CN115438860A - Multi-agent path planning method based on evolutionary algorithm - Google Patents
Multi-agent path planning method based on evolutionary algorithm Download PDFInfo
- Publication number
- CN115438860A CN115438860A CN202211085630.4A CN202211085630A CN115438860A CN 115438860 A CN115438860 A CN 115438860A CN 202211085630 A CN202211085630 A CN 202211085630A CN 115438860 A CN115438860 A CN 115438860A
- Authority
- CN
- China
- Prior art keywords
- path
- agent
- conflict
- evolutionary algorithm
- executing
- 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 48
- 230000003044 adaptive effect Effects 0.000 claims abstract description 6
- 230000035772 mutation Effects 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 230000013011 mating Effects 0.000 claims description 3
- 238000010845 search algorithm Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a path planning method, in particular to a multi-agent path planning method based on an evolutionary algorithm, which comprises the following implementation steps: A. calculating an optimal single agent path candidate node; B. constructing an evolutionary algorithm initial population; C. evaluating the adaptive value of individuals in the population; D. executing a selection operator; E. executing a crossover operator; F. executing a mutation operator; G. executing a conflict search operation; H. executing conflict resolution operation; I. performing an archiving update operation; J. when the stop condition is met, the best individual in the archive, i.e., the conflict-free and lowest cost set of multi-agent paths, is provided. The invention adopts the evolutionary algorithm to plan the conflict-free multi-agent path set in a heuristic manner, has high solving speed and high calculation efficiency, adopts the population-based evolutionary algorithm to search a plurality of groups of multi-agent path sets simultaneously, has less possibility of the algorithm falling into local optimum, and can continuously reduce the cost of the multi-agent path set within controllable time.
Description
Technical Field
The invention relates to a path planning method, in particular to a multi-agent path planning method based on an evolutionary algorithm, and belongs to the technical field of path planning.
Background
Multi-agent path planning is one of the main research contents of path planning. The single agent path is a grid map node sequence from a start location and an end location node; multi-agent path planning consists of a set of paths for individual agents, requiring that no conflicts exist between the sets of paths for the agents.
The traditional method for solving the problem of multi-agent path planning mainly comprises a single-agent path cooperation method, a multi-agent path planning method based on priority searching and a multi-agent path planning method based on conflict searching. In the single-agent path cooperation method, A is commonly used as an efficient heuristic single-agent path planning method, and all nodes of a plurality of agents are synchronously expanded along the optimal path of the single agent so as to obtain a conflict-free path. However, as the number of the agents and the map space increase, the a-algorithm search space increases exponentially, so that the method is only suitable for solving the problem of the multi-agent path with a small scale, and the method is incomplete and cannot guarantee optimality. The multi-agent path planning method based on priority search assigns priorities to agents, low-priority individuals avoid conflicts with high-priority agents, and the method is incomplete and cannot guarantee optimality. A multi-agent path planning method based on conflict search is a mainstream multi-agent path planning method, and a conflict tree is constructed by adopting two layers of alternative path planning. Path conflicts among a plurality of agents are detected in a high-level search, and paths of single agents meeting the constraint are re-planned in a low-level search. If a conflict is detected at a high level, the lower level nodes are expanded and constraints are added. And selecting the node with the minimum path cost for expansion by adopting a selection method with the optimal path cost priority each time. And alternately searching by the high-level algorithm and the low-level algorithm until the conflict-free child nodes are expanded, namely the finally found optimal conflict-free scheme is obtained. The conflict search based approach is complete and can guarantee optimality. Because the cost of the optimal path set cannot be obtained, the optimal priority search mode greedy expansion constraint node can ensure the optimality of the feasible path set. However, this approach has two major problems: (1) Although the optimality of finding a conflict-free path set can be guaranteed, with the increase of the number of agents and the problem scale, the execution time of the algorithm cannot be guaranteed, namely, the usable path set is returned within an acceptable time, which is a bottleneck problem of expanding to practical application; (2) According to the method, the conflict is resolved in an incremental manner, each node in the conflict tree only resolves one conflict, and N nodes need to be expanded when each conflict involving N agents is resolved, so that a large amount of computing memory is required to be occupied for storing the conflict tree structure, local optimization is easy to happen, and a large amount of nodes are expanded on invalid branches.
