WayFAST: Navigation with Predictive Traversability in the Field

Abstract

We present a self-supervised approach for learning to predict traversable paths for wheeled mobile robots that require good traction to navigate. Our algorithm, termed WayFAST (Waypoint Free Autonomous Systems for Traversability), uses RGB and depth data, along with navigation experience, to autonomously generate traversable paths in outdoor unstructured environments. Our key inspiration is that traction can be estimated for rolling robots using kinodynamic models. Using traction estimates provided by an online receding horizon estimator, we are able to train a traversability prediction neural network in a self-supervised manner, without requiring heuristics utilized by previous methods. We demonstrate the effectiveness of WayFAST through extensive field testing in varying environments, ranging from sandy dry beaches to forest canopies and snow covered grass fields. Our results clearly demonstrate that WayFAST can learn to avoid geometric obstacles as well as untraversable terrain, such as snow, which would be difficult to avoid with sensors that provide only geometric data, such as LiDAR. Furthermore, we show that our training pipeline based on online traction estimates is more data-efficient than other heuristic-based methods.

Project website with code and videos: https://mateusgasparino.com/wayfast-traversability-navigation/ Published in the IEEE Robotics and Automation Letters (RA-L, 2022) Accepted for presentation in the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

References in corpus (4)

• Learning robust perceptive locomotion for quadrupedal robots in the wild
• Safe Robot Navigation via Multi-Modal Anomaly Detection
• Robust Model Predictive Path Integral Control: Analysis and Performance Guarantees
• Learned Visual Navigation for Under-Canopy Agricultural Robots

Cited by in corpus (5)

• CropNav: a Framework for Autonomous Navigation in Real Farms
• Motion planning for off-road autonomous driving based on human-like cognition and weight adaptation
• Do You Know the Way? Human-in-the-Loop Understanding for Fast Traversability Estimation in Mobile Robotics
• Unmatched uncertainty mitigation through neural network supported model predictive control
• Continual Learning for Traversability Prediction with Uncertainty-Aware Adaptation