analiza aiqbench
The paper proposes a learned robot policy that conditions on a single demonstration's contact trajectory, so it reads a physical-interaction spec from a prompt rather than only copying motion. The reported 78.7% success across wiping, rotation, and insertion on unseen objects, a 13-point gain over the best baseline, is meaningful but comes from real-world trials with a limited task set. Readers should watch whether the approach generalizes beyond these three tasks and how it handles the sensing and hardware required to estimate contact.
Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration
arXiv:2610.18848v1 Announce Type: new Abstract: In-context robot learning enables robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic specifications alone may not distinguish contact-rich behaviors that share similar motions but require different interaction intensities or patterns. We propose Contact Trajectory Prompting (CTP), a framework for one-shot transfer of contact-rich manipulation behaviors. CTP encodes motion and contact information from a single demonstration into an ordered contact trajectory prompt that captures their temporal evolution and specifies the desired physical interaction behavior. During execution, the policy uses online sensory feedback to retrieve interaction-relevant information from the prompt, conditioning closed-loop action generation on the demonstrated contact behavior. Across real-world wiping, rotation, and insertion tasks on objects excluded from training, CTP achieves 78.7% overall success, outperforming the strongest evaluated baseline by 13.0 percentage points. Changing only the reference demonstration enables CTP to follow contact specifications for both intensity and direction, including an intermediate wiping force level and clockwise or counterclockwise cap rotation. These results demonstrate that contact trajectories serve as effective behavioral specifications, extending in-context robot learning beyond motion imitation to physical interaction transfer. Project website: https://ctp-robotics.github.io/project_page.
Abstract:In-context robot learning enables robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic specifications alone may not distinguish contact-rich behaviors that share similar motions but require different interaction intensities or patterns. We propose Contact Trajectory Prompting (CTP), a framework for one-shot transfer of contact-rich manipulation behaviors. CTP encodes motion and contact information from a single demonstration into an ordered contact trajectory prompt that captures their temporal evolution and specifies the desired physical interaction behavior. During execution, the policy uses online sensory feedback to retrieve interaction-relevant information from the prompt, conditioning closed-loop action generation on the demonstrated contact behavior. Across real-world wiping, rotation, and insertion tasks on objects excluded from training, CTP achieves 78.7% overall success, outperforming the strongest evaluated baseline by 13.0 percentage points. Changing only the reference demonstration enables CTP to follow contact specifications for both intensity and direction, including an intermediate wiping force level and clockwise or counterclockwise cap rotation. These results demonstrate that contact trajectories serve as effective behavioral specifications, extending in-context robot learning beyond motion imitation to physical interaction transfer. Project website: this https URL.
Robotics (cs.RO)
arXiv:2610.18848 [cs.RO]
(or arXiv:2610.18848v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.18848 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.
Text integral sub licența deschisă a publicației · 278 cuvinte
Subiecte conexe
Evaluating task vectors, unlearning and inoculation
LessWrong · 20 sept. 2026
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · 3 aug. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
Echoverse: Deep, evolving environments for computer-use agents
Microsoft Research · 30 iul. 2026