Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning

Deep Reinforcement Learning (DRL), deploying deep neural networks as function approximators for highdimensional RL tasks, achieves state of the art performance in various fields of research [1]. DRL algorithms have been studied under the context of learning navigation policies for mobile robots. Traditional navigation solutions in robotics generally require a system of procedures, such as Simultaneous Localization and Mapping (SLAM) [2], localization and path planning in a given map, etc. With the powerful representation learning capabilities of deep networks, DRL methods bring about the possibility of learning control policies directly from raw sensory inputs, bypassing all the intermediate steps. Eliminating the requirement for localization, mapping, or path planning procedures, several DRL works have been presented that learn successful navigation policies directly from raw sensor inputs: target-driven navigation [3], successor feature RL for transferring navigation policies [4], and using auxiliary tasks to boost DRL training [5]. Many followup works have also been proposed, such as embedding SLAMlike structures into DRL networks [6], or utilizing DRL for multi-robot collision avoidance [7]. In this paper, we focus specifically on mapless navigation, where the agent is expected to navigate to a designated goal location without the knowledge of the map of its current environment.