Tian-Yu Zhang

Dynamic unmanned aerial vehicle path planning for rescue missions using trajectory-predictive and attention-enhanced deep recurrent SARSA

This paper proposes a trajectory-predictive and attention-enhanced deep recurrent State-Action-Reward-State-Action (SARSA) algorithm (PA-DR-SARSA), which incorporates future motion information into on-policy reinforcement learning through a Gated Recurrent Unit–based trajectory prediction module that learns temporal mo...