic gas in a dynamic diffusing mode. By detecting and updating the route superposed with the toxic gas region, the defect caused by stationary toxic gas in a conventional model is overcome, so that obtained planned route is relatively safe and reliable.
Description
Technical field
The present invention relates to intelligent robot algorithm field, specially a kind of chemical industry disaster field search and rescue robot path planning
Method.
Background technology
Mobile robot is currently the Typical Representative of artificial intelligence field and field of electromechanical integration, is largely used in calamity
Harmful scene is searched and rescued, but currently all concentrates on mine disaster field.In addition with the progressively growth of China's chemical industry and this
In the past few years chemical industry disaster accident is taken place frequently, and its safety in production receives very big test, and development chemical industry disaster search and rescue robot is compeled
The eyebrows and eyelashes.When chemical industry disaster occurs, toxic gas diffusion produces the region that a personnel cannot pass through, and it searches and rescues technology master
Want difficult point is how rapidly to cook up a best-effort path for safety.
Genetic algorithm is imitated the selection of the Nature population, intersects and become according to the theory of Darwinian evolution " survival of the fittest "
It is different, with of overall importance, randomness and robustness.All of information is all placed in the middle of chromosome in operation, each time iteration
Will once be randomly choosed, be that can obtain by constantly iteration by fitness function constantly specification search direction
Optimal solution.Genetic algorithm can abstract problem from specific field, there is provided a kind of general computation model.
Ant group algorithm is the heuristic search of ant search of food in the middle of natural imitation circle, with concurrency, positive and negative
Feedback property and self-organization, ant can leave a certain amount of pheromones at the path passed by, concentration and the arrival of these pheromones
The distance of impact point is inversely proportional, and ant below has more maximum probability selection concentration path high in selection, forms positive feedback,
Finally cook up an optimal path.
The genetic algorithm initial stage is with the convergence rate for tending to optimal solution speed higher, and ant group algorithm contrast, later stage
The quick rising of convergence rate, has benefited from the accumulation of pheromones, thus both algorithm fusions are provided with the foundation in principle, i.e.,
Shorten ant group algorithm into the time in high-speed convergence stage in later stage using the pheromones accumulation of genetic algorithm early stage, improve algorithm
Overall speed.
The content of the invention
The purpose of the present invention is a kind of chemical industry disaster field search and rescue robot paths planning method of invention, to solve current calculation
The method speed of service is slow, and easily when being walked along path into the technical problem of toxic gas diffusion zone.
In order to solve this technical problem, the invention provides a kind of chemical industry disaster field search and rescue robot path planning side
Method, comprises the following steps:
S-1 carries out environmental modeling to disaster field using Grid Method;
S-2 finally gives a preliminary optimal path using GACA algorithm;
S-3 detects whether preliminary optimal path enters in the constantly toxic gas scope of diffusion in each unit interval;
S-4 to entering 2 points of line segment in the range of toxic gas if so, then re-start path planning to have avoided poison gas
Body, if nothing, continues to use current path.
Further, carrying out environmental modeling using Grid Method to disaster field in the step s-1 includes:
Step s-1-1:Scene is divided into the grid of n × n, wherein accessible grid is 0, there are the lattice of physical obstacles
Son is 1, takes toxic gas when path planning starts and is distributed as toxic gas prime area, and is set to 0.5;
Step s-1-2:For the grid of toxic gas, gas can be diffused into 8 adjacent lattice in setting time per unit
Son.
Further, forming the distribution of initial path pheromones using genetic algorithm in the step s-2 includes:
Step s-2-1:Genetic parameter is set, initial population is generated;
Step s-2-2:Fitness function is set and initial population is evaluated;
Step s-2-3:The operation such as selected initial population, intersected, being made a variation;
Step s-2-4:Detect whether to meet iteration termination condition, s-2-2 is jumped to if being unsatisfactory for and continues this process, if
Satisfaction then terminates iteration, and preceding 30% group of solution of fitness value is converted into the pheromones initial value of ant group algorithm.
s-2-5:Initialize all kinds of parameters, including iterations, each ant number, beginning and end, pheromones sent
Matrix etc.;
s-2-6:Obtain current ant point and go to eight probability of node around, and obtained using wheel disc algorithm next
The point that step is gone to;
s-2-7:Carry out local information element renewal, and go to s-2-6 continuing iteration, all reach home until all ants or
It is absorbed in blind alley;
s-2-8:Carry out global information element renewal, without reach ant do not count, then repeatedly s-2-6 and
S-2-7, until n completes to search for for ant.
Further, in the step s-3 in each unit interval, detect whether preliminary optimal path enters constantly diffusion
Toxic gas scope in method include:
Step s-3-1:The speed of robot and survival personnel escape is taken for v, the length according to preliminary optimal path can be with
Calculate the route that each unit interval passed through;
Step s-3-2:In each unit interval, the diffusion zone of toxic gas is updated, in current slot
Path is compared, and checks whether the beginning and end for overlapping and recording current slot and respective path.
Further, then path planning is re-started to entering 2 points of line segment in the range of toxic gas in the step s-4
Included with avoiding toxic gas:
Step s-4-1:The toxic gas region of current slot is set to 0.5 in Grid Method;
Step s-4-2:Using current slot it is corresponding 2 points as beginning and end, then carry out a step s-2, find
The optimal path of replacement.
The beneficial effects of the invention are as follows the useful information for taking full advantage of genetic algorithm in early stage Rapid Accumulation is plain, it is to avoid
Blindness when ant group algorithm is searched in the early stage, enters directly into and can efficiently using the later stage of pheromones positive feedbacks improve
The speed of service of algorithm, is that the time has been striven in the planning of disaster field rescue path;On the other hand chemical industry disaster is fully taken into account to show
The particularity of field, dynamic dispersal pattern is set to by toxic gas, and detection robot is with survivor along path traveling process
It is central whether to enter into the range of scatter of toxic gas, so as to avoid be easily accessible in legacy paths planning algorithm it is poisonous
The problem of gas zones.
Brief description of the drawings
Fig. 1 is the FB(flow block) of chemical industry disaster field search and rescue robot path planning of the invention.
Fig. 2 is search and rescue robot path planning genetic algorithm flow chart of the invention.
Fig. 3 is search and rescue robot path planning ant group algorithm flow chart of the invention.
Fig. 4 is the schematic diagram of self-recision when path planning of the invention enters toxic gas region.
Specific embodiment
To make the objects, technical solutions and advantages of the present invention clearer, clear and definite, develop simultaneously embodiment pair referring to the drawings
The present invention is further described.Example is served only for the explanation present invention, is not intended to limit the present invention.
Chemical industry disaster field search and rescue robot path planning operation principle of the invention:Make use of genetic algorithm complete in early stage
The advantage of office's search, 30% optimal solution is converted into the initial information element of ant group algorithm, avoids ant group algorithm inefficiency
Initial stage search, enter directly into can efficiently using pheromones positive feedback later stage, ant group algorithm cook up preliminary path it
Afterwards, the path moved in each unit interval is compared with the toxic gas range of scatter of corresponding time period, if there is coincidence
Then the path for this time period plans to avoid toxic gas again.
In a preferred embodiment, a kind of chemical industry disaster field search and rescue robot paths planning method, as shown in figure 1,
Comprise the following steps:
S-1 carries out environmental modeling to disaster field using Grid Method;
S-2 finally gives a preliminary optimal path using GACA algorithm;
S-3 detects whether preliminary optimal path enters in the constantly toxic gas scope of diffusion in each unit interval;
S-4 to entering 2 points of line segment in the range of toxic gas if so, then re-start path planning to have avoided poison gas
Body, if nothing, continues to use current path.
