Interpretable UAV Collision Avoidance using Deep Reinforcement Learning

Abstract

The significant components of any successful autonomous flight system are task completion and collision avoidance. Most deep learning algorithms successfully execute these aspects under the environment and conditions they are trained. However, they fail when subjected to novel environments. This paper presents an autonomous multi-rotor flight algorithm, using Deep Reinforcement Learning augmented with Self-Attention Models, that can effectively reason when subjected to varying inputs. In addition to their reasoning ability, they are also interpretable, enabling it to be used under real-world conditions. We have tested our algorithm under different weather conditions and environments and found it robust compared to conventional Deep Reinforcement Learning algorithms.