Distilling Global Traversability Priors for Image-based Affordance Prediction in Off-road Environments
2026-07-20 • Robotics
Robotics
AI summaryⓘ
The authors address the problem that robots navigating rough terrain often make short-sighted decisions because their sensors only see a limited distance. Instead of relying solely on local maps from sensors like LiDAR or cameras, they use satellite images to help the robot understand longer-range paths from its first-person view. They train a network to predict safe paths far ahead, without needing many human examples. This method leads to better navigation and fewer human corrections in real-world tests.
autonomous navigationunstructured terrainLiDARfirst-person view (FPV)satellite imagerytraversabilityfrontierslong-range planningrobotic perceptionhuman intervention
Authors
Matthew Sivaprakasam, Samuel Triest, Micah Nye, Deegan Atha, Shehryar Khattak, David Fan, Wenshan Wang, Sebastian Scherer
Abstract
Standard methods for autonomous navigation in unstructured terrain are prone to myopic behaviors in long-horizon scenarios. The use of metric maps built from LiDAR or cameras provides necessary local geometry and semantic information but is strictly limited by depth sensing range. By discarding data beyond the mapping horizon robots suffer from suboptimal, short-sighted decisions. To recover this lost information, we focus on extracting long-range traversability-aware frontiers directly from first-person-view (FPV) images. By leveraging satellite imagery, we compute the set of feasible navigation paths for a dataset of image/pose pairs and use them to supervise our network, reducing the need for extensive human demonstration data. We demonstrate that this approach improves performance in long-range off-road navigation over existing methods by more than 10% in various offline benchmarks and reduces the number of human interventions incurred in a set of real-world experiments. More details can be found at https://theairlab.org/ss_frontiers_iros .