TY - GEN
T1 - Efficiency-reinforced Learning with Auxiliary Depth Reconstruction for Autonomous Navigation of Mobile Devices
AU - Li, Cheng Chun
AU - Shuai, Hong Han
AU - Wang, Li Chun
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - In this paper, we take Unmanned Aerial Vehicles (UAVs) as the mobile devices to study the problem of autonomous navigation since UAVs have been adopted as intelligent vehicles for executing complex tasks such as bridge structure examination, crowd estimation, target searching, and package delivery. As Deep Reinforcement Learning (DRL) has achieved great success in many control tasks, it is envisaged to exploit DRL for autonomous navigation. Nevertheless, as the navigation path becomes distant, searching in a large number of states and action spaces becomes very challenging to DRL. In this paper, we provide a novel reinforcement learning framework to facilitate the autonomous navigation in complicated environments by jointly considering the temporal abstractions and policy efficiency to dynamically select the frequency of the action decisions with the efficiency regularization. Moreover, to bootstrap the learning procedure, we further add an auxiliary task of depth map reconstruction to accelerate the learning process. Experimental results on 3D UAV simulator and DeepMind Lab environments manifest that the proposed framework improves the state-of-the-art methods in terms of success rates in different environments.
AB - In this paper, we take Unmanned Aerial Vehicles (UAVs) as the mobile devices to study the problem of autonomous navigation since UAVs have been adopted as intelligent vehicles for executing complex tasks such as bridge structure examination, crowd estimation, target searching, and package delivery. As Deep Reinforcement Learning (DRL) has achieved great success in many control tasks, it is envisaged to exploit DRL for autonomous navigation. Nevertheless, as the navigation path becomes distant, searching in a large number of states and action spaces becomes very challenging to DRL. In this paper, we provide a novel reinforcement learning framework to facilitate the autonomous navigation in complicated environments by jointly considering the temporal abstractions and policy efficiency to dynamically select the frequency of the action decisions with the efficiency regularization. Moreover, to bootstrap the learning procedure, we further add an auxiliary task of depth map reconstruction to accelerate the learning process. Experimental results on 3D UAV simulator and DeepMind Lab environments manifest that the proposed framework improves the state-of-the-art methods in terms of success rates in different environments.
KW - Autonomous navigation
KW - reinforcement learning
KW - unmanned aerial vehicle
UR - http://www.scopus.com/inward/record.url?scp=85137608392&partnerID=8YFLogxK
U2 - 10.1109/MDM55031.2022.00099
DO - 10.1109/MDM55031.2022.00099
M3 - Conference contribution
AN - SCOPUS:85137608392
T3 - Proceedings - IEEE International Conference on Mobile Data Management
SP - 458
EP - 463
BT - Proceedings - 2022 23rd IEEE International Conference on Mobile Data Management, MDM 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 23rd IEEE International Conference on Mobile Data Management, MDM 2022
Y2 - 6 June 2022 through 9 June 2022
ER -