aiqbench analysis
This research introduces Stiffness Copilot, a vision-based policy that dynamically adjusts robot impedance during teleoperation to balance safety and efficiency in contact-rich tasks. By leveraging wrist-camera images for zero-shot transfer from simulation to reality, the system enables operators to command pose while an AI agent manages force application online. The approach successfully matches high-stiffness efficiency with low-stiffness safety levels without requiring privileged data at runtime.
Stiffness Copilot: An Impedance Policy for Contact-Rich Teleoperation
arXiv:2603.14068v2 Announce Type: replace Abstract: In teleoperation of contact-rich manipulation tasks, selecting robot impedance is critical but difficult. The robot must be compliant to avoid damaging the environment, but stiff to remain responsive and to apply force when needed. In this paper, we present Stiffness Copilot, a vision-based policy for shared-control teleoperation in which the operator commands robot pose and the policy adjusts robot impedance online. To train Stiffness Copilot, we first infer direction-dependent stiffness matrices in simulation using privileged contact information. We then use these matrices to supervise a lightweight vision policy that predicts robot stiffness from wrist-camera images and transfers zero-shot to real images at runtime. In a human-subject study, Stiffness Copilot achieved safety comparable to using a constant low stiffness while matching the efficiency of using a constant high stiffness.
Abstract:In teleoperation of contact-rich manipulation tasks, selecting robot impedance is critical but difficult. The robot must be compliant to avoid damaging the environment, but stiff to remain responsive and to apply force when needed. In this paper, we present Stiffness Copilot, a vision-based policy for shared-control teleoperation in which the operator commands robot pose and the policy adjusts robot impedance online. To train Stiffness Copilot, we first infer direction-dependent stiffness matrices in simulation using privileged contact information. We then use these matrices to supervise a lightweight vision policy that predicts robot stiffness from wrist-camera images and transfers zero-shot to real images at runtime. In a human-subject study, Stiffness Copilot achieved safety comparable to using a constant low stiffness while matching the efficiency of using a constant high stiffness.
Accepted to IROS 2026. Project website: this https URL
Robotics (cs.RO)
arXiv:2603.14068 [cs.RO]
(or arXiv:2603.14068v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2603.14068 Focus to learn more arXiv-issued DOI via DataCite
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 · 228 words
Related coverage
Imp-ACT: Adaptive Impedance Control and Action Chunking with Transformers to Learn Contact-Rich Manipulation from Demonstrations
arXiv · Sep 28, 2026
Learning Reflexive Behavior for Contact-Rich Manipulation
arXiv · Oct 5, 2026
Compliance for Free: Learning Identifiable Impedance via Bilateral Teleoperation
arXiv · Sep 18, 2026
Bridging Handheld and Teleoperated Supervision for Contact-Rich Manipulation via State-Gated Experts
arXiv · Sep 22, 2026