GRU-ENHANCED MADDPG WITH DECOUPLED VALUE NETWORK FOR FAILURE-RESILIENT MULTI-ROBOT ENCIRCLEMENT

Mingnan Hu and Bo Chen

References

  1. [1] J.P. Queralta, J. Taipalmaa, B. Can Pullinen, V.K. Sarker,T. Nguyen Gia, H. Tenhunen, M. Gabbouj, J. Raitoharju, andT. Westerlund, Collaborative multi-robot search and rescue:Planning, coordination, perception, and active vision, IEEEAccess, 8, 2020, 191617–191643.
  2. [2] J.K. Verma, and V. Ranga, Multi-robot coordination analysis,taxonomy, challenges and future scope, Journal of Intelligent& Robotic systems, 102(1), 2021, 10.
  3. [3] J. Cui, D. Li, P. Liu, J. Qin, Y. Ma, and Z. Lu. Game-modelprediction hybrid path planning algorithm for multiple mobilerobots in pursuit evasion game. IEEE International Conferenceon Unmanned Systems, 2021, 925–930.
  4. [4] W. Zhang, N. Wang, S. Wie, and J. Zeng, Consensus control ofmultiple autonomous underwater vehicles under delays aimingfor dynamic target hunting tasks. International Journal ofRobotics and Automation, (1), 2023, 42–49.
  5. [5] Z. Sun, H. Sun, P. Li, and J. Zou, Cooperative strategy forpursuit-evasion problem in the presence of static and dynamicobstacles, Ocean Engineering, 279, 2023, 114476.
  6. [6] Z. Zhao, Q. Hu, H. Feng, X. Feng, and W. Su, A cooperativehunting method for multi-AUV swarm in underwater weakinformation environment with obstacles, Journal of MarineScience and Engineering, 10(9), 2022, 1266.
  7. [7] T.Y. Huang, X.B. Chen, and W.B. Xv, A Self-organisingcooperative hunting by swarm robotic systems based onloose-preference rule. Acta Automatica Sinica, 39(1), 2013,57–68.
  8. [8] M.V. Ramana, and M. Kothari, Pursuit-evasion games of highspeed evader, Journal of Intelligent & Robotic Systems, 85(2),2017, 293-306.
  9. [9] Y.J. Shi, R. Li, and K.L. Teo, Cooperative enclosing controlfor multiple moving targets by a group of agents, InternationalJournal of Control, 88(1), 2015, 80–89.
  10. [10] Y.J. Shi, R. Li, and T.T. Wei, Target-enclosing control forsecond-order multi-agent systems, International Journal ofSystems Science, 46(12), 2015, 2279–2286.
  11. [11] H.Q. Zhang, L.H. Wu, and Y. Zhou, Self-organising cooperativemulti-target hunting by swarm robots in complex environments.Control Theory and Applications, 37(5), 2020, 1054–1062.
  12. [12] M.X. Yuan, T. Huang, and Y.Q. Gao, Multi-robot immunehunting algorithm optimised by parallel guidance law. ControlEngineering of China, 30(1), 2023, 177–185.
  13. [13] I.H. Ahmed, C. Brewitt, I. Carlucho, F. Christianos, M. Dunion,E. Fosong, S. Garcin, et al., Deep reinforcement learningfor multi-agent interaction, AI Communications, 35(4), 2022,357–368.
  14. [14] Z. Liu, J. Lu, G. Zhang, and J. Xuan, A behaviour-awareapproach for deep reinforcement learning in non-stationaryenvironments without known change points. Proceedings ofthe Thirty-Third International Joint Conference on ArtificialIntelligence, 2024, 4634–4642.
  15. [15] Y. Wang, L. Dong, and C. Sun, Cooperative control formulti-player pursuit-evasion games with reinforcement learning,Neurocomputing, 412, 2020, 101–114.
  16. [16] W. Wang, L. Li, F. Ye, and Y. Peng, A large-scale path planningalgorithm for underwater robots based on deep reinforcementlearning. International Journal of Robotics and Automation,39(3), 2024, 204–210.
  17. [17] Y. Sun, C. Yan, Z. Lan, B. Lin, H. Zhou, and X.Xiang, A scalable deep reinforcement learning algorithm forpartially observable pursuit-evasion game. IEEE InternationalConference on Machine Learning, Cloud Computing andIntelligent Mining, 2022, 370–376.
  18. [18] S. Iqbal, and F. Sha, Actor-attention-critic for multi-agentreinforcement learning. International Conference on MachineLearning. 2019, 2961–2970.
  19. [19] R. Lowe, Y. Wu, A. Tamar, J. Harb, P. Abbeel, and I.Mordatch, Multi-agent actor-critic for mixed cooperative-competitive environments. Proceedings of the 31st InternationalConference on Neural Information Processing Systems, 2017,6382–6393.
  20. [20] Z.H. Wang, Y.X. Zhang, and Z.Q. Huang, Multi-agentcollaboration based on RGMAAC algorithm under partialobservability. Journal of Control and Decision, 38(5), 2023,1267–1277.
  21. [21] H.U. Sheikh, and L. B¨ol¨oni, Multi-agent reinforcement learningfor problems with combined individual and team reward. 2020International Joint Conference on Neural Networks, 2020, 1–8.
  22. [22] S. Omidshafiei, J. Pazis, C. Amato, J.P. How, and J.Vian, Deep decentralised multi-task multi-agent reinforcementlearning under partial observability. International Conferenceon Machine Learning, 2017, 2681–2690.

Important Links:

Go Back