FingerSLAM: Closed-loop Unknown Object Localization and Reconstruction from Visuo-tactile Feedback

In this paper, we address the problem of using visuo-tactile feedback for 6-DoF localization and 3D reconstruction of unknown in-hand objects. We propose FingerSLAM, a closed-loop factor graph-based pose estimator that combines local tactile sensing at finger-tip and global vision sensing from a wrist-mount camera. FingerSLAM is constructed with two constituent pose estimators: a multi-pass refined tactile-based pose estimator that captures movements from detailed local textures, and a single-pass vision-based pose estimator that predicts from a global view of the object. We also design a loop closure mechanism that actively matches current vision and tactile images to previously stored key-frames to reduce accumulated error. FingerSLAM incorporates the two sensing modalities of tactile and vision, as well as the loop closure mechanism with a factor graph-based optimization framework. Such a framework produces an optimized pose estimation solution that is more accurate than the standalone estimators. The estimated poses are then used to reconstruct the shape of the unknown object incrementally by stitching the local point clouds recovered from tactile images. We train our system on real-world data collected with 20 objects. We demonstrate reliable visuo-tactile pose estimation and shape reconstruction through quantitative and qualitative real-world evaluations on 6 objects that are unseen during training.

[1]  Maria Bauzá,et al.  Tac2Pose: Tactile object pose estimation from the first touch , 2022, Int. J. Robotics Res..

[2]  M. Kaess,et al.  PatchGraph: In-hand tactile tracking with learned surface normals , 2021, 2022 International Conference on Robotics and Automation (ICRA).

[3]  Joshua G. Mangelson,et al.  ShapeMap 3-D: Efficient shape mapping through dense touch and vision , 2021, 2022 International Conference on Robotics and Automation (ICRA).

[4]  Zilin Si,et al.  Taxim: An Example-based Simulation Model for GelSight Tactile Sensors , 2021, IEEE Robotics and Automation Letters.

[5]  Yu She,et al.  GelSight Wedge: Measuring High-Resolution 3D Contact Geometry with a Compact Robot Finger , 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[6]  R. Calandra,et al.  TACTO: A Fast, Flexible, and Open-Source Simulator for High-Resolution Vision-Based Tactile Sensors , 2020, IEEE Robotics and Automation Letters.

[7]  Kuan-Ting Yu,et al.  Tactile SLAM: Real-time inference of shape and pose from planar pushing , 2020, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[8]  Oliver Kroemer,et al.  Towards Robotic Assembly by Predicting Robust, Precise and Task-oriented Grasps , 2020, CoRL.

[9]  Oliver Kroemer,et al.  Towards Precise Robotic Grasping by Probabilistic Post-grasp Displacement Estimation , 2019, FSR.

[10]  Jianhua Li,et al.  Rotational Direction Detection Using Tactile Sensor and External Camera , 2019, 2019 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM).

[11]  Maria Bauza,et al.  Tactile Mapping and Localization from High-Resolution Tactile Imprints , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[12]  Silvio Savarese,et al.  DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[13]  Marc Alexa,et al.  ABC: A Big CAD Model Dataset for Geometric Deep Learning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Yang Yang,et al.  FingerVision Tactile Sensor Design and Slip Detection Using Convolutional LSTM Network , 2018, ArXiv.

[15]  Eric Brachmann,et al.  BOP: Benchmark for 6D Object Pose Estimation , 2018, ECCV.

[16]  Silvio Savarese,et al.  Learning task-oriented grasping for tool manipulation from simulated self-supervision , 2018, Robotics: Science and Systems.

[17]  Kaspar Althoefer,et al.  iCLAP: shape recognition by combining proprioception and touch sensing , 2018, Autonomous Robots.

[18]  T. Martin McGinnity,et al.  Material recognition using tactile sensing , 2018, Expert Syst. Appl..

[19]  Jianhua Li,et al.  GelSlim: A High-Resolution, Compact, Robust, and Calibrated Tactile-sensing Finger , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[20]  Jianhua Li,et al.  Slip Detection with Combined Tactile and Visual Information , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[21]  E. Adelson,et al.  ViTac: Feature Sharing Between Vision and Tactile Sensing for Cloth Texture Recognition , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[22]  Edward H. Adelson,et al.  GelSight: High-Resolution Robot Tactile Sensors for Estimating Geometry and Force , 2017, Sensors.

[23]  Dieter Fox,et al.  PoseCNN: A Convolutional Neural Network for 6D Object Pose Estimation in Cluttered Scenes , 2017, Robotics: Science and Systems.

[24]  S. Levine,et al.  The Feeling of Success: Does Touch Sensing Help Predict Grasp Outcomes? , 2017, CoRL.

[25]  Bo Chen,et al.  MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications , 2017, ArXiv.

[26]  Edward H. Adelson,et al.  Connecting Look and Feel: Associating the Visual and Tactile Properties of Physical Materials , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[27]  Véronique Perdereau,et al.  Tactile sensing in dexterous robot hands - Review , 2015, Robotics Auton. Syst..

[28]  Kaspar Althoefer,et al.  Tactile Object Recognition with Semi-Supervised Learning , 2015, ICIRA.

[29]  Siddhartha S. Srinivasa,et al.  The YCB object and Model set: Towards common benchmarks for manipulation research , 2015, 2015 International Conference on Advanced Robotics (ICAR).

[30]  Edward H. Adelson,et al.  Measurement of shear and slip with a GelSight tactile sensor , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[31]  K. Althoefer,et al.  Localizing the object contact through matching tactile features with visual map , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[32]  Helge J. Ritter,et al.  Using haptics to extract object shape from rotational manipulations , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[33]  F. Dellaert Factor Graphs and GTSAM: A Hands-on Introduction , 2012 .

[34]  Christoph H. Lampert,et al.  Learning Dynamic Tactile Sensing With Robust Vision-Based Training , 2011, IEEE Transactions on Robotics.

[35]  Hugh F. Durrant-Whyte,et al.  Simultaneous localization and mapping: part I , 2006, IEEE Robotics & Automation Magazine.

[36]  John F. Canny,et al.  Planning optimal grasps , 1992, Proceedings 1992 IEEE International Conference on Robotics and Automation.

[37]  R. Klatzky,et al.  There's more to touch than meets the eye: The salience of object attributes for haptics with and without vision. , 1987 .

[38]  R L Klatzky,et al.  Identifying objects by touch: An “expert system” , 1985, Perception & psychophysics.