Used as a kind of optional implementation method of Grid Method environmental modeling, the step s-1 uses grid to disaster field
The method that method carries out environmental modeling includes:Global map is divided using grid and to barrier and toxic gas region
Carry out special marking.
Specifically, the Grid Method environmental modeling, will scene be divided into 20 × 20 grid, wherein accessible grid
It is 0, it is 1 to have the grid of physical obstacles, takes toxic gas when path planning starts and be distributed as toxic gas prime area,
And it is set to 0.5;For the grid of toxic gas, setting gas in its time per unit can be diffused into 8 adjacent grid.
As a kind of optional implementation method for generating initial optimal path, as shown in Figure 2 and Figure 3, the step s-2 profits
The method for finally giving a preliminary optimal path with GACA algorithm includes:
Step s-2-1:Genetic parameter is set, initial population is generated;
Population scale n, crossover probability P are setc, mutation probability PmAnd maximum iteration Nmax, by starting point and target
After point is fixed, genetic fragment one by one is formed by randomly choosing point interior in grid, these points are coupled together, formd
One chromosome, i.e. initial path, different chromosomes then constitute initial population.
Step s-2-2:Fitness function is set;
Fitness function is set according to the following formula
F=B- λ1·f1-λ2·f2-λ3·f3
Wherein f1It is path length, f2It is node number, f3It is smoothness, λ1、λ2、λ3It is the coefficient of each variable, B is just
Value;
f1Can be calculated with following formula:
Wherein mjThe point passed through by path;
f2The node number passed through by path;
f3Can be calculated by following formula:
θjDeflection angle between route segment and route segment.
Step s-2-3:Initial population is selected, is intersected, mutation operation;
Selection operation uses elitism strategy back-and-forth method, i.e., contemporary population is completed after an iteration, and fitness function is to new
Individual evaluations of a generation be less than before a generation, just will be by the optimal individual of previous generation with the of future generation worst individuality of equal number
Body is substituted, to ensure that excellent genes are continued;
Crossover operation is intersected using the single-point in random selection crosspoint, i.e., for two chromosomes, randomly choose therein
One gene is swapped;
Mutation operation is substituted according to certain probability using alternative method, i.e. each gene is substituted by new gene.
Step s-2-4:Detect whether to meet iteration termination condition, i.e. iterations more than Nmax, s- is jumped to if being unsatisfactory for
2-2 continues this process, terminates iteration if meeting, and preceding 30% group of solution of fitness value is converted into the information of ant group algorithm
Plain initial value.
Step s-2-5:Initialize all kinds of parameters, including iterations Nc, every time send ant number m, beginning and end,
Pheromone Matrix etc..
Step s-2-6:Obtain current ant point and go to eight probability of node around, and obtained using wheel disc algorithm
The point that next step is gone to, new probability formula is as follows;
Wherein τijT () is giAnd gjBetween pheromone concentration, ηijIt is and giAnd gjAssociated heuristic information, α, β point
Wei not τij(t),ηijWeight parameter, N represent robot be currently able to reach grid, it is clear that a robot at most can only
Having 8 grids can reach, and tabukThen represent the current taboo location sets closed on, including barrier, toxic gas region
And the route passed by before robot.
Step s-2-7:Local updating, and more new route and path length are carried out, and goes to s-3-2 continuation iteration, until
All ants are all reached home or are absorbed in blind alley, and pheromones local updating formula is as follows:
τij=(1- ξ) τij(t)+τ0·ξ;
Wherein 0<ξ<1 is constant, representative information element volatility coefficient.
Step s-2-8:Global information element renewal is carried out, is not counted without the ant for reaching, then repeatedly s-
2-6 and s-2-7, until n completes to search for for ant, the pheromones overall situation more new formula is as follows:
τij(t+1)=(1- ρ) τij(t)+Δτij;
Wherein ρ is pheromones volatility coefficient, and Q is ant through increased pheromone concentration, L laterkT () is currently to search
Shortest path length.
