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

• URL: http://arxiv.org/abs/2601.13250v1
• Date: Mon, 19 Jan 2026 17:36:28 GMT
• Title: Diffusion-based Inverse Model of a Distributed Tactile Sensor for Object Pose Estimation
• Abstract summary: We learn an inverse tactile sensor model using denoising diffusion to efficiently leverage tactile data for pose estimation.<n>The model is conditioned on tactile observations from a distributed tactile sensor and trained in simulation using a geometric sensor model.<n>For online pose estimation, we integrate the inverse model with a particle filter through a proposal scheme.
• Score: 45.95486121114164
• License: http://creativecommons.org/licenses/by/4.0/
• 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.

Related papers

• Event-Based Motion Estimation via Oriented Distance Fields [55.23416502666468]
  Event-based motion estimation is central to tasks that demand high temporal resolution and robustness to fast motion.<n>We propose Oriented Distance Field Motion Estimation (ODF Motion Estimation), which replaces this optimization with a single averaging step over a precomputed field of event distance vectors.<n>On public and self-collected datasets, ODF motion estimation reaches sub-pixel accuracy at the lowest latency among compared methods.
  arXiv  Detail & Related papers  (2026-08-25T08:27:42Z)
• BayesContact: Uncertain Pose Estimation via Visuo-Tactile Proposals and Simulation-based Inference [16.840783588655523]
  BayesContact is a framework for visuo-tactile pose estimation in peg-in-hole insertion.<n>It maintains a particle belief over object pose and fuses depth observations with force/torque-derived contact evidence.<n>It improves pose observability and insertion success over vision-only inference by 30%.
  arXiv  Detail & Related papers  (2026-07-17T17:00:42Z)
• Bayesian Active Object Recognition and 6D Pose Estimation from Multimodal Contact Sensing [14.370567509757555]
  We present an active tactile exploration framework for joint object recognition and 6D pose estimation.<n>The proposed method integrates wrist force/torque sensing, GelSight tactile sensing, and free-space constraints.<n>Results show that incorporating tactile and free-space information substantially improves recognition and pose estimation accuracy and stability.
  arXiv  Detail & Related papers  (2026-03-22T21:30:23Z)
• Mobile Robot Localization Using a Novel Whisker-Like Sensor [2.4440761580878823]
  This paper presents a framework for estimating contact points and robot localization in a known planar environment using a single whisker sensor.<n>Results demonstrate accurate contact estimation and localization with errors under 7 mm.
  arXiv  Detail & Related papers  (2026-01-09T08:11:15Z)
• Simultaneous Extrinsic Contact and In-Hand Pose Estimation via Distributed Tactile Sensing [20.162368645967153]
  We propose a method that pairs local observations from sensing with the physical constraints of contact.<n>We formalize our problem as a factor graph, allowing for efficient estimation.<n>In our experiments, we demonstrate that our method outperforms existing geometric and contact-informed estimation pipelines.
  arXiv  Detail & Related papers  (2025-12-29T20:45:38Z)
• Advances in Compliance Detection: Novel Models Using Vision-Based Tactile Sensors [0.7199733380797579]
  Compliance is a critical parameter for describing objects in engineering, agriculture, and biomedical applications.<n>Traditional compliance detection methods are limited by their lack of portability and scalability, rely on specialized, often expensive equipment, and are unsuitable for robotic applications.<n>We propose two models based on Long-term Recurrent Convolutional Networks (LRCNs) and Transformer architectures that leverage RGB tactile images and other information captured by the vision-based sensor GelSight to predict compliance metrics accurately.
  arXiv  Detail & Related papers  (2025-06-17T21:10:05Z)
• OOSTraj: Out-of-Sight Trajectory Prediction With Vision-Positioning Denoising [49.86409475232849]
  Trajectory prediction is fundamental in computer vision and autonomous driving. Existing approaches in this field often assume precise and complete observational data. We present a novel method for out-of-sight trajectory prediction that leverages a vision-positioning technique.
  arXiv  Detail & Related papers  (2024-04-02T18:30:29Z)
• Diffusion-Based Particle-DETR for BEV Perception [94.88305708174796]
  Bird-Eye-View (BEV) is one of the most widely-used scene representations for visual perception in Autonomous Vehicles (AVs) Recent diffusion-based methods offer a promising approach to uncertainty modeling for visual perception but fail to effectively detect small objects in the large coverage of the BEV. Here, we address this problem by combining the diffusion paradigm with current state-of-the-art 3D object detectors in BEV.
  arXiv  Detail & Related papers  (2023-12-18T09:52:14Z)
• Physical-Layer Semantic-Aware Network for Zero-Shot Wireless Sensing [74.12670841657038]
  Device-free wireless sensing has recently attracted significant interest due to its potential to support a wide range of immersive human-machine interactive applications. Data heterogeneity in wireless signals and data privacy regulation of distributed sensing have been considered as the major challenges that hinder the wide applications of wireless sensing in large area networking systems. We propose a novel zero-shot wireless sensing solution that allows models constructed in one or a limited number of locations to be directly transferred to other locations without any labeled data.
  arXiv  Detail & Related papers  (2023-12-08T13:50:30Z)
• Layout Sequence Prediction From Noisy Mobile Modality [53.49649231056857]
  Trajectory prediction plays a vital role in understanding pedestrian movement for applications such as autonomous driving and robotics. Current trajectory prediction models depend on long, complete, and accurately observed sequences from visual modalities. We propose LTrajDiff, a novel approach that treats objects obstructed or out of sight as equally important as those with fully visible trajectories.
  arXiv  Detail & Related papers  (2023-10-09T20:32:49Z)
• Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensors [4.886250215151643]
  We reason on the possible spatial configurations of the sensors along the object surface. We use selected sensors configurations to optimize over the space of 6D poses. We rank the obtained poses by penalizing those that are in collision with the sensors.
  arXiv  Detail & Related papers  (2023-01-31T14:35:26Z)
• Particle-Based Score Estimation for State Space Model Learning in Autonomous Driving [62.053071723903834]
  Multi-object state estimation is a fundamental problem for robotic applications. We consider learning maximum-likelihood parameters using particle methods. We apply our method to real data collected from autonomous vehicles.
  arXiv  Detail & Related papers  (2022-12-14T01:21:05Z)
• Tactile Object Pose Estimation from the First Touch with Geometric Contact Rendering [19.69677059281393]
  We present an approach to tactile pose estimation from the first touch for known objects. We create an object-agnostic map from real tactile observations to contact shapes. For a new object with known geometry, we learn a tailored perception model completely in simulation.
  arXiv  Detail & Related papers  (2020-12-09T18:00:35Z)
• Learning Tactile Models for Factor Graph-based Estimation [24.958055047646628]
  Vision-based tactile sensors provide rich, local image measurements at the point of contact. A single measurement contains limited information and multiple measurements are needed to infer latent object state. We propose a two-stage approach: first we learn local tactile observation models supervised with ground truth data, and then integrate these models along with physics and geometric factors within a factor graph.
  arXiv  Detail & Related papers  (2020-12-07T15:09:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.