RoadRunner M&M - Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigation
OPEN ACCESS
Loading...
Author / Producer
Date
2024-12
Publication Type
Journal Article
ETH Bibliography
yes
Citations
Altmetric
OPEN ACCESS
Data
Rights / License
Abstract
Autonomous robot navigation in off–road environments requires a comprehensive understanding of the terrain geometry and traversability. The degraded perceptual conditions and sparse geometric information at longer ranges make the problem challenging especially when driving at high speeds. Furthermore, the sensing–to–mapping latency and the look–ahead map range can limit the maximum speed of the vehicle. Building on top of the recent work RoadRunner, in this work, we address the challenge of long-range ±100m traversability estimation. Our RoadRunner (M&M) is an end-to-end learning-based framework that directly predicts the traversability and elevation maps at multiple ranges ( ±50m , ±100m ) and resolutions (0.2m, 0.8m) taking as input multiple images and a LiDAR voxel map. Our method is trained in a self–supervised manner by leveraging the dense supervision signal generated by fusing predictions from an existing traversability estimation stack (X-Racer) in hindsight and satellite Digital Elevation Maps. RoadRunner M&M achieves a significant improvement of up to 50% for elevation mapping and 30% for traversability estimation over RoadRunner, and is able to predict in 30% more regions compared to X-Racer while achieving real–time performance. Experiments on various out–of–distribution datasets also demonstrate that our data-driven approach starts to generalize to novel unstructured environments. We integrate our proposed framework in closed–loop with the path planner to demonstrate autonomous high–speed off–road robotic navigation in challenging real–world environments.
Permanent link
Publication status
published
External links
Editor
Book title
Journal / series
Volume
9 (12)
Pages / Article No.
11425 - 11432
Publisher
IEEE
Event
Edition / version
Methods
Software
Geographic location
Date collected
Date created
Subject
Field robots; Deep learning; Visual perception; Mapping
Organisational unit
09570 - Hutter, Marco / Hutter, Marco