Login / Signup
Deep Reinforcement Learning of Collision-Free Flocking Policies for Multiple Fixed-Wing UAVs Using Local Situation Maps.
Chao Yan
Chang Wang
Xiaojia Xiang
Zhen Lan
Yuna Jiang
Published in:
IEEE Trans. Ind. Informatics (2022)
Keyphrases
</>
reinforcement learning
path planning
optimal policy
dynamic environments
collision free
motion planning
potential field
aerial vehicles
state space
control algorithm
objective function
dynamic programming
multi robot
policy search