A General Framework for Formulating Adjustable Autonomy of Multi-agent Systems by Fuzzy Logic
Autonomous agents and multi-agent systems significantly facilitate solutions to many complex and distributed problem-solving environments due to the agents’ various capabilities. These environments comprise uncertain, high dynamism or irregular workload that might prone the agents to make decisions that lead to undesirable outcomes. This paper proposes a Fuzzy Logic-based Adjustable Autonomy (FLAA) as a general framework for managing the autonomy of multi-agent systems that operate in complex environments. The framework includes a fuzzy logic technique to quantitatively measure and distribute the autonomy among operators (autonomous agents and humans) based on adjustable autonomy attributes. The FLAA framework dynamically changes the autonomy of the operators to directions that meets their ability to perform and produce desirable outcomes. The technical application of the framework is demonstrated by an example scenario. The scenario illustrates the competence performance of the collaborative operators. The advantages of using the framework are to capture relationships between discrete autonomy attributes, quantify adjustable autonomy and manage adjustable autonomous multi-agent systems.
KeywordsAutonomous agent Multi-agent system Adjustable autonomy Fuzzy logic
This project is sponsored by the postdoctoral grant of Universiti Tun Hussein Onn Malaysia (UTHM) under Vot D004 and partially supported by the Tier 1 research grant scheme of UTHM under Vot U893.
- 1.Mostafa, S.A., Ahmad, M.S., Mustapha, A.: Adjustable autonomy: a systematic literature review. Artif. Intell. Rev. 1–38 (2017)Google Scholar
- 2.Hexmoor, H., Mclaughlan, B.: Computationally adjustable autonomy. Scalable Comput. Pract. Exp. 8(1), 41–48 (2001)Google Scholar
- 3.Jaafar, J., McKenzie, E.: Decision-making method using fuzzy logic for autonomous agent navigation. Electron. J. Comput. Sci. Inf. Technol. 3(1), 8–18 (2011)Google Scholar
- 4.Mostafa, S., Gunasekaran, S.S., Ahmad, M.S., Ahmad, A., Annamalai, M., Mustapha, A.: Defining tasks and actions complexity-levels via their deliberation intensity measures in the layered adjustable autonomy model. In: International Conference on Intelligent Environments (IE), pp. 52–55. IEEE (2014)Google Scholar
- 10.Gharbi, A., Samir, B.A.: Fuzzy logic multi-agent system. Int. J. Comput. Sci. Inf. Technol. 6(4), 273 (2014)Google Scholar
- 11.Shamshirb, S., Kalantari, S., Bakhsh, Z.: Designing a smart multi-agent system based on fuzzy logic to improve the gas consumption pattern. Sci. Res. Essays 5(6), 592–605 (2010)Google Scholar