Geometrically-Aware One-Shot Skill Transfer of Category-Level Objects
This addresses the problem of reducing training or pre-programming efforts for robotic manipulation in new environments, representing an incremental improvement in skill transfer methods.
The authors tackled robotic manipulation of unfamiliar objects by proposing a skill transfer framework that enables robots to replicate complex manipulation skills from a single human demonstration, achieving successful skill transfer and task execution in diverse real-world environments without additional training.
Robotic manipulation of unfamiliar objects in new environments is challenging and requires extensive training or laborious pre-programming. We propose a new skill transfer framework, which enables a robot to transfer complex object manipulation skills and constraints from a single human demonstration. Our approach addresses the challenge of skill acquisition and task execution by deriving geometric representations from demonstrations focusing on object-centric interactions. By leveraging the Functional Maps (FM) framework, we efficiently map interaction functions between objects and their environments, allowing the robot to replicate task operations across objects of similar topologies or categories, even when they have significantly different shapes. Additionally, our method incorporates a Task-Space Imitation Algorithm (TSIA) which generates smooth, geometrically-aware robot paths to ensure the transferred skills adhere to the demonstrated task constraints. We validate the effectiveness and adaptability of our approach through extensive experiments, demonstrating successful skill transfer and task execution in diverse real-world environments without requiring additional training.