The traditional method is suitable for the problems of less intelligent agent quantity and smaller map scale, and the calculation complexity is too high in the problems of more intelligent agents and larger map scale, so that a conflict-free intelligent agent path set can be drawn out in an acceptable time without regulation.
The present invention has been made in view of this situation.
Disclosure of Invention
The present invention aims to solve the above problems and provide a multi-agent path planning method based on an evolutionary algorithm.
The invention realizes the aim through the following technical scheme, and a multi-agent path planning method based on an evolutionary algorithm comprises the following implementation steps:
A. calculating an optimal single agent path candidate node;
B. constructing an evolutionary algorithm initial population;
C. evaluating the adaptive value of population individuals;
D. executing a selection operator;
E. executing a crossover operator;
F. executing a mutation operator;
G. executing a conflict search operation;
H. executing conflict resolution operation;
I. performing an archiving and updating operation;
J. when the stop condition is met, the best individual in the archive, i.e., the conflict-free and lowest cost set of multi-agent paths, is provided.
Further, in the step a, an optimal single agent path candidate node is calculated: and executing a deterministic path search algorithm to determine the optimal candidate path set of the single intelligent agent.
The optimal candidate path candidate nodes of the single agent refer to a node set with the sum of the distances from a starting point to an end point equal to the optimal path cost in the grid map, specifically, the path planning problem < A1, S1, G1> of the single agent is considered, and the path cost of each grid on the map is
d(n)＝dist(S1，n)+dist(n，G1)。
Further, in B, B1, constructing an evolutionary algorithm initial population: and (3) constructing an initial population for the evolutionary algorithm from the single agent candidate path node set, namely arranging path nodes in sequence according to a time step sequence, namely the candidate path node set obtained from the step A according to the time step sequence to form a path sequence of the single agent.
Further, in C, the adaptive value of the candidate solution is evaluated: calculating a fitness function of the candidate solution P according to the conflict situation:
f(P)＝cost(P)+cost-to-go(P)+M×conflict(P)。
further, in D, a selection operator is executed: and selecting the superior offspring individuals, and entering a mating pool to serve as the parent individuals of the current iteration.
Further, in E, a crossover operator is executed: each candidate solution swaps a portion of the single agent path to increase population diversity.
Further, in F, a mutation operator is performed: and (4) randomly generating a path from the single agent candidate path set obtained by the calculation of the step (A) to replace the current agent path, thereby avoiding the population from falling into local optimum.
Further, in G, a conflict search operator is performed: for searching a set of conflicts existing between paths, the conflict types include three types: and in B, B7. executes a conflict resolution operator: and resolving the conflict set obtained by B6.
Further, in the I, an archive update operation is performed: the multi-agent path set updating method comprises the steps of updating the optimal multi-agent path set up to the present, and directly inserting when the archive is empty; if the archive is not empty, the cost is compared to the multi-agent path set cost in the archive, and if the current candidate path set cost is lower, the archive is updated.
Further, in said J, a conflict-free and least costly set of multi-agent paths in the archive is provided when the stop condition is met.
The invention has the technical effects and advantages that: (1) Compared with the traditional multi-agent path planning method which adopts an independent single agent path and then resolves conflicts in an incremental mode, the method adopts an evolutionary algorithm to plan conflict-free large-scale multi-agent paths in a heuristic mode, solving speed is high, and calculating efficiency is high; (2) Compared with the traditional multi-agent path planning, which only considers a single agent path, the method adopts a group of optimal path candidate sets of single agents, so that the establishment of an initial population of an evolutionary algorithm becomes possible; (3) By utilizing an evolutionary algorithm based on population, a better multi-agent path set is searched by heuristic optimization, an incremental searching idea of a traditional method is changed, step searching is realized, the searching performance and the solving efficiency of multi-agent path planning are greatly improved, and the multi-agent path planning problem with more agents and larger map scale can be solved in a given time.
