Curiosity-driven Exploration for Mapless Navigation with Deep Reinforcement Learning
It addresses exploration challenges in robot navigation for applications like indoor or dynamic environments, but is incremental as it builds on existing curiosity methods in DRL.
This paper tackles the problem of learning navigation policies for mobile robots in mapless settings by augmenting deep reinforcement learning with curiosity-driven intrinsic rewards, resulting in improved performance and better generalization to unseen environments.
This paper investigates exploration strategies of Deep Reinforcement Learning (DRL) methods to learn navigation policies for mobile robots. In particular, we augment the normal external reward for training DRL algorithms with intrinsic reward signals measured by curiosity. We test our approach in a mapless navigation setting, where the autonomous agent is required to navigate without the occupancy map of the environment, to targets whose relative locations can be easily acquired through low-cost solutions (e.g., visible light localization, Wi-Fi signal localization). We validate that the intrinsic motivation is crucial for improving DRL performance in tasks with challenging exploration requirements. Our experimental results show that our proposed method is able to more effectively learn navigation policies, and has better generalization capabilities in previously unseen environments. A video of our experimental results can be found at https://goo.gl/pWbpcF.