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
Robust High-Speed State Estimation for Off-road Navigation using Radar Velocity Factors
Morten Nissov, Jeffrey A. Edlund, Patrick Spieler, Curtis Padgett, Kostas Alexis, Shehryar Khattak
RoadRunner M&M -- Learning Multi-range Multi-resolution Traversability Maps for Autonomous Off-road Navigation
Manthan Patel, Jonas Frey, Deegan Atha, Patrick Spieler, Marco Hutter, Shehryar Khattak
PIETRA: Physics-Informed Evidential Learning for Traversing Out-of-Distribution Terrain
Xiaoyi Cai, James Queeney, Tong Xu, Aniket Datar, Chenhui Pan, Max Miller, Ashton Flather, Philip R. Osteen, Nicholas Roy, Xuesu Xiao, Jonathan P. How
Reinforcement Learning for Wheeled Mobility on Vertically Challenging Terrain
Tong Xu, Chenhui Pan, