Navigating by Touch: Haptic Monte Carlo Localization via Geometric Sensing and Terrain Classification
arXiv:2108.08015 · doi:10.1007/s10514-021-10013-w
Abstract
Legged robot navigation in extreme environments can hinder the use of cameras and laser scanners due to darkness, air obfuscation or sensor damage. In these conditions, 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 class, 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 class probability with the geometric information of the foot contact points. Results are demonstrated showing this approach operating online and onboard a ANYmal B300 quadruped robot traversing a series of terrain courses with different geometries and terrain types over more than 1.2km. The method keeps the localization error below 20cm using only the information coming from the feet, IMU, and joints of the quadruped.
arXiv commentAutonomous Robots. arXiv admin note: substantial text overlap with arXiv:2005.01567
References in corpus (9)
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
- Decoupled Weight Decay Regularization
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- On-Manifold Preintegration for Real-Time Visual-Inertial Odometry
- Learning Quadrupedal Locomotion over Challenging Terrain
- Voxblox: Incremental 3D Euclidean Signed Distance Fields for On-Board MAV Planning
- Memory Unscented Particle Filter for 6-DOF Tactile Localization
- Heuristic Planning for Rough Terrain Locomotion in Presence of External Disturbances and Variable Perception Quality
- Haptic Sequential Monte Carlo Localization for Quadrupedal Locomotion in Vision-Denied Scenarios