This program will develop a communication-less solution to decentralized control and task coordination for multi-agent systems (MAS). Reducing the operational burden of MAS swarms on human operators will greatly improve the capability of spacecraft constellations and distant planetary explorations. The proposed solution would guide the MAS towards a cost minimized set of actions by performing gradient descent on Game Theory models for individual agents. In this setup, convergence is achieved when the MAS reaches a Nash equilibrium. Game Theory models are commonly found in nature and can be expressed as traditional optimization problems. The novel algorithmic solution will be executed on each agent’s processor in a MAS in order to observe the local environment and other nearby agents. The local algorithms will be derived from online and stochastic optimization methods. Convergence to the Nash equilibrium will be proved under conditions of noisy and uncertain observations, including the case of communication-less coordination. Precise, non-asymptotic convergence bounds will be proved. Multiple game models will be designed for different coordination tasks, system architectures, and hardware.
The developed communication-less coordination and control applies to NASA's ongoing development of MAS that operate in close proximity to one another. This includes future solutions such as the Mars Helicopter or JPL’s PUFFER robots. The primary goal is to provide a software framework that uses shared potential functions, game models, and individual observations to facilitate communication-less, or very limited communication for coordination between agents in a MAS. The swarming MAS would be composed of homogeneous agents.
Non-NASA applications for this technology include integration into a variety of multi-agent autonomous vehicle systems. This includes applications such as precision agriculture UAVs, LEO communication satellite constellations and mine or industrial site inspection. Non-NASA government applications include UAVs and ground vehicles for defense and surveillance as well as search and rescue.