Toward End-to-End Control for UAV Autonomous Landing via Deep Reinforcement Learning
- 1 June 2018
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The autonomous landing of an unmanned aerial vehicle (UAV) is still an open problem. Previous work focused on the use of hand-crafted geometric features and sensor-data fusion for identifying a fiducial marker and guide the UAV toward it. In this article we propose a method based on deep reinforcement learning that only requires low-resolution images coming from a down looking camera in order to drive the vehicle. The proposed approach is based on a hierarchy of Deep Q-Networks (DQNs) that are used as high-end control policy for the navigation in different phases. We implemented various technical solutions, such as the combination of vanilla and double DQNs trained using a form of prioritized buffer replay that separates experiences in multiple containers. The optimal control policy is learned without any human supervision, providing the agent with a sparse reward feedback indicating the success or failure of the landing. The results show that the quadrotor can autonomously land on a large variety of simulated environments and with relevant noise, proving that the underline DQNs are able to generalise effectively on unseen scenarios. Furthermore, it was proved that in some conditions the network outperformed human pilots.Keywords
This publication has 24 references indexed in Scilit:
- Continuous on-board monocular-vision-based elevation mapping applied to autonomous landing of micro aerial vehiclesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Human-level control through deep reinforcement learningNature, 2015
- Language Understanding for Text-based Games using Deep Reinforcement LearningPublished by Association for Computational Linguistics (ACL) ,2015
- Deep learning in neural networks: An overviewNeural Networks, 2015
- A survey of autonomous landing techniques for UAVsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Autonomous reinforcement learning with experience replayNeural Networks, 2013
- Airborne Vision-Based Navigation Method for UAV Accuracy Landing Using Infrared LampsJournal of Intelligent & Robotic Systems, 2013
- A UAV for bridge inspection: Visual servoing control law with orientation limitsAutomation in Construction, 2007
- Landing on a Moving Target Using an Autonomous HelicopterPublished by Springer Science and Business Media LLC ,2006
- Imaging from an unmanned aerial vehicle: agricultural surveillance and decision supportComputers and Electronics in Agriculture, 2004