Learning Reusable Manipulation Strategies
This addresses the challenge of flexible and reusable robotic manipulation for applications in robotics and AI, though it appears incremental as it builds on existing planning methods.
The paper tackles the problem of enabling machines to acquire and generalize manipulation skills from single demonstrations, presenting a framework that interprets demonstrations as contact mode changes to learn continuous parameters, resulting in skills that can be integrated into task and motion planners for compositional use.
Humans demonstrate an impressive ability to acquire and generalize manipulation "tricks." Even from a single demonstration, such as using soup ladles to reach for distant objects, we can apply this skill to new scenarios involving different object positions, sizes, and categories (e.g., forks and hammers). Additionally, we can flexibly combine various skills to devise long-term plans. In this paper, we present a framework that enables machines to acquire such manipulation skills, referred to as "mechanisms," through a single demonstration and self-play. Our key insight lies in interpreting each demonstration as a sequence of changes in robot-object and object-object contact modes, which provides a scaffold for learning detailed samplers for continuous parameters. These learned mechanisms and samplers can be seamlessly integrated into standard task and motion planners, enabling their compositional use.