A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm
Abstract
:1. Introduction
2. A Mathematical Model and Systematic Framework for Multi-Robot Task Allocation
2.1. Mathematical Model of Multi-Robot Task Allocation
2.2. Multi-Robot Tasking System Framework
3. Improved K-Means++ Clustering Algorithm and Particle Swarm Algorithm Synergistic Approach to Task Allocation
3.1. Improved K-Means++ Clustering Algorithm
3.2. Particle Swarm Algorithm for Multi-Robot Task Allocation Based on Clustering Results
3.3. Particle Swarm Algorithm to Optimize Clustering Task Set Ordering
4. Simulation Experiment
4.1. Scene Description
- (1)
- Robot type: A single-tasking robot (ST) is one that can only perform one task at a time; a multi-tasking robot (MT) is one that can perform multiple tasks simultaneously.
- (2)
- Task types: Single-robot tasks (SR) are those that require only one robot to complete; multi-robot tasks (MR) are those that require multiple robots to complete.
- (3)
- Assignment types: Instantaneous assignment (IA) refers to a situation where each robot is assigned one task without future planning; time-expanded assignment (TA) refers to a scenario where a series of tasks can be assigned to a robot within the planning horizon.
- (1)
- Each robot has a maximum load limit, the transportation process occurs at a uniform speed, and transportation cannot exceed the load limit and is assumed to be in good condition.
- (2)
- Adequate power is possessed by each robot to complete all assigned tasks.
- (3)
- The robots begin at their designated starting points, travel to the task location to fulfill the transportation tasks, and then return to their initial positions upon completing all assigned tasks.
4.2. Simulation Experiment Platform Construction
4.3. Comparison of Simulation Experiments
4.4. Simulation Experiment Results and Analysis
5. Real Robot Experiments
5.1. Real Robot Experiments Platform Construction
5.2. Real Robot Experiments Process
5.3. Comparison of Real Robot Experiments
5.4. Real Robot Experiments Results and Analysis
6. Discussion
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Ju, C.; Kim, J.; Seol, J.; Son, H.I. A Review on Multirobot Systems in Agriculture. Comput. Electron. Agric. 2022, 202, 107336. [Google Scholar] [CrossRef]
- Baroudi, U.; Alshaboti, M.; Koubaa, A.; Trigui, S. Dynamic Multi-Objective Auction-Based (DYMO-Auction) Task Allocation. Appl. Sci. 2020, 10, 3264. [Google Scholar] [CrossRef]
- Mishra, B.; Garg, D.; Narang, P.; Mishra, V. Drone-Surveillance for Search and Rescue in Natural Disaster. Comput. Commun. 2020, 156, 1–10. [Google Scholar] [CrossRef]
- Xiong, Q.C.; Dong, C.; Hong, Q.Y. A multi-robot task allocation method for raw material supply chain in smart factory. Small Microcomput. Syst. 2022, 43, 1625–1630. [Google Scholar] [CrossRef]
- Guo, X.; Hu, J.; Chen, J.; Deng, F.; Lam, T.L. Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment. IEEE Robot. Autom. Lett. 2021, 6, 8349–8356. [Google Scholar] [CrossRef]
- Seenu, N.; RM, K.C.; Ramya, M.M.; Janardhanan, M.N. Review on State-of-the-Art Dynamic Task Allocation Strategies for Multiple-Robot Systems. Ind. Robot 2020, 47, 929–942. [Google Scholar] [CrossRef]
- Wang, W.J.; Zheng, Y.T.; Lin, G.Z.; Zhang, L.; Han, Z.G. Swarm robotics: A review. Robot 2020, 42, 232–256. [Google Scholar] [CrossRef]
