BayesContact: Uncertain Pose Estimation via Visuo-Tactile Proposals and Simulation-based Inference

• URL: http://arxiv.org/abs/2607.16123v1
• Date: Fri, 17 Jul 2026 17:00:42 GMT
• Title: BayesContact: Uncertain Pose Estimation via Visuo-Tactile Proposals and Simulation-based Inference
• Abstract summary: 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%.
• Score: 16.840783588655523
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Contact-rich manipulation requires pose estimates that are often more accurate than what depth-only sensing provides. Existing methods, relying on vision and contact, employ costly offline training procedures that need to be retrained for new environments and geometries. We propose BayesContact, a Simulation-Based Inference framework for visuo-tactile pose estimation in peg-in-hole insertion. BayesContact maintains a particle belief over object pose and fuses depth observations with force/torque-derived contact evidence. We employ simulation based forward models to approximate these observation likelihoods. For each pose hypothesis, a renderer predicts depth measurements and a physics simulator predicts contact outcomes under guarded probing actions; both are scored against real observations to update the belief. The resulting multimodal belief also enables information-gain-based probing for active disambiguation. Across simulated geometries and real-robot experiments, BayesContact improves pose observability and insertion success over vision-only inference by 30%

Related papers

• Diffusion-based Inverse Model of a Distributed Tactile Sensor for Object Pose Estimation [45.95486121114164]
  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.
  arXiv  Detail & Related papers  (2026-01-19T17:36:28Z)
• 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)
• Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning [50.76723760768117]
  Existing human pose estimation methods cannot recover plausible close interactions from in-the-wild videos.<n>We find that human appearance can provide a straightforward cue to address these obstacles.<n>We propose a dual-branch optimization framework to reconstruct accurate interactive motions with plausible body contacts constrained by human appearances, social proxemics, and physical laws.
  arXiv  Detail & Related papers  (2025-07-03T12:19:26Z)
• ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation [2.140861702387444]
  dexterous contact-rich object manipulation demands both object poses and external contact locations.<n>We present ViTaSCOPE: VisuoTac Simultaneous Contact and Object Estimation.
  arXiv  Detail & Related papers  (2025-06-13T21:35:58Z)
• DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation [81.11585774044848]
  We present DeepSimHO, a novel deep-learning pipeline that combines forward physics simulation and backward gradient approximation with a neural network. Our method noticeably improves the stability of the estimation and achieves superior efficiency over test-time optimization.
  arXiv  Detail & Related papers  (2023-10-11T05:34:36Z)
• Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation [66.86987509942607]
  We evaluate how such a paradigm should be done in imitation learning. We consider a setting where the pretraining corpus consists of multitask demonstrations. We argue that inverse dynamics modeling is well-suited to this setting.
  arXiv  Detail & Related papers  (2023-05-26T14:40:46Z)
• PDC-Net+: Enhanced Probabilistic Dense Correspondence Network [161.76275845530964]
  Enhanced Probabilistic Dense Correspondence Network, PDC-Net+, capable of estimating accurate dense correspondences. We develop an architecture and an enhanced training strategy tailored for robust and generalizable uncertainty prediction. Our approach obtains state-of-the-art results on multiple challenging geometric matching and optical flow datasets.
  arXiv  Detail & Related papers  (2021-09-28T17:56:41Z)
• Physically Plausible Pose Refinement using Fully Differentiable Forces [68.8204255655161]
  We propose an end-to-end differentiable model that refines pose estimates by learning the forces experienced by the object. By matching the learned net force to an estimate of net force based on finite differences of position, this model is able to find forces that accurately describe the movement of the object. We show this model successfully corrects poses and finds contact maps that better match the ground truth, despite not using any RGB or depth image data.
  arXiv  Detail & Related papers  (2021-05-17T23:33:04Z)
• 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)

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.