Efficiency-reinforced Learning with Auxiliary Depth Reconstruction for Autonomous Navigation of Mobile Devices

研究成果: Conference contribution同行評審

摘要

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.

原文English
主出版物標題Proceedings - 2022 23rd IEEE International Conference on Mobile Data Management, MDM 2022
發行者Institute of Electrical and Electronics Engineers Inc.
頁面458-463
頁數6
ISBN(電子)9781665451765
DOIs
出版狀態Published - 2022
事件23rd IEEE International Conference on Mobile Data Management, MDM 2022 - Virtual, Paphos, Cyprus
持續時間: 6 6月 20229 6月 2022

出版系列

名字Proceedings - IEEE International Conference on Mobile Data Management
2022-June
ISSN(列印)1551-6245

Conference

Conference23rd IEEE International Conference on Mobile Data Management, MDM 2022
國家/地區Cyprus
城市Virtual, Paphos
期間6/06/229/06/22

指紋

深入研究「Efficiency-reinforced Learning with Auxiliary Depth Reconstruction for Autonomous Navigation of Mobile Devices」主題。共同形成了獨特的指紋。

引用此