- Ghassemi, P.; Chowdhury, S. Multi-Robot Task Allocation in Disaster Response: Addressing Dynamic Tasks with Deadlines and Robots with Range and Payload Constraints. Robot. Auton. Syst. 2022, 147, 103905. [Google Scholar] [CrossRef]
- Ghassemi, P.; DePauw, D.; Chowdhury, S. Decentralized Dynamic Task Allocation in Swarm Robotic Systems for Disaster Response: Extended Abstract. In Proceedings of the 2019 International Symposium on Multi-Robot and Multi-Agent Systems (MRS), New Brunswick, NJ, USA, 22–23 August 2019; pp. 83–85. [Google Scholar] [CrossRef]
- De Ryck, M.; Pissoort, D.; Holvoet, T.; Demeester, E. Decentral Task Allocation for Industrial AGV-Systems with Routing Constraints. J. Manuf. Syst. 2022, 62, 135–144. [Google Scholar] [CrossRef]
- Talebpour, Z.; Martinoli, A. Risk-Based Human-Aware Multi-Robot Coordination in Dynamic Environments Shared with Humans. In Proceedings of the 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain, 1–5 October 2018; pp. 3365–3372. [Google Scholar] [CrossRef]
- Saeedvand, S.; Aghdasi, H.S.; Baltes, J. Robust Multi-Objective Multi-Humanoid Robots Task Allocation Based on Novel Hybrid Metaheuristic Algorithm. Appl. Intell. 2019, 49, 4097–4127. [Google Scholar] [CrossRef]
- Alitappeh, R.J.; Jeddisaravi, K. Multi-Robot Exploration in Task Allocation Problem. Appl. Intell. 2022, 52, 2189–2211. [Google Scholar] [CrossRef]
- Martin, J.G.; Muros, F.J.; Maestre, J.M.; Camacho, E.F. Multi-Robot Task Allocation Clustering Based on Game Theory. Robot. Auton. Syst. 2023, 161, 104314. [Google Scholar] [CrossRef]
- Chakraa, H.; Guérin, F.; Leclercq, E.; Lefebvre, D. Optimization Techniques for Multi-Robot Task Allocation Problems: Review on the State-of-the-Art. Robot. Auton. Syst. 2023, 168, 104492. [Google Scholar] [CrossRef]
- Zou, H. Research on Task Scheduling and Path Planning Technology for Intelligent Mobile Platform. Master’s Thesis, Chengdu University of Technology, Chengdu, China, 2023. [Google Scholar] [CrossRef]
- Ren, S.X. Research on Material Handling Task Allocation and Path Planning in Smart Factory Workshop. Master’s Thesis, Beijing Jiaotong University, Beijing, China, 2023. [Google Scholar] [CrossRef]
- Yang, S.; Zhang, Y.; Ma, L.; Song, Y.; Zhou, P.; Shi, G.; Chen, H. A Novel Maximin-Based Multi-Objective Evolutionary Algorithm Using One-by-One Update Scheme for Multi-Robot Scheduling Optimization. IEEE Access 2021, 9, 121316–121328. [Google Scholar] [CrossRef]
- Chen, J.; Wang, J.; Xiao, Q.; Chen, C. A Multi-Robot Task Allocation Method Based on Multi-Objective Optimization. In Proceedings of the 2018 15th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 18–21 November 2018; pp. 1868–1873. [Google Scholar] [CrossRef]
- Song, W.; Gao, Y.; Shen, L.Y.; Zhang, Y.N. A Multi-robot Task Allocation Algorithm Based on Near-field Subset Partition. Robot 2021, 43, 629–640. [Google Scholar] [CrossRef]
- Chen, X.; Zhang, P.; Du, G.; Li, F. Ant Colony Optimization Based Memetic Algorithm to Solve Bi-Objective Multiple Traveling Salesmen Problem for Multi-Robot Systems. IEEE Access 2018, 6, 21745–21757. [Google Scholar] [CrossRef]
- Janati, F.; Abdollahi, F.; Ghidary, S.S.; Jannatifar, M.; Baltes, J.; Sadeghnejad, S. Multi-Robot Task Allocation Using Clustering Method. In Robot Intelligence Technology and Applications 4; Kim, J.-H., Karray, F., Jo, J., Sincak, P., Myung, H., Eds.; Springer International Publishing: Cham, Switzerland, 2017; pp. 233–247. [Google Scholar] [CrossRef]
