ROPES: Robotic Pose Estimation via Score-based Causal Representation Learning

ICLR 2026 Conference Submission20481 Authors

Keywords: Causal Representational Learning

Abstract:

Causal representation learning (CRL) has emerged as a powerful unsupervised
framework that can (i) disentangle the latent generative factors underlying highdimensional data, and (ii) learn the cause-and-effect interactions among the disentangled variables. There have been extensive recent advances in the identifiability
aspects of CRL, accompanied by some practical progress. However, a substantial
gap remains between theory and real-world practice. This paper takes a step toward
closing that gap by bringing CRL into robotics, a domain that has motivated CRL.
Specifically, this paper addresses the well-defined robot pose estimation – the
recovery of position and orientation from raw images – by introducing RObotic
Pose Estimation via Score-Based CRL (ROPES). Being an unsupervised framework, ROPES embodies the essence of interventional CRL by identifying those
generative factors that are actuated: images are generated by intrinsic and extrinsic
latent factors (e.g., joint angles, arm/limb geometry, lighting, background, and
camera configuration) and the objective is to disentangle and recover the controllable latent variables, i.e., those that can be directly manipulated (intervened
upon) through actuation. Interventional CRL theory establishes that variables
that undergo variations induced by interventions can be identified. In robotics,
such interventions arise naturally by commanding actuators of various joints and
recording images under varied controls. Empirical evaluations in semi-synthetic
manipulator experiments demonstrate that ROPES successfully disentangles latent
generative factors with high fidelity with respect to the ground truth. Crucially, this
is achieved by leveraging only distributional changes, without using any labeled
data. The paper also includes a comparison with a baseline based on a recently
proposed semi-supervised framework. This paper concludes by positioning robot
pose estimation as a near-practical testbed for CRL.

Primary Area: causal reasoning

Submission Number: 20481