Collision-free trajectory generation for UAVs using Markov decision process

摘要

A collision-free trajectory generation method capable of re-planning the trajectories of an unmanned aerial vehicle (UAV) can increase flight safety and decrease the possibility of mission failure. For this purpose, a Markov decision process (MDP) based algorithm combined with backtracking method, is presented to create a safe trajectory in the case of obstacles. Subsequently, a differential flatness method is adopted to smooth the profile of the rerouted trajectory for satisfying the UAV physical constraints. Simulation results demonstrate that the UAV with the proposed strategy can avoid obstacles and track moving targets in a hostile environment.