Performance prediction of an unmanned airborne vehicle multi-agent system

• Published in: European journal of operational research Vol. 172; no. 2; pp. 680 - 695
• Main Authors: Lian, Zhaotong, Deshmukh, Abhijit
• Format: Journal Article
• Language: English
• Published: Amsterdam Elsevier B.V 16.07.2006; Elsevier; Elsevier Sequoia S.A
• Series: European Journal of Operational Research
• Subjects: Air traffic control; Applied sciences; Decision theory. Utility theory; Exact sciences and technology; Markov analysis; Markov decision processes; Multi-agent systems; Operational research and scientific management; Operational research. Management science; Operations research; Optimization; Sample path; Studies; UAV; Unmanned aerial vehicles; Sample path; UAV; Markov decision processes; Multi-agent systems; Markov process; Autonomous system; Gun; Markov decision; On line; Probabilistic approach; Dynamical system; Multiagent system; Optimal trajectory; Airport; Fuel; Optimal path
• ISSN: 0377-2217; 1872-6860
• DOI: 10.1016/j.ejor.2004.10.015

Consider unmanned airborne vehicle (UAV) control agents in a dynamic multi-agent system. The agents must have a set of goals such as destination airport and intermediate positions. At the same time, the agents have to avoid gun shootings which move to their neighbors randomly. Agents try to build and execute plans that yield a high probability of successfully achieving the targets. The plans are developed based on the negotiations between different UAVs in the region with the overall goal in mind. The information about enemy defenses can be communicated between UAVs and they can negotiate about the paths to be taken based on their resources, such as fuel, load, available time to complete the task and the information about the threat. By constructing a Markov Decision Process (MDP) in this paper, we derive the optimal path. Combining the MDP and the sample path technique, we obtain the maximum probability that the UAVs successfully reach the target.