ASTS: Autonomous switching of task-level strategies

Wang, Xianchang ; Lv, Bingyu ; Wang, Kaiyu ; Zhang, Rui 

International Journal of Applied Mathematics and Computer Science, Tome 33 (2023) no. 4, pp. 553-568.

Résumé

Autonomous coordination of multi-agent systems can improve the reaction and dispatching ability of multiple agents to emergency events. The existing research has mainly focused on the reactions or dispatching in specific scenarios. However, task-level coordination has not received significant attention. This study proposes a framework for autonomous switching of task-level strategies (ASTS), which can automatically switch strategies according to different scenarios in the task execution process. The framework is based on the blackboard system, which takes the form of an instance as an agent and the form of norm(s) as a strategy; it uses events to drive autonomous cooperation among multiple agents. A norm may be triggered when an event occurs. After the triggered norm is executed, it can change the data, state, and event in ASTS. To demonstrate the autonomy and switchability of the proposed framework, we develop a fire emergency reaction dispatch system. This system is applied to emergency scenarios involving fires. Five types of strategies and two control modes are designed for this system. Experiments show that this system can autonomously switch between different strategies and control modes in different scenarios with promising results. Our framework improves the adaptability and flexibility of multiple agents in an open environment and represents a solid step toward switching strategies at the task level.

Détail

Keywords: task level, autonomous switching strategy, blackboard system
Mots-clés : poziom zadania, strategia przełączania, system tablicowy

Bibliographie

[1] [1] Bai, S., Jia, X., Cheng, Z. and Guo, B. (2021). Operation strategy optimization for on-orbit satellite subsystems considering multiple active switching, Reliability Engineering and System Safety 215: 107765, DOI: 10.1016/j.ress.2021.107765.

[2] [2] Hook, J., El-Sedky, S., Silva, V.D. and Kondoz, A.M. (2021). Learning data-driven decision-making policies in multi-agent environments for autonomous systems, Cognitive Systems Research 65(2): 40-49, DOI: 10.1016/j.cogsys.2020.09.006.

[3] [3] Kanazawa, A., Kinugawa, J., and Kosuge, K. (2021). Motion planning for human-robot collaboration using an objective-switching strategy, IEEE Transactions on Human-Machine Systems 51(6): 590-600, DOI: 10.1109/THMS.2021.3112953.

[4] [4] Landgren, P., Srivastava, V. and Leonard, N.E. (2021). Distributed cooperative decision making in multi-agent multi-armed bandits, Automatica 125: 109445, DOI: 10.1016/j.automatica.2020.109445.

[5] [5] Li, Y., Ma, D., An, Z., Wang, Z., Zhong, Y., Chen, S. and Feng, C. (2022). V2x-sim: Multi-agent collaborative perception dataset and benchmark for autonomous driving, IEEE Robotics and Automation Letters 7(4): 10914-10921, DOI: 10.1109/LRA.2022.3192802.

[6] [6] Lin, J., Su, W., Xiao, L. and Jiang, X. (2018). Adaptive modulation switching strategy based on Q-learning for underwater acoustic communication channel, International Conference on Underwater Networks & Systems, WUWNet 2018, Shenzhen, China, pp. 38:1-38:5.

[7] [7] Liu, G., Wu, S., Zhu, L., Wang, J. and Lv, Q. (2022). Fast and smooth trajectory planning for a class of linear systems based on parameter and constraint reduction, International Journal of Applied Mathematics and Computer Science 32(1): 11-21, DOI: 10.34768/amcs-2022-0002.

[8] [8] Ma, J., Cheng, Z., Zhang, X., Mamun, A.A., de Silva, C.W. and Lee, T.H. (2020). Data-driven predictive control for multi-agent decision making with chance constraints, arXiv: abs/2011.03213.

[9] [9] Ming, Y., Chen, J., Dong, Y. and Wang, Z. (2022). Evolutionary game based strategy selection for hybrid v2v communications, IEEE Transactions on Vehicular Technology 71(2): 2128-2133, DOI: 10.1109/TVT.2021.3132025.

[10] [10] Nimmolrat, A., Sutham, K. and Thinnukool, O. (2021). Patient triage system for supporting the operation of dispatch centres and rescue teams, BMC Medical Informatics and Decision Making 21(1): 68-84, DOI: 10.1186/s12911-021-01440-x.

[11] [11] Oguz-Ekim, P., Bostanci, B., Tekkk, S.. and Synmez, E. (2020). The EKF based localization and initialization algorithms with UWB and odometry for indoor applications and ROS ecosystem, International Conference on Advanced Computing and Applications, SIU 2020, Gaziantep, Turkey, pp. 1-4.

[12] [12] Roy, D., Chowdhury, A., Maitra, M. and Bhattacharya, S. (2018). Multi-robot virtual structure switching and formation changing strategy in an unknown occluded environment, IEEE Conference on Computer Communications, IROS 2018, Madrid, Spain, pp. 4854-4861.

[13] [13] Sengupta, A. and Yasser Mohammad, S.N. (2021). An autonomous negotiating agent framework with reinforcement learning based strategies and adaptive strategy switching mechanism, arXiv: abs/2102.03588.

[14] [14] Shin, M.E., Kang, T. and Kim, S. (2018). Blackboard architecture for detecting and notifying failures for component-based unmanned systems, Journal of Intelligent and Robotic Systems 90(2): 571-585, DOI: 10.1007/s10846-017-0677-4.

[15] [15] Sun, K. and Liu, X. (2021). Path planning for an autonomous underwater vehicle in a cluttered underwater environment based on the heat method, International Journal of Applied Mathematics and Computer Science 31(2): 289-301, DOI: 10.34768/amcs-2021-0020.

[16] [16] Tan, J., Khalili, R., Karl, H. and Hecker, A. (2022). Multi-agent distributed reinforcement learning for making decentralized offloading decisions, IEEE Conference on Computer Communications, INFOCOM 2022, London, UK, pp. 2098-2107.

[17] [17] Wang, H., Yan, J., Han, S. and Liu, Y. (2020a). Switching strategy of the low wind speed wind turbine based on real-time wind process prediction for the integration of wind power and EVS, Renewable Energy 157: 256-272, DOI: 10.1016/j.renene.2020.04.132.

[18] [18] Wang, P., Yang, J., Jin, Y. and Wang, J. (2020b). Research on allocation and dispatching strategies of rescue vehicles in emergency situation on the freeway, International Conference on Control, Automation, Robotics and Vision, ICARCV 2020, Shenzhen, China, pp. 130-135.

[19] [19] Wang, X., Fu, R. and Zhang, R. (2020c). MONE: Mutation oriented norm evolution, IEEE Access 8: 205386-205395, DOI: 10.1109/ACCESS.2020.3037798.

[20] [20] Wu, P., Chu, F., Che, A. and Zhou, M. (2018). Bi-objective scheduling of fire engines for fighting forest fires: New optimization approaches, IEEE Transactions on Intelligent Transportation Systems 19(4): 1140-1151, DOI: 10.1109/TITS.2017.2717188.

[21] [21] Zhao, T., Zhang, W., Zhao, H. and Jin, Z. (2017). A reinforcement learning-based framework for the generation and evolution of adaptation rules, International Conference on Autonomic Computing, ICAC 2017, Columbus, USA, pp. 103-112.

[22] [22] Zhou, Z. (2021). Large-Scale Multi-Agent Decision-Making UsingMean Field Game Theory and Reinforcement Learning, PhD thesis, University of Nevada, Reno.