Vision-based target tracking with a small UAV: Optimization-based control strategies

This paper considers the problem of a small, fixed-wing UAV equipped with a gimbaled camera autonomously tracking an unpredictable moving ground vehicle. Thus, the UAV must maintain close proximity to the ground target and simultaneously keep the target in its camera׳s visibility region. To achieve this objective robustly, two novel optimization-based control strategies are developed. The first assumes an evasive target motion while the second assumes a stochastic target motion. The resulting optimal control policies have been successfully flight tested, thereby demonstrating the efficacy of both approaches in a real-world implementation and highlighting the advantages of one approach over the other. •We consider a small, fixed-wing, camera-equipped UAV tracking a moving ground target.•Game theory and stochastic optimal control address evasive and random target motion.•UAV minimizes an expected cumulative cost that favors good viewing geometry.•Dynamic programming computes optimal control policies offline.•Flight tests verify robustness of control policies to unpredictable target motion.