Learning-Based Strategy for Composite Robot Assembly Skill Adaptation
This work addresses industrial automation needs for adaptable robot assembly, but it is incremental as it builds on existing methods like RRL and skill-based approaches.
The paper tackled the challenge of contact-rich robotic assembly skills by proposing a reusable skill-based strategy using Residual Reinforcement Learning, achieving robust execution in simulation with a UR5e robot.
Contact-rich robotic skills remain challenging for industrial robots due to tight geometric tolerances, frictional variability, and uncertain contact dynamics, particularly when using position-controlled manipulators. This paper presents a reusable and encapsulated skill-based strategy for peg-in-hole assembly, in which adaptation is achieved through Residual Reinforcement Learning (RRL). The assembly process is represented using composite skills with explicit pre-, post-, and invariant conditions, enabling modularity, reusability, and well-defined execution semantics across task variations. Safety and sample efficiency are promoted through RRL by restricting adaptation to residual refinements within each skill during contact-rich interactions, while the overall skill structure and execution flow remain invariant. The proposed approach is evaluated in MuJoCo simulation on a UR5e robot equipped with a Robotiq gripper and trained using SAC and JAX. Results demonstrate that the proposed formulation enables robust execution of assembly skills, highlighting its suitability for industrial automation.