Navigating by touch: haptic Monte Carlo localization via geometric sensing and terrain classification

Legged robot navigation in extreme environments can hinder the use of cameras and lidar due to darkness, air obfuscation or sensor damage, whereas proprioceptive sensing will continue to work reliably. In this paper, we propose a purely proprioceptive localization algorithm which fuses information from both geometry and terrain type to localize a legged robot within a prior map. First, a terrain classifier computes the probability that a foot has stepped on a particular terrain class from sensed foot forces. Then, a Monte Carlo-based estimator fuses this terrain probability with the geometric information of the foot contact points. Results demonstrate this approach operating online and onboard an ANYmal B300 quadruped robot traversing several terrain courses with different geometries and terrain types over more than 1.2 km. The method keeps pose estimation error below 20 cm using a prior map with trained network and using sensing only from the feet, leg joints and IMU.

[1]  Hendrik Kolvenbach,et al.  Towards autonomous inspection of concrete deterioration in sewers with legged robots , 2020, J. Field Robotics.

[2]  Sebastian Thrun,et al.  FastSLAM: a factored solution to the simultaneous localization and mapping problem , 2002, AAAI/IAAI.

[3]  Frank Dellaert,et al.  On-Manifold Preintegration for Real-Time Visual--Inertial Odometry , 2015, IEEE Transactions on Robotics.

[4]  Peter Fankhauser,et al.  Robust Rough-Terrain Locomotion with a Quadrupedal Robot , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Eric Krotkov,et al.  Active perception for legged locomotion: every step is an experiment , 1990, Proceedings. 5th IEEE International Symposium on Intelligent Control 1990.

[6]  Peter Fankhauser,et al.  ANYmal - a highly mobile and dynamic quadrupedal robot , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[7]  Darwin G. Caldwell,et al.  Heuristic Planning for Rough Terrain Locomotion in Presence of External Disturbances and Variable Perception Quality , 2018, ECHORD++.

[8]  Krzysztof Walas,et al.  Robotic Touch: Classification of Materials for Manipulation and Walking , 2019, 2019 2nd IEEE International Conference on Soft Robotics (RoboSoft).

[9]  Frank Hutter,et al.  Decoupled Weight Decay Regularization , 2017, ICLR.

[10]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[11]  Krzysztof Walas,et al.  What am I touching? Learning to classify terrain via haptic sensing , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[12]  Jens Reinecke,et al.  Online in-hand object localization , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[15]  Hendrik Kolvenbach,et al.  Haptic Inspection of Planetary Soils With Legged Robots , 2019, IEEE Robotics and Automation Letters.

[16]  Daniel D. Lee,et al.  Proprioceptive localilzatilon for a quadrupedal robot on known terrain , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[17]  Haptic Sequential Monte Carlo Localization for Quadrupedal Locomotion in Vision-Denied Scenarios , 2020, 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[18]  Siddhartha S. Srinivasa,et al.  Manifold Representations for State Estimation in Contact Manipulation , 2013, ISRR.

[19]  Stefan Leutenegger,et al.  Efficient Octree-Based Volumetric SLAM Supporting Signed-Distance and Occupancy Mapping , 2018, IEEE Robotics and Automation Letters.

[20]  Wolfram Burgard,et al.  Particle Filters for Mobile Robot Localization , 2001, Sequential Monte Carlo Methods in Practice.

[21]  Sepp Hochreiter,et al.  Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs) , 2015, ICLR.

[23]  Hannes Sommer,et al.  The Two-State Implicit Filter Recursive Estimation for Mobile Robots , 2018, IEEE Robotics and Automation Letters.

[24]  Frank Kirchner,et al.  Using Embodied Data for Localization and Mapping , 2014, J. Field Robotics.

[25]  Roland Siegwart,et al.  HAPTIC TERRAIN CLASSIFICATION ON NATURAL TERRAINS FOR LEGGED ROBOTS , 2010 .

[26]  Giorgio Battistelli,et al.  Memory Unscented Particle Filter for 6-DOF Tactile Localization , 2017, IEEE Transactions on Robotics.

[27]  Ruben Grandia,et al.  Quadrupedal Locomotion on Uneven Terrain With Sensorized Feet , 2020, IEEE Robotics and Automation Letters.

[28]  Yoshua Bengio,et al.  Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation , 2014, EMNLP.

[29]  Lorenz Wellhausen,et al.  Learning quadrupedal locomotion over challenging terrain , 2020, Science Robotics.

[30]  Maani Ghaffari,et al.  Contact-aided invariant extended Kalman filtering for robot state estimation , 2020, Int. J. Robotics Res..

[31]  Wolfram Burgard,et al.  A benchmark for the evaluation of RGB-D SLAM systems , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[32]  Krzysztof Walas,et al.  Where Should I Walk? Predicting Terrain Properties From Images Via Self-Supervised Learning , 2019, IEEE Robotics and Automation Letters.

[33]  Sangbae Kim,et al.  Dynamic Locomotion in the MIT Cheetah 3 Through Convex Model-Predictive Control , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).