Learning to Explore by Reinforcement over High-Level Options
This addresses the problem of efficient 3D environment exploration for applications like navigation, representing an incremental improvement over existing methods.
The paper tackles autonomous 3D environment exploration by proposing a method that grants an agent two intertwined options ('look-around' and 'frontier navigation') using an option-critic architecture trained with reinforcement learning, achieving higher coverage than competing techniques with better efficiency on two publicly available datasets.
Autonomous 3D environment exploration is a fundamental task for various applications such as navigation. The goal of exploration is to investigate a new environment and build its occupancy map efficiently. In this paper, we propose a new method which grants an agent two intertwined options of behaviors: "look-around" and "frontier navigation". This is implemented by an option-critic architecture and trained by reinforcement learning algorithms. In each timestep, an agent produces an option and a corresponding action according to the policy. We also take advantage of macro-actions by incorporating classic path-planning techniques to increase training efficiency. We demonstrate the effectiveness of the proposed method on two publicly available 3D environment datasets and the results show our method achieves higher coverage than competing techniques with better efficiency.