Rope Manipulation
Rope manipulation research focuses on developing algorithms and robotic systems capable of effectively interacting with and controlling deformable ropes, addressing challenges posed by their complex physics and inherent uncertainty. Current efforts concentrate on improving model-based and data-driven approaches, including differentiable physics simulators and parameter-aware policies that enable one-shot learning and generalization across different rope types. These advancements are crucial for applications ranging from surgical robotics and industrial automation to autonomous driving, where robust rope handling is essential for improved efficiency and safety. The development of more generalizable and data-efficient methods remains a key focus.
Papers
Focused Adaptation of Dynamics Models for Deformable Object Manipulation
Peter Mitrano, Alex LaGrassa, Oliver Kroemer, Dmitry Berenson
Bimanual rope manipulation skill synthesis through context dependent correction policy learning from human demonstration
T. Baturhan Akbulut, G. Tuba C. Girgin, Arash Mehrabi, Minoru Asada, Emre Ugur, Erhan Oztop