SkillPlug: Unsupervised Skill Mining for Few-Shot Adaptation in Robotic Manipulation
For robotic manipulation, SkillPlug provides a scalable method to improve data-efficient generalization and few-shot adaptation without full end-to-end retraining.
SkillPlug introduces a plug-in framework that mines reusable skill libraries from multi-task demonstrations via self-supervised learning, enabling few-shot adaptation to new manipulation tasks by fine-tuning only lightweight components. On simulation benchmarks and a real robot, it improves multi-task performance and few-shot adaptation efficiency.
Learning transferable visuomotor imitation policies that generalize across diverse manipulation tasks and adapt rapidly to new tasks from only a handful of demonstrations remains challenging. Most modern policies are trained end-to-end to map observations directly to low-level actions, offering little explicit structure for reusing and recombining behaviors across tasks and making transfer data-inefficient under limited supervision. We propose SkillPlug, a plug-in framework that augments an existing visuomotor policy with a skill-conditioning module and mines a shared, transferable skill library from raw multi-task demonstrations. SkillPlug learns skills via self-supervised objectives that promote compact, reusable, and non-redundant behavior-level primitives, forming a task-shared prior for compositional control. After skill mining, we keep the learned skills fixed and specialize to unseen tasks by fine-tuning only lightweight router and action head, enabling efficient adaptation without full end-to-end retraining. We evaluate SkillPlug on two simulation benchmarks and on a real robot, and observe that the mined transferable skills consistently improve both multi-task performance and few-shot adaptation. Overall, SkillPlug offers a scalable way to mine reusable skills that improve data-efficient generalization in robotic manipulation.