RoboAssembly: Learning Generalizable Furniture Assembly Policy in a Novel Multi-robot Contact-rich Simulation Environment
This addresses the challenge of generalizable robotic assembly for furniture, though it is incremental as it builds on existing simulation and RL methods.
The paper tackles the problem of robotic furniture assembly by developing a simulation environment and reinforcement learning pipeline, achieving success rates of 74.5% and 50.0% on unseen chairs compared to a baseline of 18.8%.
Part assembly is a typical but challenging task in robotics, where robots assemble a set of individual parts into a complete shape. In this paper, we develop a robotic assembly simulation environment for furniture assembly. We formulate the part assembly task as a concrete reinforcement learning problem and propose a pipeline for robots to learn to assemble a diverse set of chairs. Experiments show that when testing with unseen chairs, our approach achieves a success rate of 74.5% under the object-centric setting and 50.0% under the full setting. We adopt an RRT-Connect algorithm as the baseline, which only achieves a success rate of 18.8% after a significantly longer computation time. Supplemental materials and videos are available on our project webpage.