AUV fuzzy neural BDI

Abstract

The typical BDI (belief desire intention) model of agent is not efficiently computable and the strict logic expression is not easily applicable to the AUV (autonomous underwater vehicle) domain with uncertainties. In this paper, an AUV fuzzy neural BDI model is proposed. The model is a fuzzy neural network composed of five layers: input (beliefs and desires), fuzzification, commitment, fuzzy intention, and defuzzification layer. In the model, the fuzzy commitment rules and neural network are combined to form intentions from beliefs and desires. The model is demonstrated by solving PEG (pursuit-evasion game), and the simulation result is satisfactory.

Keywords

autonomous underwater vehicle / fuzzy neural network / belief-desire-intention / pursuit-evasion game

References

[1] Bratman M E. Intentions, plans, and practical reason [M]. 1987, Cambridge: Harvard University Press

[2] SINGH M P, ASHER N M. Towards a formal theory of intentions [A]. Proceedings of the European Workshop JELIA-90 [C]. Amsterdam, 1991:472–486.

[3] RAO A S, GEORGEFF M P. An abstract architecture for rational agents [A]. Proceedings of the third International Conference on Principles of Knowledge Representation and Reasoning [C]. San Mateo, 1992:439–449.

[4] RAO A S, GEORGEFF M P. BDI agents: from theory to Practice [A]. Proceedings of the First International Conference on Multi-Agent Systems [C]. San Francisco, 1995: 312–319.

[5] Wooldridge M. An Introduction to multiagent systems [M]. 2002, Chichester: John Wiley & Sons

[6] Poole D. The independent choice logic for modelling multiple agents under uncertainty [J]. Artificial Intelligence, 1997, 94(1–2): 5-56

[7] Kaelbling L P, Littman M L, Cassandra A R. Planning and acting in partially observable stochastic domains [J]. Artificial Intelligence, 1998, 101(1–2): 99-134

[8] Soueina S O. Mall. A multi-agent learning language for competitive and uncertain environments [J]. Transactions of IEICE, 1988, E81-D(12): 1339-1349

[9] XUAN P, LESSER V R. Handling uncertainty in multi-agent Commitments [R]. [S.L.]:University of Massachusetts Amherst, 1999.

[10] Jang J S R. ANFIS: adaptive network based fuzzy inference systems [J]. IEEE Transactions on System, Man and Cybernetics, 1993, 23(3): 665-685

[11] Kachroo P, Shedied S A, Vanlandingham H. Pursuit evasion: the herding non-cooperative dynamic game. transactions of the SDPS [J]. Journal of Integrated Design & Process Science, 2002, 6(1): 31-42