TY - GEN
T1 - Decentralized Planning-Assisted Deep Reinforcement Learning for Collision and Obstacle Avoidance in UAV Networks
AU - Lin, Ju Shan
AU - Chiu, Hsiao Ting
AU - Gau, Rung-Hung
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/4
Y1 - 2021/4
N2 - In this paper, we propose using a decentralized planning-assisted approach of deep reinforcement learning for collision and obstacle avoidance in UAV networks. We focus on a UAV network where there are multiple UAVs and multiple static obstacles. To avoid hitting obstacles without severely deviating from the ideal UAV trajectories, we propose merging adjacent obstacles based on convex hulls and design a novel trajectory planning algorithm. For UAVs to efficiently avoid collisions in a distributed manner, we propose using a decentralized multi-agent deep reinforcement learning approach based on policy gradients. In addition, we propose using a priority-based algorithm for avoiding collisions without reducing the speeds of UAVs too much. Simulation results show that the proposed decentralized planning-assisted deep reinforcement learning approach outperforms a number of baseline approaches in terms of the probability that all UAVs successfully reach their goals within the deadline.
AB - In this paper, we propose using a decentralized planning-assisted approach of deep reinforcement learning for collision and obstacle avoidance in UAV networks. We focus on a UAV network where there are multiple UAVs and multiple static obstacles. To avoid hitting obstacles without severely deviating from the ideal UAV trajectories, we propose merging adjacent obstacles based on convex hulls and design a novel trajectory planning algorithm. For UAVs to efficiently avoid collisions in a distributed manner, we propose using a decentralized multi-agent deep reinforcement learning approach based on policy gradients. In addition, we propose using a priority-based algorithm for avoiding collisions without reducing the speeds of UAVs too much. Simulation results show that the proposed decentralized planning-assisted deep reinforcement learning approach outperforms a number of baseline approaches in terms of the probability that all UAVs successfully reach their goals within the deadline.
KW - collision and obstacle avoidance
KW - deep reinforcement learning
KW - optimal trajectory planning
KW - unmanned aerial vehicles
UR - http://www.scopus.com/inward/record.url?scp=85112469738&partnerID=8YFLogxK
U2 - 10.1109/VTC2021-Spring51267.2021.9448710
DO - 10.1109/VTC2021-Spring51267.2021.9448710
M3 - Conference contribution
AN - SCOPUS:85112469738
T3 - IEEE Vehicular Technology Conference
BT - 2021 IEEE 93rd Vehicular Technology Conference, VTC 2021-Spring - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 93rd IEEE Vehicular Technology Conference, VTC 2021-Spring
Y2 - 25 April 2021 through 28 April 2021
ER -