An evolutionary approach for the target search problem in uncertain environment

Search path planning is critical to achieve efficient information-gathering tasks in dynamic uncertain environments. Given task complexity, most proposed approaches rely on various strategies to reduce computational complexity, from deliberate simplifications or ad hoc constraint relaxation to fast approximate global search methods utilization often focusing on a single objective. However, problem-solving search techniques designed to compute near-optimal solutions largely remain computationally prohibitive and are not scalable. In this paper, a new information-theoretic evolutionary anytime path planning algorithm is proposed to solve a dynamic search path planning problem in which a fleet of homogeneous unmanned aerial vehicles explores a search area to hierarchically minimize target zone occupancy uncertainty, lateness, and travel/discovery time respectively. Conditioned by new observation outcomes and request events, the evolutionary algorithm episodically solves an augmented static open-loop search path planning model over a receding time horizon incorporating any anticipated information feedback. The proposed approach has shown to outperform alternate myopic and greedy heuristics, significantly improving relative information gain at the expense of modest additional travel cost.