Road Navigation
Road navigation, particularly in off-road environments, focuses on enabling autonomous vehicles to safely and efficiently traverse unstructured terrains. Current research emphasizes robust state estimation using sensor fusion (LiDAR, radar, cameras, IMUs), often incorporating deep learning models like transformers and convolutional neural networks to predict traversability and elevation maps from various sensor inputs. These advancements are crucial for improving the reliability and speed of autonomous systems in challenging environments, with applications ranging from autonomous driving to search and rescue operations.
Papers
Pixel to Elevation: Learning to Predict Elevation Maps at Long Range using Images for Autonomous Offroad Navigation
Chanyoung Chung, Georgios Georgakis, Patrick Spieler, Curtis Padgett, Ali Agha, Shehryar Khattak
ROAMER: Robust Offroad Autonomy using Multimodal State Estimation with Radar Velocity Integration
Morten Nissov, Shehryar Khattak, Jeffrey A. Edlund, Curtis Padgett, Kostas Alexis, Patrick Spieler