- Biswas, S.; Anavatti, S.G.; Garratt, M.A. Nearest Neighbour Based Task Allocation with Multi-Agent Path Planning in Dynamic Environments. In Proceedings of the 2017 International Conference on Advanced Mechatronics, Intelligent Manufacture, and Industrial Automation (ICAMIMIA), Surabaya, Indonesia, 12–14 October 2017; IEEE: Piscataway, NJ, USA, 2017; pp. 181–186. [Google Scholar] [CrossRef]
- Wang, H.; Ni, J.; Qi, Y.; Zhao, M. Optimal Design of Laser SLAM Algorithm Based on RBPF Improved Resampling Technology. In Proceedings of the 2020 IEEE International Conference on Mechatronics and Automation (ICMA), Beijing, China, 13–16 October 2020; IEEE: Piscataway, NJ, USA, 2020; pp. 1245–1250. [Google Scholar] [CrossRef]
- Trelea, I.C. The particle swarm optimization algorithm: Convergence analysis and parameter selection. Inf. Process. Lett. 2003, 85, 317–325. [Google Scholar] [CrossRef]
- MacQueen, J. Some Methods for Classification and Analysis of Multivariate Observations. In Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Volume 1: Statistics; University of California Press: Berkeley, CA, USA, 1967. [Google Scholar]
- Arthur, D.; Vassilvitskii, S. K-Means++: The Advantages of Careful Seeding. In Proceedings of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007, New Orleans, LA, USA, 7–9 January 2007. [Google Scholar] [CrossRef]
- Luo, X.D. Multi-Robot Path Planning and Scheduling for Intelligent Warehouse. Master’s Thesis, Chongqing University of Posts and Telecommunications, Chongqing, China, 2022. [Google Scholar] [CrossRef]
- Gerkey, B.P.; Matarić, M.J. A Formal Analysis and Taxonomy of Task Allocation in Multi-Robot Systems. Int. J. Robot. Res. 2004, 23, 939–954. [Google Scholar] [CrossRef]
Task Allocation Optimization Algorithm | Future Research Directions and Trends |
---|---|
Market-based task allocation | 1. The construction of a robust and reliable communication network is a necessary condition for market tasking, which has not yet been addressed. |
Task allocation based on heuristic algorithms | 1. There is a wide variety of heuristic algorithms, each with its own advantages and disadvantages. Future research could explore how to integrate different heuristic algorithms to fully utilize their respective advantages and improve the efficiency and quality of task allocation. |
Clustering-based task allocation | 1. How to determine the optimal number of tasks in a cluster is a direction for further research. 2. Developing effective switching strategies between clusters to cope with uncertainties such as robot failures is a direction for further research. |
Alternative methods of allocating tasks | 1. Fully apply artificial intelligence, reinforcement learning and other technologies to optimize task allocation to improve the autonomous decision-making ability and adaptability of the robot. 2. The use of a multiple algorithm fusion strategy for task allocation is also a future research direction |
Task | Position/m | Task | Position/m | Task | Position/m | Task | Position/m |
---|---|---|---|---|---|---|---|
T1 | (7, 25) | T6 | (12, 15) | T11 | (17, 15) | T16 | (22, 25) |
T2 | (7, 20) | T7 | (12, 20) | T12 | (17, 10) | T17 | (27, 25) |
T3 | (7, 15) | T8 | (12, 25) | T13 | (22, 10) | T18 | (27, 20) |
