aiqbench analysis
This research advances machine learning for robotics by introducing a Learning from Demonstration method that explicitly models physical contact interactions, enabling single-shot acquisition of complex manipulation tasks like opening locks or screwing bolts. By integrating these interaction cues into hybrid position-force controllers, the approach significantly improves robustness to geometric variations and facilitates online adaptation without prior task knowledge. This work directly addresses a critical gap in interpretable few-shot learning for robotic systems, moving beyond trajectory tracking to understand the underlying physics of human demonstrations.
One-Shot Learning from Demonstration of Contact-Rich Robotic Manipulation by Identifying Physical Interactions
arXiv:2608.24741v1 Announce Type: new Abstract: Learning from Demonstration (LfD) allows robots to learn manipulation tasks directly from humans, thereby supporting the versatile application of robots. Most LfD methods do not explicitly model the physical interactions between a robot and its environment, such as the making and breaking of contact, while these are crucial during manipulation tasks. Because the same basic physical interactions recur often, they can be a basis for robust, generalizable, and adaptive task reproduction. We propose an LfD method that explicitly uses what physical interactions take place where and when. Using that information, a hybrid position-force controller tracks demonstrated trajectories until contact-based transition conditions from the demonstrations are met. We evaluate our method in real robot experiments consisting of opening doors and locks, bolt picking and screwing, dislodging, and surface contouring. We show that explicitly modeling physical interactions benefits LfD in four ways. First, by allowing reproduction of complex, sequential, and contact-rich manipulation tasks using only a single demonstration and no prior knowledge of the task. Second, by facilitating robustness to unknown geometric variations in the environment. Third, by facilitating generalization when geometric variations are known. Fourth, by facilitating online adaptation using geometric information explored during task reproduction. We discuss how robustness, generalization, and adaptivity can be explicitly implemented, which is generally lacking in the LfD literature. Thereby, our work aims to close a gap in interpretable few-shot LfD of robotic manipulation.
Abstract:Learning from Demonstration (LfD) allows robots to learn manipulation tasks directly from humans, thereby supporting the versatile application of robots. Most LfD methods do not explicitly model the physical interactions between a robot and its environment, such as the making and breaking of contact, while these are crucial during manipulation tasks. Because the same basic physical interactions recur often, they can be a basis for robust, generalizable, and adaptive task reproduction. We propose an LfD method that explicitly uses what physical interactions take place where and when. Using that information, a hybrid position-force controller tracks demonstrated trajectories until contact-based transition conditions from the demonstrations are met. We evaluate our method in real robot experiments consisting of opening doors and locks, bolt picking and screwing, dislodging, and surface contouring. We show that explicitly modeling physical interactions benefits LfD in four ways. First, by allowing reproduction of complex, sequential, and contact-rich manipulation tasks using only a single demonstration and no prior knowledge of the task. Second, by facilitating robustness to unknown geometric variations in the environment. Third, by facilitating generalization when geometric variations are known. Fourth, by facilitating online adaptation using geometric information explored during task reproduction. We discuss how robustness, generalization, and adaptivity can be explicitly implemented, which is generally lacking in the LfD literature. Thereby, our work aims to close a gap in interpretable few-shot LfD of robotic manipulation.
Robotics (cs.RO)
arXiv:2608.24741 [cs.RO]
(or arXiv:2608.24741v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2608.24741 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 322 words
Related coverage
Dex-X: Learning Visual-Tactile Dexterous Manipulation From Human Videos with Simulated Interaction
arXiv · Sep 9, 2026
PHASE: Compliance-Enabled Tactile Phase Retrieval for Few-Shot Insertion Learning
arXiv · Sep 28, 2026
Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration
arXiv · Oct 14, 2026
Morphometric Imitation: From Morphology and Contact Aware Hand Retargeting to Sim-to-Real Visuomotor Policy
arXiv · Sep 25, 2026