Drawings
FIG. 1 is a schematic diagram of the process of the present invention;
FIG. 2 is a diagram illustrating the collision types according to the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1-2, a multi-agent path planning method based on evolutionary algorithm includes the following steps:
A. calculating an optimal single agent path candidate node;
B. constructing an evolutionary algorithm initial population;
C. evaluating the adaptive value of population individuals;
D. executing a selection operator: selecting more excellent offspring individuals (namely individuals with lower fitness), and entering a mating pool to serve as parent individuals of the current iteration;
E. and (3) executing a crossover operator: each candidate solution exchanges a portion of the single agent paths to increase population diversity;
F. performing a mutation operator: randomly generating a path from the single agent candidate path set obtained by the calculation of the step A to replace the current agent path, and avoiding the population from falling into local optimum;
G. and (3) executing a conflict search operation: for searching a set of conflicts existing between paths, the conflict types include three types: node conflicts, edge conflicts and end point conflicts, as shown in figure 2 of the specification;
H. and (3) executing conflict resolution operation: the conflict set is used for resolving the conflict set obtained by the G;
I. performing an archive update operation, G performing an update archive operation: the multi-agent path set updating method comprises the steps of updating the optimal multi-agent path set up to the present, and directly inserting when the archive is empty; if the archive is not empty, it is compared to the multi-agent path set cost in the archive, and if the current candidate path set cost is lower, the archive is updated.
J. When the stop condition is met, the best individual in the archive, i.e., the conflict-free and lowest cost set of multi-agent paths, is provided.
Further, in a, calculating an optimal single agent path candidate node: and executing a deterministic path search algorithm to determine a single intelligent agent optimal candidate path set.
The optimal candidate path candidate node of the single agent refers to a node set with the sum of the distances from the starting point and the end point equal to the optimal path cost in the grid map. Specifically, considering the single agent path planning problem < A1, S1, G1>, the path cost of each grid on the map is
d(n)＝dist(S1，n)+dist(n，G1)
Where n represents a map grid node, S1 represents a start location of agent A1, G1 represents a target location of agent A1, dist (S1, n) represents a path cost from agent A1 to point n from S1, dist (n, G1) represents a path cost from point n to G1. If the optimal path cost of the single agent < A1, S1, G1> path planning is Cmin (A1, S1, G1), the optimal path candidate path node is
NS(A1，S1，G1)＝{n|d(n)＝Cmin(A1，S1，G1)}。
Further, in B, constructing an evolutionary algorithm initial population: and (3) constructing an initial population for the evolutionary algorithm from the single agent candidate path node set, namely arranging path nodes in sequence according to a time step sequence, namely the candidate path node set obtained from the step A according to the time step sequence to form a path sequence of the single agent.
Further, in C, the adaptation value of the candidate solution is evaluated: calculating a fitness function of the candidate solution P according to the conflict situation:
f(P)＝cost(P)+cost-to-go(P)+M×conflict(P)
wherein cost (P) is the path cost of the current multi-agent; cost-to-go is the added cost of the conflict-free path set (target optimal path set) that the current multi-agent set is expected to reach; m is a penalty factor, which is generally set to a larger number; conflict (P) is the number of conflicts in the path set. The fitness function has a first factor for evaluating the actual cost of the current multi-agent path set (without considering conflicts), a second factor for evaluating the amount of cost required by the nearest conflict-free set to guide the population to evolve towards the direction with smaller cost of the target node, and a third factor for punishing existing conflicts, and can guide the individual to evolve towards the direction with the least number of conflicts (increasing the conflict-free property of the agent path set). The fitness design adapts to the most important goal of the algorithm-a conflict-free and lowest cost set of multi-agent paths is obtained.
Compared with the traditional multi-agent path planning method which adopts an independent single agent path and then incrementally resolves conflicts, the method adopts an evolutionary algorithm to plan conflict-free large-scale multi-agent paths iteratively based on a population heuristic method, and is high in solving speed, high in calculating efficiency and flexible in solving time.
Economically, in the scene of intelligent warehousing, before a multi-agent path planning system is not used, a logistics center simply depends on manual picking of staff, and the average time from picking to delivery is 1.5 hours, and the whole process can be easily finished only in l5 minutes by simultaneously planning a plurality of agents (carrying robots) by using the multi-agent system. The efficient and automatic multi-agent path planning scheme can reduce the walking of 90% of traditional logistics personnel and simplify the goods picking process, so that the operation scale and the profitability of intelligent warehousing can be greatly improved with efficiency far higher than that of manual operation and lower cost and error rate. Technically, the method provides key technical support for the application of the unmanned intelligent system in the multi-machine cooperation unmanned intelligent warehousing environment.
