EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Framework for Spatially Generalizable Contact-rich Tasks
EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Framework for Spatially Generalizable Contact-rich Tasks
This paper presents EquiContact, a hierarchical framework for learning vision-based robotic policies in contact-rich manipulation tasks that generalize across spatial configurations.
The paper introduces EquiContact, a hierarchical SE(3)-equivariant framework combining a Diffusion Equivariant Descriptor Field for planning and a Geometric Compliant Action Chunking Transformer for low-level control, validated on peg-in-hole insertion tasks with near-perfect success rates in spatially out-of-distribution configurations.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- paper: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
arXiv:2507.10961v5 Announce Type: replace Abstract: This paper presents a framework for learning vision-based robotic policies for contact-rich manipulation tasks, which generalize spatially across task configurations. We propose EquiContact, a novel hierarchical framework composed of a high-level vision planner, such as a Diffusion Equivariant Descriptor Field (Diff-EDF) and a low-level compliant visuomotor policy,
Open source S2
such as a Geometric Compliant Action Chunking Transformer (G-CompACT). G-CompACT, operating using localized observations from wrist-mounted RGB images, end-effector pose feedback in the form of a geometrically consistent error vector (GCEV) and force-torque readings, produces actions defined on the end-effector frame. We show that the entire EquiContact pipeline is $\SE$-equivariant under equivariant reference-frame
Open source S3
estimation and left-invariant visual features, from perception to force control. Once the robot learns to execute a contact-rich task, such as inserting a peg-in-hole (PiH), it can execute similar tasks at different locations and orientations without retraining of the low-level policy. We also describe three key components for attaining spatially generalizable contact-rich policies: geometrically consistent complianc
Open source S4
e, the use of localized policies, and induced equivariance. Real-world peg-in-hole (PiH) experiments demonstrate near-perfect success rates under spatially out-of-distribution configurations, validating the proposed framework and principles, while additional screwing and surface-wiping experiments evaluate the transfer of the localized policy design beyond insertion. The experimental videos and more details can be fo
Open source S5
und on the project website: https://equicontact.github.io/EquiContact-website/
Open source S6
EquiContact: A Hierarchical SE(3) Vision-to-Force Equivariant Framework for Spatially Generalizable Contact-rich Tasks
Open source S1
Source：arXiv Robotics — research abstracts · arxiv.org