Toward Agile Maneuvers in Highly Constrained Spaces: Learning from Hallucination
This addresses the challenge of enabling agile maneuvers for robots in highly constrained spaces without risking collisions during training, offering a safer and more efficient solution compared to existing methods.
The paper tackles the problem of autonomous robot navigation in tightly constrained spaces by introducing a new paradigm called learning from hallucination (LfH), which uses safe training data to achieve fast, smooth, and safe navigation, outperforming three baselines on a real robot and generalizing to unseen environments.
While classical approaches to autonomous robot navigation currently enable operation in certain environments, they break down in tightly constrained spaces, e.g., where the robot needs to engage in agile maneuvers to squeeze between obstacles. Recent machine learning techniques have the potential to address this shortcoming, but existing approaches require vast amounts of navigation experience for training, during which the robot must operate in close proximity to obstacles and risk collision. In this paper, we propose to side-step this requirement by introducing a new machine learning paradigm for autonomous navigation called learning from hallucination (LfH), which can use training data collected in completely safe environments to compute navigation controllers that result in fast, smooth, and safe navigation in highly constrained environments. Our experimental results show that the proposed LfH system outperforms three autonomous navigation baselines on a real robot and generalizes well to unseen environments, including those based on both classical and machine learning techniques.