mlsanityData to 14 Oct 2026

AcTExplore: Active Tactile Exploration of Unknown Objects

arXiv 2310.08745 ↗First posted 12 Oct 2023cs.RO cs.CVcited by 12

Not on the map. Why?

Abstract (arXiv)

Tactile exploration plays a crucial role in understanding object structures for fundamental robotics tasks such as grasping and manipulation. However, efficiently exploring such objects using tactile sensors is challenging, primarily due to the large-scale unknown environments and limited sensing coverage of these sensors. To this end, we present AcTExplore, an active tactile exploration method driven by reinforcement learning for object reconstruction at scales that automatically explores the object surfaces in a limited number of steps. Through sufficient exploration, our algorithm incrementally collects tactile data and reconstructs 3D shapes of the objects as well, which can serve as a representation for higher-level downstream tasks. Our method achieves an average of 95.97% IoU coverage on unseen YCB objects while just being trained on primitive shapes. Project Webpage: https://prg.cs.umd.edu/AcTExplore

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 35 of its 71 references that are in the map. First posted on arXiv 12 Oct 2023.

Builds on

35 of 71 references.

References · 35

  1. 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,041
  2. 2018Learning Dexterous In-Hand Manipulationcited by 687
  3. 2017Minimax Regret Bounds for Reinforcement Learningcited by 503
  4. 2018Is Q-learning Provably Efficient?cited by 487
  5. 2020Learning to Explore using Active Neural SLAMcited by 316
  6. 2016Learning to Navigate in Complex Environmentscited by 198
  7. 2020DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulationcited by 167
  8. 2017IQA: Visual Question Answering in Interactive Environmentscited by 155
  9. 2019Learning Exploration Policies for Navigationcited by 116
  10. 2015Benchmarking in Manipulation Research: The YCB Object and Model Set and Benchmarking Protocolscited by 99
  11. 2022A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontierscited by 66
  12. 2020TACTO: A Fast, Flexible, and Open-source Simulator for High-Resolution Vision-based Tactile Sensorscited by 63
23 more
  1. 20203D Shape Reconstruction from Vision and Touchcited by 42
  2. 2022MidasTouch: Monte-Carlo inference over distributions across sliding touchcited by 33
  3. 2021ShapeMap 3-D: Efficient shape mapping through dense touch and visioncited by 31
  4. 2020Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphscited by 30
  5. 2021Sim-to-Real for Robotic Tactile Sensing via Physics-Based Simulation and Learned Latent Projectionscited by 28
  6. 2019Learning to Identify Object Instances by Touch: Tactile Recognition via Multimodal Matchingcited by 16
  7. 2019Soft-bubble: A highly compliant dense geometry tactile sensor for robot manipulationcited by 16
  8. 2020Tactile SLAM: Real-time inference of shape and pose from planar pushingcited by 15
  9. 2022Tac2Pose: Tactile Object Pose Estimation from the First Touchcited by 15
  10. 2022DenseTact: Optical Tactile Sensor for Dense Shape Reconstructioncited by 13
  11. 2023FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedbackcited by 12
  12. 2022TANDEM3D: Active Tactile Exploration for 3D Object Recognitioncited by 10
  13. 2023Collision-aware In-hand 6D Object Pose Estimation using Multiple Vision-based Tactile Sensorscited by 10
  14. 2019A Short Survey On Memory Based Reinforcement Learningcited by 9
  15. 2021Simultaneous Tactile Exploration and Grasp Refinement for Unknown Objectscited by 9
  16. 2022Visual-Tactile Multimodality for Following Deformable Linear Objects Using Reinforcement Learningcited by 9
  17. 2022DTact: A Vision-Based Tactile Sensor that Measures High-Resolution 3D Geometry Directly from Darknesscited by 9
  18. 2018SalientDSO: Bringing Attention to Direct Sparse Odometrycited by 8
  19. 2020Seeing Through your Skin: Recognizing Objects with a Novel Visuotactile Sensorcited by 8
  20. 2022Tactile Pose Estimation and Policy Learning for Unknown Object Manipulationcited by 8
  21. 2021Interpreting and Predicting Tactile Signals for the SynTouch BioTaccited by 7
  22. 2022GradTac: Spatio-Temporal Gradient Based Tactile Sensingcited by 2
  23. 2022Curiosity Driven Self-supervised Tactile Exploration of Unknown Objectscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 5; 2026: 4.

12 papers.

  1. 2024FeelAnyForce: Estimating Contact Force Feedback from Tactile Sensation for Vision-Based Tactile Sensorscited by 11
  2. 2023Sim2Real Bilevel Adaptation for Object Surface Classification using Vision-Based Tactile Sensorscited by 4
  3. 2025Tactile MNIST: Benchmarking Active Tactile Perceptioncited by 3
  4. 2024FusionSense: Bridging Common Sense, Vision, and Touch for Robust Sparse-View Reconstructioncited by 2
  5. 2025Apple: Toward General Active Perception via Reinforcement Learningcited by 2
  6. 2025Imagine, Verify, Execute: Memory-guided Agentic Exploration with Vision-Language Modelscited by 2
  7. 2025ControlTac: Scaling Tactile Data with Physically Controlled Tactile Image Generationcited by 0
  8. 2025Object Pose Estimation through Dexterous Touchcited by 0
  9. 2026Monocular Reconstruction of Neural Tactile Fieldscited by 0
  10. 2026Physically Grounded 3D Generative Reconstruction under Hand Occlusion using Proprioception and Multi-Contact Touchcited by 0
  11. 2026TACTFUL: Tactile-Driven Exploration For Object Localization and Identification in Confined Environmentscited by 0
  12. 2026ROMA: LLM System for Real-World Object-Centric Multi-Sensory Active Perceptioncited by 0