mlsanityData to 14 Oct 2026

Object Pose Estimation through Dexterous Touch

arXiv 2509.13591 ↗First posted 16 Sep 2025cs.RO cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Robust object pose estimation is essential for manipulation and interaction tasks in robotics, particularly in scenarios where visual data is limited or sensitive to lighting, occlusions, and appearances. Tactile sensors often offer limited and local contact information, making it challenging to reconstruct the pose from partial data. Our approach uses sensorimotor exploration to actively control a robot hand to interact with the object. We train with Reinforcement Learning (RL) to explore and collect tactile data. The collected 3D point clouds are used to iteratively refine the object's shape and pose. In our setup, one hand holds the object steady while the other performs active exploration. We show that our method can actively explore an object's surface to identify critical pose features without prior knowledge of the object's geometry. Supplementary material and more demonstrations will be provided at https://amirshahid.github.io/BimanualTactilePose .

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 33 of its 47 references that are in the map. First posted on arXiv 16 Sep 2025.

Builds on

33 of 47 references.

References · 33

  1. 2017PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenescited by 775
  2. 2020SAPIEN: A SimulAted Part-based Interactive ENvironmentcited by 595
  3. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  4. 2022MegaPose: 6D Pose Estimation of Novel Objects via Render & Comparecited by 201
  5. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 167
  6. 2023Rotating without Seeing: Towards In-hand Dexterity through Touchcited by 84
  7. 2024Learning Visuotactile Skills with Two Multifingered Handscited by 76
  8. 20243D-ViTac: Learning Fine-Grained Manipulation with Visuo-Tactile Sensingcited by 72
  9. 2016Multi-view Self-supervised Deep Learning for 6D Pose Estimation in the Amazon Picking Challengecited by 70
  10. 2019Deep Reinforcement Learning for Industrial Insertion Tasks with Visual Inputs and Natural Rewardscited by 64
  11. 2022NeRF-Pose: A First-Reconstruct-Then-Regress Approach for Weakly-supervised 6D Object Pose Estimationcited by 58
  12. 2018GelSlim: A High-Resolution, Compact, Robust, and Calibrated Tactile-sensing Fingercited by 52
21 more
  1. 2022Surface Reconstruction from Point Clouds: A Survey and a Benchmarkcited by 41
  2. 2016The Curious Robot: Learning Visual Representations via Physical Interactionscited by 38
  3. 2021Active 3D Shape Reconstruction from Vision and Touchcited by 34
  4. 2021ShapeMap 3-D: Efficient shape mapping through dense touch and visioncited by 31
  5. 2023Neural feels with neural fields: Visuo-tactile perception for in-hand manipulationcited by 28
  6. 2024Lessons from Learning to Spin "Pens"cited by 26
  7. 2023Challenges for Monocular 6D Object Pose Estimation in Roboticscited by 21
  8. 2020Tactile Object Pose Estimation from the First Touch with Geometric Contact Renderingcited by 20
  9. 2021Active Extrinsic Contact Sensing: Application to General Peg-in-Hole Insertioncited by 19
  10. 2023TouchSDF: A DeepSDF Approach for 3D Shape Reconstruction using Vision-Based Tactile Sensingcited by 15
  11. 2022TransNet: Category-Level Transparent Object Pose Estimationcited by 13
  12. 2022TANDEM: Learning Joint Exploration and Decision Making with Tactile Sensorscited by 12
  13. 2023AcTExplore: Active Tactile Exploration of Unknown Objectscited by 12
  14. 2022Active Visuo-Haptic Object Shape Completioncited by 11
  15. 2024FeelAnyForce: Estimating Contact Force Feedback from Tactile Sensation for Vision-Based Tactile Sensorscited by 11
  16. 2023Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensorscited by 10
  17. 2024ManiPose: A Comprehensive Benchmark for Pose-aware Object Manipulation in Roboticscited by 7
  18. 2022Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensingcited by 5
  19. 2023TactoFind: A Tactile Only System for Object Retrievalcited by 5
  20. 2023Efficient Visuo-Haptic Object Shape Completion for Robot Manipulationcited by 2
  21. 2023TransTouch: Learning Transparent Objects Depth Sensing Through Sparse Touchescited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Improving Robotic Manipulation: Techniques for Object Pose Estimation, Accommodating Positional Uncertainty, and Disassembly Tasks from Examples
  2. 2024Learning a Shape-Conditioned Agent for Purely Tactile In-Hand Manipulation of Various Objects
  3. 2026Pose-Aware Modeling to Mitigate Pose-Related Artifacts in Tactile Gloves ↗
  4. 2026UniDex-ViTac: Learning Unified Visuo-Tactile Dexterous Manipulation Policy from Human Video Data ↗
  5. 2026TaRL: Learning General and Physical Rewards from Tactile Demonstrations ↗
  6. 2023Learning active tactile perception through belief-space control
  7. 2020Physics-Based Dexterous Manipulations with Estimated Hand Poses and Residual Reinforcement Learning
  8. 2026NoContactNoWorries: Estimating Contact through Vision and Proprioception for In-Hand Dexterous Manipulation