Collision-Free UAV Navigation with a Monocular Camera Using Deep Reinforcement Learning
Authors:
- 1 September 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Small unmanned aerial vehicles (UAV) with reduced sensing and communication capabilities can support potential use cases in different indoor environments such as automated factories or commercial buildings. In this context, we consider the problem of collision-free autonomous UAV navigation supported by a simple sensor. We propose a navigation system based on object detection and deep reinforcement learning (DRL) that only exploits sensing data obtained by a monocular camera mounted on the UAV. Object detection is incorporated into DRL training to reduce flight time and to maximize the probability of avoiding both current and future crashes. Moreover, object detection also helps to remove the impact of wrong predictions from the deep network. When compared to schemes using traditional RL methods, the proposed framework not only leads to collision- free trips, but it also reduces flying times towards given destinations by 25%, and cuts down 50% of unnecessary turns.Keywords
This publication has 15 references indexed in Scilit:
- Learning to fly by crashing2017
- Speed/Accuracy Trade-Offs for Modern Convolutional Object Detectors2017
- Survey on Computer Vision for UAVs: Current Developments and TrendsJournal of Intelligent & Robotic Systems, 2017
- Development of an indoor guidance system for unmanned aerial vehicles with power industry applicationsIET Radar, Sonar & Navigation, 2017
- Autonomous flight and obstacle avoidance of a quadrotor by monocular SLAM2016
- Visual–Inertial Navigation Systems for Aerial Robotics: Sensor Fusion and TechnologyIEEE Transactions on Automation Science and Engineering, 2016
- Self-calibrating multi-sensor fusion with probabilistic measurement validation for seamless sensor switching on a UAV2016
- Collision Avoidance for Quadrotors with a Monocular Camera2015
- A UAV system for inspection of industrial facilities2013
- Q-learningMachine Learning, 1992