aiqbench analysis
This paper introduces CODES, a framework that leverages weakly supervised learning and reinforcement learning to discover and compose distinct motion styles for robots with redundant degrees of freedom. By successfully deploying on physical hardware like the Unitree Go2, the method demonstrates improved kinematic coherence and robust generalization beyond training data distributions. The work represents a significant advancement in machine learning applications for robotics control, specifically addressing how to balance independent task commands with preserved stylistic characteristics.
Weakly Supervised Discovery of Motion Styles for Compositional Robot Control
arXiv:2610.24008v1 Announce Type: cross Abstract: When a robot possesses more degrees of freedom than a task requires, multiple trajectories can achieve the same objective using distinct motion styles. Compositional robot control aims to preserve a selected style while simultaneously executing an independent task command, effectively balancing these potentially competing objectives. In this paper, we present CODES, a framework for compositional robot control that discovers a coherent style repertoire from diverse recordings and composes it with independent commands. First, motion retargeting maps the recordings to motions executable by the target robot; next, weakly supervised consensus encoding and density-based clustering identify styles within and across recordings without a prescribed count; finally, reinforcement learning trains a policy to compose the discovered styles with independent commands. We evaluate CODES on a Unitree Go2 quadruped across two simulators and physical hardware. Compared to baselines, CODES significantly improves kinematic coherence. Furthermore, our controller successfully tracks velocity commands that generalize beyond the support of the recorded data, exhibiting robust and distinguishable style characteristics during both cross-simulator and real-world hardware deployments. Project website: https://www.proroklab.org/compositional-motion-styles/
Abstract:When a robot possesses more degrees of freedom than a task requires, multiple trajectories can achieve the same objective using distinct motion styles. Compositional robot control aims to preserve a selected style while simultaneously executing an independent task command, effectively balancing these potentially competing objectives. In this paper, we present CODES, a framework for compositional robot control that discovers a coherent style repertoire from diverse recordings and composes it with independent commands. First, motion retargeting maps the recordings to motions executable by the target robot; next, weakly supervised consensus encoding and density-based clustering identify styles within and across recordings without a prescribed count; finally, reinforcement learning trains a policy to compose the discovered styles with independent commands. We evaluate CODES on a Unitree Go2 quadruped across two simulators and physical hardware. Compared to baselines, CODES significantly improves kinematic coherence. Furthermore, our controller successfully tracks velocity commands that generalize beyond the support of the recorded data, exhibiting robust and distinguishable style characteristics during both cross-simulator and real-world hardware deployments. Project website: this https URL
Robotics (cs.RO); Machine Learning (cs.LG)
arXiv:2610.24008 [cs.RO]
(or arXiv:2610.24008v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.24008 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 · 269 words
Related coverage
[AINews] not much happened today
Latent Space · Sep 10, 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · Sep 17, 2026
EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Data
arXiv · Oct 15, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026