It will be evident to those skilled in the art that the invention is not limited to the details of the foregoing illustrative embodiments, and that the present invention may be embodied in other specific forms without departing from the spirit or essential attributes thereof. The present embodiments are therefore to be considered in all respects as illustrative and not restrictive, the scope of the invention being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein. Any reference sign in a claim should not be construed as limiting the claim concerned.
Furthermore, it should be understood that although the present description refers to embodiments, not every embodiment may contain only a single embodiment, and such description is for clarity only, and those skilled in the art should integrate the description, and the embodiments may be combined as appropriate to form other embodiments understood by those skilled in the art.
Claims (10)
1. A multi-agent path planning method based on an evolutionary algorithm is characterized in that: the method comprises the following implementation steps:
A. calculating an optimal single agent path candidate node;
B. constructing an evolutionary algorithm initial population;
C. evaluating the adaptive value of population individuals;
D. executing a selection operator;
E. executing a crossover operator;
F. executing a mutation operator;
G. performing a conflict search operation;
H. executing conflict resolution operation;
I. performing an archiving update operation;
J. when the stop condition is met, the best individual in the archive, i.e., the conflict-free and lowest-cost set of multi-agent paths, is provided.
2. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in the step A, calculating an optimal single agent path candidate node: and executing a deterministic path search algorithm to determine the optimal candidate path set of the single intelligent agent.
The optimal candidate path candidate node of the single agent refers to a node set with the sum of the distances from the starting point to the end point equal to the optimal path cost in the grid map, specifically, the path planning problem < A1, S1, G1> of the single agent is considered, and the path cost of each grid on the map is
d(n)＝dist(S1，n)+dist(n，G1)。
3. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: and B, constructing an evolutionary algorithm initial population: and (3) constructing an initial population for the evolutionary algorithm from the single agent candidate path node set, namely sequentially arranging path nodes in the candidate path node set obtained from the step A according to the time step sequence to form a path sequence of the single agent.
4. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in the step C, the adaptive value of the candidate solution is evaluated: calculating a fitness function of the candidate solution P according to the conflict situation:
f(P)＝cost(P)+cost-to-go(P)+M×conflict(P)。
5. an evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in D, executing a selection operator: and selecting the superior offspring individuals, and entering a mating pool to serve as the parent individuals of the current iteration.
6. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in E, a crossover operator is executed: each candidate solution swaps a portion of the single agent path to increase population diversity.
7. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in the step F, a mutation operator is executed: and randomly generating a path from the single agent candidate path set obtained by the calculation of the step A to replace the current agent path, thereby avoiding the population from falling into local optimum.
8. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: and G, executing a conflict search operator: for searching a set of conflicts existing between paths, the conflict types include three types: and in H, executing a conflict resolution operator: and resolving the conflict set obtained by G.
9. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: in the step I, performing archive updating operation: the method is used for updating the optimal multi-agent path set so far, and if the current population has a conflict-free path set, the multi-agent path set is directly inserted when the archive is empty; if the archive is not empty, it is compared to the multi-agent path set cost in the archive, and if the current candidate path set cost is lower, the archive is updated.
10. An evolutionary algorithm based multi-agent path planning method as claimed in claim 1, wherein: said J, when the stop condition is met, provides a conflict-free and least costly set of multi-agent paths in the archive.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085630.4A CN115438860A (en) | 2022-09-06 | 2022-09-06 | Multi-agent path planning method based on evolutionary algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211085630.4A CN115438860A (en) | 2022-09-06 | 2022-09-06 | Multi-agent path planning method based on evolutionary algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115438860A true CN115438860A (en) | 2022-12-06 |
Family
