Diffusion-based Inverse Model of a Distributed Tactile Sensor for Object Pose Estimation

2026-01-19

AI Summary

This work addresses the challenge of multimodal ambiguity in tactile pose estimation under visually degraded conditions, where partial observability leads to inherent uncertainty. The authors propose the first application of denoising diffusion probabilistic models to tactile inverse modeling, integrating signed distance field geometry with a single-step contact projection constraint to establish a high-fidelity tactile-to-pose mapping. By further incorporating a particle filter proposal mechanism, the method enables online multimodal pose estimation without visual input and under weak prior assumptions. Experiments demonstrate that the approach significantly outperforms local sampling baselines in both simulated and real-world planar pose estimation tasks, achieving higher sampling efficiency and accuracy. Moreover, it exhibits strong robustness to unmodeled contacts and sensor dynamics in a box-pushing task.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Tactile sensing provides a promising sensing modality for object pose estimation in manipulation settings where visual information is limited due to occlusion or environmental effects. However, efficiently leveraging tactile data for estimation remains a challenge due to partial observability, with single observations corresponding to multiple possible contact configurations. This limits conventional estimation approaches largely tailored to vision. We propose to address these challenges by learning an inverse tactile sensor model using denoising diffusion. The model is conditioned on tactile observations from a distributed tactile sensor and trained in simulation using a geometric sensor model based on signed distance fields. Contact constraints are enforced during inference through single-step projection using distance and gradient information from the signed distance field. For online pose estimation, we integrate the inverse model with a particle filter through a proposal scheme that combines generated hypotheses with particles from the prior belief. Our approach is validated in simulated and real-world planar pose estimation settings, without access to visual data or tight initial pose priors. We further evaluate robustness to unmodeled contact and sensor dynamics for pose tracking in a box-pushing scenario. Compared to local sampling baselines, the inverse sensor model improves sampling efficiency and estimation accuracy while preserving multimodal beliefs across objects with varying tactile discriminability.

Problem

• tactile sensing
• object pose estimation
• partial observability
• distributed tactile sensor
• manipulation

Innovation

• diffusion model
• tactile sensing
• inverse sensor model
• signed distance field
• particle filter