How To Train Your HERON
This addresses autonomous navigation in natural environments for robotics, though it is incremental as it applies existing methods to a specific domain.
The paper tackled autonomous navigation for an Unmanned Surface Vehicle using Deep Reinforcement Learning and Domain Randomization in simulation, achieving successful zero-shot transfer to real-world lake and river environments with improved robustness, speed, and accuracy over a baseline controller.
In this paper we apply Deep Reinforcement Learning (Deep RL) and Domain Randomization to solve a navigation task in a natural environment relying solely on a 2D laser scanner. We train a model-based RL agent in simulation to follow lake and river shores and apply it on a real Unmanned Surface Vehicle in a zero-shot setup. We demonstrate that even though the agent has not been trained in the real world, it can fulfill its task successfully and adapt to changes in the robot's environment and dynamics. Finally, we show that the RL agent is more robust, faster, and more accurate than a state-aware Model-Predictive-Controller.