aiqbench analysis
This research introduces LeCo, a novel framework that resolves coordination failures between learning policies and compliant controllers in robotic assembly tasks. By integrating multirate feedback and specific conflict costs, the method significantly reduces unproductive loading forces while maintaining high task success rates on real-world connector insertion scenarios. The work advances reliable autonomous manufacturing by enabling robots to effectively leverage physical compliance despite pose errors and contact uncertainty.
Learning to Leverage Compliance: A Policy-Admittance Learning Framework for Robotic Insertion
arXiv:2609.31439v1 Announce Type: new Abstract: Policy learning and compliant control offer a promising route to reliable autonomous assembly under pose errors and contact uncertainty. However, combining them does not ensure coordination: the policy may continue pushing against contact while the controller yields, producing sustained loading with limited progress. To address this problem, we propose LeCo (Leverage Compliance), a policy-admittance learning framework that guides a visual policy through execution-time interaction under fixed admittance. A multirate feedback mechanism aggregates high-rate contact-interaction records into policy-transition rewards. An integrated conflict cost then characterizes sustained policy-loading/controller-unloading opposition, while a directional high-force tail cost captures continued-loading events within a transition. Together with task completion, these costs encourage the policy to leverage compliance with less unproductive loading. We evaluate LeCo on four real connector-assembly tasks, obtaining an aggregate success rate of 94%. Across tasks, mean successful-trial resultant-force and torque peaks decrease by approximately 30% and 64% relative to the comparison baseline. Reward ablation further shows that adding conflict shaping reduces median successful-trial contact-conditioned conflict density by approximately 53%. These results support learning to leverage fixed compliance by turning multirate policy-admittance interaction into complementary reward signals for effective, lower-load insertion.
Abstract:Policy learning and compliant control offer a promising route to reliable autonomous assembly under pose errors and contact uncertainty. However, combining them does not ensure coordination: the policy may continue pushing against contact while the controller yields, producing sustained loading with limited progress. To address this problem, we propose LeCo (Leverage Compliance), a policy-admittance learning framework that guides a visual policy through execution-time interaction under fixed admittance. A multirate feedback mechanism aggregates high-rate contact-interaction records into policy-transition rewards. An integrated conflict cost then characterizes sustained policy-loading/controller-unloading opposition, while a directional high-force tail cost captures continued-loading events within a transition. Together with task completion, these costs encourage the policy to leverage compliance with less unproductive loading. We evaluate LeCo on four real connector-assembly tasks, obtaining an aggregate success rate of 94%. Across tasks, mean successful-trial resultant-force and torque peaks decrease by approximately 30% and 64% relative to the comparison baseline. Reward ablation further shows that adding conflict shaping reduces median successful-trial contact-conditioned conflict density by approximately 53%. These results support learning to leverage fixed compliance by turning multirate policy-admittance interaction into complementary reward signals for effective, lower-load insertion.
Robotics (cs.RO)
arXiv:2609.31439 [cs.RO]
(or arXiv:2609.31439v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2609.31439 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 · 280 words
Related coverage
Why I Left Google DeepMind
LessWrong · Jul 15, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Residual Compliant Policy: Learning Compliant Policies from Few Demonstrations
arXiv · Oct 14, 2026
PAKT: Physically-Aligned Kinesthetic Teaching for Reinforcement Learning
arXiv · Sep 24, 2026