Whether enter a kind of optional implementation method in toxic gas region as inspection planning path, as shown in figure 4, institute
Step s-3 is stated in each unit interval, the method whether optimal path enters in the constantly toxic gas scope of diffusion is detected
Including:
Step s-3-1:The speed that robot is taken with survival personnel escape is v, and the length according to optimal path can be calculated
Go out the route that each unit interval passed through;
That is during t=1, path is OA sections, and during t=2, path is AB sections, and during t=3, path is BT sections.
Step s-3-2:In each unit interval, the diffusion zone of toxic gas is updated, in current slot
Path is compared, and checks whether the beginning and end for overlapping and recording current slot and respective path;
That is during t=1, the scope of toxic gas is middle small square, now misaligned with path;It is poisonous during t=2
Air range is diffused into big square, is now overlapped with path.
As a kind of optional implementation method for re-starting path planning, as shown in figure 4, the step s-4 is to entering
2 points of line segment in the range of toxic gas re-starts path planning to be included with avoiding the method for toxic gas:
Step s-4-1:The toxic gas region of current slot is set to 0.5 in Grid Method;
Will t=2 when toxic gas region correspond to grid matrix in the middle of relevant position mark 0.5;
Step s-4-2:Using 2 points of the line segment as beginning and end, then a step s-2 is carried out, find and substitute most
Shortest path;
To AB, 2 points re-execute step s-2 to s-4, obtain an alternative route, i.e. dotted line in figure.
Finally illustrate, the above embodiments are merely illustrative of the technical solutions of the present invention and it is unrestricted, although with reference to compared with
Good embodiment has been described in detail to the present invention, it will be understood by those within the art that, can be to skill of the invention
Art scheme is modified or equivalent, and without deviating from the objective and scope of technical solution of the present invention, it all should cover at this
In the middle of the right of invention.
Claims (5)
1. a kind of chemical industry disaster field search and rescue robot paths planning method, it is characterised in that:The paths planning method includes
Following steps:
S-1 carries out environmental modeling to disaster field using Grid Method;
S-2 finally gives a preliminary optimal path using GACA algorithm;
S-3 detects whether preliminary optimal path enters in the constantly toxic gas scope of diffusion in each unit interval;
S-4 if so, then to enter toxic gas in the range of 2 points of line segment re-start path planning to avoid toxic gas, if
Nothing, then continue to use current path.
2. chemical industry disaster field search and rescue robot paths planning method according to claim 1, it is characterised in that the step
Carrying out environmental modeling with Grid Method to disaster field in s-1 includes:
s-1-1:According to the size of actual environment, scene is divided into the grid of n × n, and to accessible, physical obstacles and
The grid of toxic gas does different marks;
s-1-2:For toxic gas region, set gas in each toxic gas grid time per unit can be diffused into it is adjacent
8 grid.
3. chemical industry disaster field search and rescue robot paths planning method according to claim 1, it is characterised in that the step
A preliminary optimal path is finally given in s-2 using GACA algorithm to comprise the following steps:
s-2-1:Genetic algorithm is performed, and preceding 30% group of solution of fitness value is converted into the pheromones initial value of ant group algorithm;
s-2-2:The pheromones initial value given using genetic algorithm, performs ant group algorithm, searches out a preliminary optimal path.
4. chemical industry disaster field search and rescue robot paths planning method according to claim 1, it is characterised in that the step
In s-3 in each unit interval, the method whether detection optimal path enters in the constantly toxic gas scope of diffusion includes
Following steps:
s-3-1:The speed that robot is taken with survival personnel escape is v, and each list can be calculated according to preliminary optimal path
The path that the position time is advanced;
s-3-2:In each unit interval, the diffusion zone of toxic gas is updated, carried out with the path in current slot
Compare, check whether the beginning and end for overlapping and recording current slot and respective path.
5. chemical industry disaster field search and rescue robot paths planning method according to claim 1, it is characterised in that the step
Then include following step to avoid toxic gas to re-starting path planning into 2 points of line segment in the range of toxic gas in s-4
Suddenly:
s-4-1:The toxic gas region of current slot is set to 0.5 in grid;
s-4-2:Using current slot it is corresponding 2 points as beginning and end, then carry out a step s-2, find and substitute most
Shortest path.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710172949.3A CN106708063A (en) | 2017-03-22 | 2017-03-22 | Route planning method for search and rescue robot in chemical disaster scene |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710172949.3A CN106708063A (en) | 2017-03-22 | 2017-03-22 | Route planning method for search and rescue robot in chemical disaster scene |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106708063A true CN106708063A (en) | 2017-05-24 |
Family
ID=58887244
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710172949.3A Pending CN106708063A (en) | 2017-03-22 | 2017-03-22 | Route planning method for search and rescue robot in chemical disaster scene |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106708063A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109299831A (en) * | 2018-10-31 | 2019-02-01 | 浙江中烟工业有限责任公司 | A kind of best-effort path of expanded cut tobacco workshop section instructs system |
WO2020107583A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技(深圳)有限公司 | Improved ant colony algorithm-based path planning method, apparatus, terminal and medium |
CN111240326A (en) * | 2020-01-15 | 2020-06-05 | 重庆邮电大学 | Mobile robot path planning method based on heterogeneous double-colony ant colony algorithm |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101917776A (en) * | 2010-07-27 | 2010-12-15 | 上海中为智能机器人有限公司 | Autonomous intelligent mine detection multi-robot wireless communication system based on wireless network |
CN102682341A (en) * | 2012-04-30 | 2012-09-19 | 山西潞安环保能源开发股份有限公司常村煤矿 | System and method for managing coal mine emergency rescue command information |
CN103092204A (en) * | 2013-01-18 | 2013-05-08 | 浙江大学 | Mixed robot dynamic path planning method |
CN103489042A (en) * | 2013-09-17 | 2014-01-01 | 中国科学院深圳先进技术研究院 | Method for optimizing disaster emergency decision system path |
CN104713549A (en) * | 2015-04-03 | 2015-06-17 | 兖州煤业股份有限公司 | Under-well risk-avoiding navigation method and under-well risk-avoiding navigation device |
CN105509749A (en) * | 2016-01-04 | 2016-04-20 | 江苏理工学院 | Mobile robot path planning method and system based on genetic ant colony algorithm |
CN106225788A (en) * | 2016-08-16 | 2016-12-14 | 上海理工大学 | The robot path planning method of ant group algorithm is expanded based on path |
CN106444755A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Mobile robot path planning method and system based on improved genetic algorithm |
-
2017
- 2017-03-22 CN CN201710172949.3A patent/CN106708063A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101917776A (en) * | 2010-07-27 | 2010-12-15 | 上海中为智能机器人有限公司 | Autonomous intelligent mine detection multi-robot wireless communication system based on wireless network |
CN102682341A (en) * | 2012-04-30 | 2012-09-19 | 山西潞安环保能源开发股份有限公司常村煤矿 | System and method for managing coal mine emergency rescue command information |
CN103092204A (en) * | 2013-01-18 | 2013-05-08 | 浙江大学 | Mixed robot dynamic path planning method |
CN103489042A (en) * | 2013-09-17 | 2014-01-01 | 中国科学院深圳先进技术研究院 | Method for optimizing disaster emergency decision system path |
CN104713549A (en) * | 2015-04-03 | 2015-06-17 | 兖州煤业股份有限公司 | Under-well risk-avoiding navigation method and under-well risk-avoiding navigation device |
CN105509749A (en) * | 2016-01-04 | 2016-04-20 | 江苏理工学院 | Mobile robot path planning method and system based on genetic ant colony algorithm |
CN106225788A (en) * | 2016-08-16 | 2016-12-14 | 上海理工大学 | The robot path planning method of ant group algorithm is expanded based on path |
