Rodrigues Network for Learning Robot Actions
This work addresses the challenge of predicting articulated actions in robotics, offering a domain-specific solution that is incremental in nature.
The paper tackled the problem of learning robot actions by proposing the Rodrigues Network, which integrates kinematic priors into neural architectures, resulting in significant improvements on synthetic tasks and realistic applications like imitation learning and 3D hand reconstruction.
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.