analiza aiqbench
EmbodiSteer addresses a critical bottleneck in robot imitation learning by enabling Cartesian policies to safely adapt to specific physical bodies without retraining. By integrating joint-space collision guidance during inference, the framework significantly reduces failure rates when deploying models across heterogeneous robotic hardware. This advancement is essential for scaling embodied AI systems that must operate reliably within complex, constrained environments using diverse platforms.
EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
arXiv:2606.12965v1 Announce Type: new Abstract: Scalable robot imitation learning relies on large-scale heterogeneous data from diverse robots or body-free data, making Cartesian end-effector actions a key interface for embodiment-agnostic policy learning. However, end-effector-only abstraction leaves Cartesian policies unaware of the deployed robot body, making them brittle under robot-specific constraints such as whole-body collision avoidance. To overcome this limitation, we present EmbodiSteer, a training-free framework that steers embodiment-agnostic visuomotor policies toward zero-shot, embodiment-aware deployment. EmbodiSteer keeps policy learning in Cartesian space while efficiently lifting inference-time diffusion sampling into the target robot's joint space via forward kinematics and Jacobian-based updates. With whole-body collision-aware guidance over joint trajectories after each denoising step, the arm can be steered away from collisions while preserving learned end-effector behavior. Compared with Cartesian-only execution, EmbodiSteer reduces collision rate by 46.1% and improves task success rate by 28.5% across 9 simulated robots, and further achieves 90.0% collision rate reduction and 36.7% success rate increase on two physical robots in highly constrained scenarios. Our project page is at https://frankwang67.github.io/EmbodiSteer-Page.
Abstract:Scalable robot imitation learning relies on large-scale heterogeneous data from diverse robots or body-free data, making Cartesian end-effector actions a key interface for embodiment-agnostic policy learning. However, end-effector-only abstraction leaves Cartesian policies unaware of the deployed robot body, making them brittle under robot-specific constraints such as whole-body collision avoidance. To overcome this limitation, we present EmbodiSteer, a training-free framework that steers embodiment-agnostic visuomotor policies toward zero-shot, embodiment-aware deployment. EmbodiSteer keeps policy learning in Cartesian space while efficiently lifting inference-time diffusion sampling into the target robot's joint space via forward kinematics and Jacobian-based updates. With whole-body collision-aware guidance over joint trajectories after each denoising step, the arm can be steered away from collisions while preserving learned end-effector behavior. Compared with Cartesian-only execution, EmbodiSteer reduces collision rate by 46.1% and improves task success rate by 28.5% across 9 simulated robots, and further achieves 90.0% collision rate reduction and 36.7% success rate increase on two physical robots in highly constrained scenarios. Our project page is at this https URL.
Robotics (cs.RO)
arXiv:2606.12965 [cs.RO]
(or arXiv:2606.12965v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.12965 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 · 259 cuvinte
Subiecte conexe
EmbodiSteer: Steering Embodiment-Agnostic Visuomotor Policies with Joint-Space Guidance for Zero-Shot Cross-Embodiment Deployment
arXiv · 14 oct. 2026
Latent Policy Steering: An Efficient and Flexible Framework for Cross-Embodiment Transfer
arXiv · 22 sept. 2026
Building a Foundation Stack for General-Purpose Robots
IEEE Spectrum · 13 iul. 2026
Game-Theoretic Disempowerment: Loss of Control to Agencyless AI
LessWrong · 27 sept. 2026