Leveraging Procedural Generation for Learning Autonomous Peg-in-Hole Assembly in Space
This addresses the challenge of unpredictable space conditions for robotic assembly, though it is incremental as it builds on existing simulation and learning techniques.
The study tackled autonomous peg-in-hole assembly for space robotics by using procedural generation and domain randomization with deep reinforcement learning in simulation, demonstrating adaptability to novel scenarios and assembly sequences.
The ability to autonomously assemble structures is crucial for the development of future space infrastructure. However, the unpredictable conditions of space pose significant challenges for robotic systems, necessitating the development of advanced learning techniques to enable autonomous assembly. In this study, we present a novel approach for learning autonomous peg-in-hole assembly in the context of space robotics. Our focus is on enhancing the generalization and adaptability of autonomous systems through deep reinforcement learning. By integrating procedural generation and domain randomization, we train agents in a highly parallelized simulation environment across a spectrum of diverse scenarios with the aim of acquiring a robust policy. The proposed approach is evaluated using three distinct reinforcement learning algorithms to investigate the trade-offs among various paradigms. We demonstrate the adaptability of our agents to novel scenarios and assembly sequences while emphasizing the potential of leveraging advanced simulation techniques for robot learning in space. Our findings set the stage for future advancements in intelligent robotic systems capable of supporting ambitious space missions and infrastructure development beyond Earth.