mlsanityData to 14 Oct 2026

The Role of Tactile Sensing for Learning Reach and Grasp

arXiv 2502.20367 ↗First posted 27 Feb 2025cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot locomotion and manipulation

Abstract (arXiv)

Stable and robust robotic grasping is essential for current and future robot applications. In recent works, the use of large datasets and supervised learning has enhanced speed and precision in antipodal grasping. However, these methods struggle with perception and calibration errors due to large planning horizons. To obtain more robust and reactive grasping motions, leveraging reinforcement learning combined with tactile sensing is a promising direction. Yet, there is no systematic evaluation of how the complexity of force-based tactile sensing affects the learning behavior for grasping tasks. This paper compares various tactile and environmental setups using two model-free reinforcement learning approaches for antipodal grasping. Our findings suggest that under imperfect visual perception, various tactile features improve learning outcomes, while complex tactile inputs complicate training.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot locomotion and manipulation, one of 15 directions in Deep reinforcement learning methods. Builds on 33 of its 48 references that are in the map. First posted on arXiv 27 Feb 2025.

Builds on

33 of 48 references.

References · 33

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2013Describing Textures in the Wildcited by 2,125
  4. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  5. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  6. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 612
  7. 2023FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objectscited by 429
  8. 2018Maximum a Posteriori Policy Optimisationcited by 328
  9. 2019Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Modelcited by 231
  10. 2019Robust Reinforcement Learning for Continuous Control with Model Misspecificationcited by 78
  11. 2022GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRFcited by 67
  12. 2022Visuo-Tactile Transformers for Manipulationcited by 47
21 more
  1. 2021GelSlim3.0: High-Resolution Measurement of Shape, Force and Slip in a Compact Tactile-Sensing Fingercited by 41
  2. 2021ReSkin: versatile, replaceable, lasting tactile skinscited by 35
  3. 2018Deep Reinforcement Learning for Vision-Based Robotic Grasping: A Simulated Comparative Evaluation of Off-Policy Methodscited by 33
  4. 2022DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systemscited by 29
  5. 2023Dextrous Tactile In-Hand Manipulation Using a Modular Reinforcement Learning Architecturecited by 20
  6. 2019TactileGCN: A Graph Convolutional Network for Predicting Grasp Stability with Tactile Sensorscited by 17
  7. 2020GelTip: A Finger-shaped Optical Tactile Sensor for Robotic Manipulationcited by 15
  8. 2019MAT: Multi-Fingered Adaptive Tactile Grasping via Deep Reinforcement Learningcited by 12
  9. 2024DexTouch: Learning to Seek and Manipulate Objects with Tactile Dexteritycited by 12
  10. 2021Sim-to-Real Transfer for Robotic Manipulation with Tactile Sensorycited by 11
  11. 2023TacGNN:Learning Tactile-based In-hand Manipulation with a Blind Robotcited by 11
  12. 2021Improved Learning of Robot Manipulation Tasks via Tactile Intrinsic Motivationcited by 10
  13. 2021A soft thumb-sized vision-based sensor with accurate all-round force perceptioncited by 10
  14. 2020A Sensorized Multicurved Robot Finger with Data-driven Touch Sensing via Overlapping Light Signalscited by 9
  15. 2020Soft, Round, High Resolution Tactile Fingertip Sensors for Dexterous Robotic Manipulationcited by 9
  16. 2022DenseTact 2.0: Optical Tactile Sensor for Shape and Force Reconstructioncited by 9
  17. 2022GraspARL: Dynamic Grasping via Adversarial Reinforcement Learningcited by 8
  18. 2023GelSight360: An Omnidirectional Camera-Based Tactile Sensor for Dexterous Robotic Manipulationcited by 5
  19. 2023Minsight: A Fingertip-Sized Vision-Based Tactile Sensor for Robotic Manipulationcited by 5
  20. 2021The Role of Tactile Sensing in Learning and Deploying Grasp Refinement Algorithmscited by 2
  21. 2024Stable Object Placing using Curl and Diff Features of Vision-based Tactile Sensorscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Tactile-Guided Robot Learning: From Representation Learning to Foundation Models ↗
  2. 2025Enhancing Tactile-based Reinforcement Learning for Robotic Control
  3. 2025Improving Robotic Manipulation: Techniques for Object Pose Estimation, Accommodating Positional Uncertainty, and Disassembly Tasks from Examples
  4. 2026The impact of tactile sensor configurations on grasp learning efficiency -- a comparative evaluation in simulation ↗
  5. 2024Learning Stable Robot Grasping with Transformer-based Tactile Control Policies
  6. 2025Tactile-based Reinforcement Learning for Adaptive Grasping under Observation Uncertainties
  7. 2026Tactile Curiosity Drives Robot Interaction
  8. 2025Disambiguate Gripper State in Grasp-Based Tasks: Pseudo-Tactile as Feedback Enables Pure Simulation Learning