CN106444755A (en) * | 2016-09-22 | 2017-02-22 | 江苏理工学院 | Mobile robot path planning method and system based on improved genetic algorithm |
Non-Patent Citations (1)
Title |
---|
周旺平,等: "化工灾害搜救机器人路径规划研究" * |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109299831A (en) * | 2018-10-31 | 2019-02-01 | 浙江中烟工业有限责任公司 | A kind of best-effort path of expanded cut tobacco workshop section instructs system |
CN109299831B (en) * | 2018-10-31 | 2021-05-11 | 浙江中烟工业有限责任公司 | Escape path guidance system for expanded tobacco shred workshop section |
WO2020107583A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技(深圳)有限公司 | Improved ant colony algorithm-based path planning method, apparatus, terminal and medium |
CN111240326A (en) * | 2020-01-15 | 2020-06-05 | 重庆邮电大学 | Mobile robot path planning method based on heterogeneous double-colony ant colony algorithm |
CN111240326B (en) * | 2020-01-15 | 2023-05-16 | 重庆邮电大学 | Mobile robot path planning method based on heterogeneous double-population ant colony algorithm |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104361178B (en) | A kind of indoor evacuation emulation optimization method driving cellular ant group algorithm based on potential energy | |
CN106225788B (en) | The robot path planning method of ant group algorithm is expanded based on path | |
CN104008417B (en) | Set up skyscraper evacuating personnel bioluminescence particle swarm optimization algorithm model method | |
CN104317293B (en) | City rescue intelligent agent dynamic path planning method based on improved ant colony algorithm | |
CN106323293B (en) | Two groups of multidirectional robot path planning methods based on multiple target search | |
CN102288192B (en) | Multi-robot path planning method based on Ad-Hoc network | |
CN106708063A (en) | Route planning method for search and rescue robot in chemical disaster scene | |
CN103489042B (en) | A kind of method of calamity emergency decision system path optimization | |
CN105892480A (en) | Self-organizing method for cooperative scouting and hitting task of heterogeneous multi-unmanned-aerial-vehicle system | |
Zhao et al. | An evacuation simulation method based on an improved artificial bee colony algorithm and a social force model | |
CN108180914A (en) | A kind of method for planning path for mobile robot improved based on ant colony with despiking | |
CN113625716B (en) | Multi-agent dynamic path planning method | |
CN112146673A (en) | Expressway multi-point collaborative rescue path planning method based on improved ant colony algorithm | |
CN106650991A (en) | Path planning based on analog annealing ant colony algorithm | |
CN111784079A (en) | Unmanned aerial vehicle path planning method based on artificial potential field and ant colony algorithm | |
CN104392283A (en) | Artificial fish swarm algorithm based traffic route searching method | |
CN109186619A (en) | A kind of intelligent navigation algorithm based on real-time road | |
CN110045738A (en) | Robot path planning method based on ant group algorithm and Maklink figure | |
CN109357678A (en) | A kind of multiple no-manned plane paths planning method based on heterogeneousization dove colony optimization algorithm | |
CN110334838A (en) | AGV trolley coordinated dispatching method and system based on ant group algorithm and genetic algorithm | |
CN109299778A (en) | A kind of calculation method of the RCRSS rescue map subregion based on cuckoo searching algorithm | |
CN115545359B (en) | Dynamic intelligent evacuation method and device for complex building fire | |
CN113917925A (en) | Mobile robot path planning method based on improved genetic algorithm | |
CN115355922A (en) | Travel path planning method and system based on improved ant colony algorithm | |
CN108241911A (en) | A kind of Site Selection Method of Distribution Center for optimization algorithm of being looked for food based on bacterium |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170524 |
|
RJ01 | Rejection of invention patent application after publication |