T4 | (7, 10) | T9 | (17, 25) | T14 | (22, 15) | T19 | (27, 15) |
T5 | (12, 10) | T10 | (17, 20) | T15 | (22, 20) | T20 | (27, 10) |
Task | Position/m | Task | Position/m | Task | Position/m | Task | Position/m |
---|---|---|---|---|---|---|---|
T1 | (−4.8, 0.3) | T6 | (−2.8, 1.3) | T11 | (−2.8, 2.3) | T16 | (−4.8, 3.3) |
T2 | (−3.8, 0.3) | T7 | (−3.8, 1.3) | T12 | (−1.8, 2.3) | T17 | (−4.8, 4.3) |
T3 | (−2.8, 0.3) | T8 | (−4.8, 1.3) | T13 | (−1.8, 3.3) | T18 | (−3.8, 4.3) |
T4 | (−1.8, 0.3) | T9 | (−3.8, 2.3) | T14 | (−2.8, 3.3) | T19 | (−2.8, 4.3) |
T5 | (−1.8, 1.3) | T10 | (−2.8, 2.3) | T15 | (−3.8, 3.3) | T20 | (−1.8, 4.3) |
Algorithms | No. of Experiments/Times | Number of Tasks /Number | Distance to Mission Completion/m | Task Completion Time/s | Task Allocation Time/s | |
---|---|---|---|---|---|---|
Three-Robot Travelling Distance d = {d1, d2, d3}/m | Total Distance/m | |||||
K-means++ + PSO | 1 | 8 | {19.31, 16.32, 15.05} | 50.68 | 84.90 | 0.59 |
2 | 10 | {19.85, 15.23, 18.67} | 53.75 | 92.35 | 0.66 | |
3 | 13 | {20.87, 18.20, 17.46} | 56.53 | 98.62 | 0.79 | |
4 | 15 | {25.29, 20.23, 14.86} | 60.32 | 103.21 | 0.83 | |
5 | 16 | {28.34, 17.63, 16.21} | 62.18 | 107.25 | 0.92 | |
Average | 56.69 | 97.266 | 0.758 | |||
K-means + MAA | 1 | 8 | {20.56, 13.87, 18.69} | 53.12 | 89.82 | 1.36 |
2 | 10 | {23.45, 15,64, 17.99} | 57.08 | 97.24 | 1.48 | |
3 | 13 | {18.32, 25.16, 16.55} | 60.03 | 103.55 | 1.59 | |
4 | 15 | {20.85, 26.85, 16.12} | 63.82 | 108.16 | 1.63 | |
5 | 16 | {29.68, 19.86, 18.17} | 67.71 | 113.79 | 1.72 | |
Average | 60.35 | 102.512 | 1.556 | |||
PSO | 1 | 8 | {17.13, 22.59, 15.32} | 55.04 | 93.39 | 1.86 |
2 | 10 | {18.45, 25.68, 15.62} | 59.39 | 102.51 | 2.32 | |
3 | 13 | {21.29, 29.12, 12.33} | 62.74 | 111.16 | 2.45 | |
4 | 15 | {19.37, 30.84, 17.35} | 67.56 | 113.16 | 2.68 | |
5 | 16 | {22.56, 32.36, 15.47} | 70.39 | 119.69 | 2.85 | |
Average | 63.02 | 108.014 | 2.432 | |||
K-means++ + GA | 1 | 8 | {19.94, 17.32, 15.80} | 52.96 | 87.35 | 1.18 |
2 | 10 | {24.26, 18.53, 13.88} | 56.67 | 96.67 | 1.26 | |
3 | 13 | {26.13, 19.75, 15.47} | 61.35 | 102.34 | 1.45 | |
4 | 15 | {26.85, 20.65, 16.12} | 63.62 | 106.56 | 1.52 | |
5 | 16 | {31.23, 19.56, 16.08} | 66.87 | 113.68 | 1.66 | |
Average | 60.29 | 101.32 | 1.41 | |||
K-means++ + PSO reduces % compared to K-means + MAA | 6.06 | 5.12 | 51.25 | |||
K-means++ + PSO reduces % compared to PSO | 10.04 | 9.95 | 68.82 | |||
K-means++ + PSO reduces % compared to K-means + GA | 5.97 | 4.00 | 46.24 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yuan, Y.; Yang, P.; Jiang, H.; Shi, T. A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm. Biomimetics 2024, 9, 694. https://doi.org/10.3390/biomimetics9110694
Yuan Y, Yang P, Jiang H, Shi T. A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm. Biomimetics. 2024; 9(11):694. https://doi.org/10.3390/biomimetics9110694
Chicago/Turabian StyleYuan, Youdong, Ping Yang, Hanbing Jiang, and Tiange Shi. 2024. "A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm" Biomimetics 9, no. 11: 694. https://doi.org/10.3390/biomimetics9110694
APA StyleYuan, Y., Yang, P., Jiang, H., & Shi, T. (2024). A Multi-Robot Task Allocation Method Based on the Synergy of the K-Means++ Algorithm and the Particle Swarm Algorithm. Biomimetics, 9(11), 694. https://doi.org/10.3390/biomimetics9110694