Rodrigues Network for Learning Robot Actions

ICLR 2026 Conference Submission14589 Authors

Keywords: Robot learning, Action understanding, Neural architecture

TL;DR: We design a new neural network, the Rodrigues Network (RodriNet), that addresses the kinematic structural priors in articulated robot action learning.

Abstract: Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the underlying kinematic structure of articulated systems. To this end, we propose the **Neural Rodrigues Operator**, a learnable generalization of the classical forward kinematics operation, designed to inject kinematics-aware inductive bias into neural computation. Building on this operator, we design the **Rodrigues Network (RodriNet)**, a novel neural architecture specialized for processing actions. We evaluate the expressivity of our network on two synthetic tasks on kinematic and motion prediction, showing significant improvements compared to standard backbones. We further demonstrate its effectiveness in two realistic applications: (i) imitation learning on robotic benchmarks with the Diffusion Policy, and (ii) single-image 3D hand reconstruction. Our results suggest that integrating structured kinematic priors into the network architecture improves action learning in various domains.

Primary Area: applications to robotics, autonomy, planning

Submission Number: 14589