ID=84247432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211085630.4A Pending CN115438860A (en) | 2022-09-06 | 2022-09-06 | Multi-agent path planning method based on evolutionary algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115438860A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110903A (en) * | 2019-04-17 | 2019-08-09 | 大连理工大学 | A kind of distribution vehicle paths planning method based on neural evolution |
| CN110264120A (en) * | 2019-05-06 | 2019-09-20 | 盐城品迅智能科技服务有限公司 | A kind of intelligent storage route planning system and method based on more AGV |
| CN110986960A (en) * | 2019-12-31 | 2020-04-10 | 哈尔滨工业大学 | Unmanned aerial vehicle track planning method based on improved clustering algorithm |
| CN111157002A (en) * | 2019-12-30 | 2020-05-15 | 西安电子科技大学 | Aircraft 3D path planning method based on multi-agent evolutionary algorithm |
| WO2021022637A1 (en) * | 2019-08-06 | 2021-02-11 | 南京赛沃夫海洋科技有限公司 | Unmanned surface vehicle path planning method and system based on improved genetic algorithm |
| CN114326621A (en) * | 2021-12-25 | 2022-04-12 | 长安大学 | Group intelligent airport trolley dispatching method and system based on layered architecture |
| CN114819316A (en) * | 2022-04-18 | 2022-07-29 | 中国人民解放军96901部队 | Complex optimization method for multi-agent task planning |
-
2022
- 2022-09-06 CN CN202211085630.4A patent/CN115438860A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110110903A (en) * | 2019-04-17 | 2019-08-09 | 大连理工大学 | A kind of distribution vehicle paths planning method based on neural evolution |
| CN110264120A (en) * | 2019-05-06 | 2019-09-20 | 盐城品迅智能科技服务有限公司 | A kind of intelligent storage route planning system and method based on more AGV |
| WO2021022637A1 (en) * | 2019-08-06 | 2021-02-11 | 南京赛沃夫海洋科技有限公司 | Unmanned surface vehicle path planning method and system based on improved genetic algorithm |
| CN111157002A (en) * | 2019-12-30 | 2020-05-15 | 西安电子科技大学 | Aircraft 3D path planning method based on multi-agent evolutionary algorithm |
| CN110986960A (en) * | 2019-12-31 | 2020-04-10 | 哈尔滨工业大学 | Unmanned aerial vehicle track planning method based on improved clustering algorithm |
| CN114326621A (en) * | 2021-12-25 | 2022-04-12 | 长安大学 | Group intelligent airport trolley dispatching method and system based on layered architecture |
| CN114819316A (en) * | 2022-04-18 | 2022-07-29 | 中国人民解放军96901部队 | Complex optimization method for multi-agent task planning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109948855A (en) | A kind of isomery harmful influence Transport route planning method with time window | |
| CN112016812B (en) | Multi-unmanned aerial vehicle task scheduling method, system and storage medium | |
| CN110989612A (en) | Robot path planning method and device based on ant colony algorithm | |
| CN109839110B (en) | Multi-target point path planning method based on rapid random search tree | |
| CN110632907B (en) | Scheduling optimization method and system for distributed assembly type replacement flow shop | |
| Mladenović et al. | Solving the p‐center problem with tabu search and variable neighborhood search | |
| Ribeiro et al. | Ant colony optimization: an overview | |
| CN110334837A (en) | A kind of more AGV dispatching methods decomposed based on petri net | |
| Skinderowicz | An improved ant colony system for the sequential ordering problem | |
| CN105467997A (en) | Storage robot path program method based on linear temporal logic theory | |
| Altiparmak et al. | Optimal design of reliable computer networks: A comparison of metaheuristics | |
| CN109544998A (en) | A kind of flight time slot distribution Multipurpose Optimal Method based on Estimation of Distribution Algorithm | |
| CN110345960B (en) | Route planning intelligent optimization method for avoiding traffic obstacles | |
| CN108921468A (en) | A kind of logistic distribution vehicle intelligence wire arranging method | |
| CN114815802A (en) | Unmanned overhead traveling crane path planning method and system based on improved ant colony algorithm | |
| CN113935452A (en) | Distribution center goods picking path planning method based on ant colony algorithm and genetic algorithm fusion | |
| CN110689174A (en) | Personnel route planning method and device based on public transport | |
| CN115438860A (en) | Multi-agent path planning method based on evolutionary algorithm | |
| CN117075634A (en) | Power distribution network multi-unmanned aerial vehicle scheduling inspection method and device based on improved ant colony algorithm | |
| Júnior et al. | A multiple ant colony system with random variable neighbourhood descent for the vehicle routing problem with time windows | |
| Gambardella et al. | Coupling ant colony system with local search | |
| Shen et al. | Particle swarm optimization in solving vehicle routing problem | |
| CN114237259A (en) | Multi-agent path planning method based on floating resources, navigation server and readable storage medium | |
| CN114415690A (en) | Multi-agent path planning method, navigation server and readable storage medium | |
| Göçken et al. | Improvement of a genetic algorithm approach for the solution of vehicle routing problem with time windows |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221206 |