aiqbench analysis
This paper proposes a robot manipulation pipeline that makes compliance explicit during teleoperated data collection, uses Laplacian editing with trajectory optimization to generalize across object poses, and refines interaction forces with residual reinforcement learning. The reported gains (40/40 out-of-distribution trials versus 33/40 and 24/40 for baselines, and 35/40 for the base policy alone) come from only three tasks and seven demonstrations on one robot, so the results are promising but need broader testing. For ML readers, the useful takeaway is the combination of few-shot imitation learning with residual RL in contact-rich settings.
Residual Compliant Policy: Learning Compliant Policies from Few Demonstrations
arXiv:2610.14035v1 Announce Type: new Abstract: Contact-rich manipulation requires a robot to be precise in free space to establish the intended contacts, and compliant once in contact to avoid excessive forces. Imitation learning has proven effective for simpler manipulation tasks, but the compliance underlying a demonstration is not directly observable and is therefore difficult to infer from demonstration data alone. We present a framework that makes compliance explicit at every stage. During data collection, the operator teleoperates the real robot while a synchronized digital twin visualizes the error between the commanded reference and the achieved pose, making the current compliance visible, and selects between two discrete compliance modes. To generalize across object poses, we combine Laplacian editing, which retargets trajectories efficiently but is not physics-consistent during contact, with simulation-based trajectory optimization, which enforces physical plausibility but offers no manual guidance. Finally, a residual reinforcement learning policy refines the interaction forces by adjusting the reference pose of the underlying admittance controller. We evaluate on three flipping and pushing tasks on a Franka FR3 based on a total of 7 demonstrations across tasks. Our method is successful on all 40 out-of-distribution trials, compared to 33/40 and 24/40 for two baselines, with our base policy alone reaching 35/40.
Abstract:Contact-rich manipulation requires a robot to be precise in free space to establish the intended contacts, and compliant once in contact to avoid excessive forces. Imitation learning has proven effective for simpler manipulation tasks, but the compliance underlying a demonstration is not directly observable and is therefore difficult to infer from demonstration data alone. We present a framework that makes compliance explicit at every stage. During data collection, the operator teleoperates the real robot while a synchronized digital twin visualizes the error between the commanded reference and the achieved pose, making the current compliance visible, and selects between two discrete compliance modes. To generalize across object poses, we combine Laplacian editing, which retargets trajectories efficiently but is not physics-consistent during contact, with simulation-based trajectory optimization, which enforces physical plausibility but offers no manual guidance. Finally, a residual reinforcement learning policy refines the interaction forces by adjusting the reference pose of the underlying admittance controller. We evaluate on three flipping and pushing tasks on a Franka FR3 based on a total of 7 demonstrations across tasks. Our method is successful on all 40 out-of-distribution trials, compared to 33/40 and 24/40 for two baselines, with our base policy alone reaching 35/40.
9 pages, 6 figures. Project website: this https URL
Robotics (cs.RO)
arXiv:2610.14035 [cs.RO]
(or arXiv:2610.14035v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.14035 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 · 301 words
Related coverage
Compliant GMT: Making General Motion Tracking Compliant via Residual Reference Adaptation
arXiv · Oct 16, 2026
Force-Aware Residual DAgger via Trajectory Editing for Precision Insertion with Impedance Control
arXiv · Jul 24, 2026
CompliantWBC: Whole-Body Compliance for Heavy Humanoids via Force Latent Estimation and Residual Impedance Targets
arXiv · Sep 29, 2026
Intent-guided Adaptive Stiffening for Visuomotor Policies under Unknown Resistance
arXiv · Oct 14, 2026