Multi-Objective Multi-Agent Planning for Discovering and Tracking Unknown and Varying Number of Mobile Objects
share
We consider the online planning problem for a team of agents to discover and track an unknown and time-varying number of moving objects from measurements with uncertain measurement-object origins. Since the onboard sensors have limited field of views (FoV), the usual planning strategy based solely on either tracking detected objects or discovering hidden objects is not adequate. We propose a new multi-objective multi-agent partially observable Markov decision process (MM-POMDP) based on information-theoretic criteria and a state-of-the-art online multi-object tracker. The resulting multi-agent planning problem is exponentially complex due to the unknown data association between objects and multi-sensor measurements, and hence, computing an optimal control action is intractable. We prove that the proposed multi-objective value function is a monotone submodular set function, and develop a greedy algorithm that can achieve an 0.5OPT compared to an optimal algorithm. We demonstrate the proposed solution via a series of numerical examples.
READ FULL TEXT
