Learning Sequences of Manipulation Primitives for Robotic Assembly
It addresses robust robotic assembly for industrial applications, with incremental improvements in generalization and sim2real transfer.
The paper tackles robotic assembly by representing it as sequences of Manipulation Primitives learned via Reinforcement Learning, achieving excellent success rates in sim2real transfer for tasks like round peg insertion with 0.04 mm clearance.
This paper explores the idea that skillful assembly is best represented as dynamic sequences of Manipulation Primitives, and that such sequences can be automatically discovered by Reinforcement Learning. Manipulation Primitives, such as "Move down until contact", "Slide along x while maintaining contact with the surface", have enough complexity to keep the search tree shallow, yet are generic enough to generalize across a wide range of assembly tasks. Moreover, the additional "semantics" of the Manipulation Primitives make them more robust in sim2real and against model/environment variations and uncertainties, as compared to more elementary actions. Policies are learned in simulation, and then transferred onto a physical platform. Direct sim2real transfer (without retraining in real) achieves excellent success rates on challenging assembly tasks, such as round peg insertion with 0.04 mm clearance or square peg insertion with large hole position/orientation estimation errors.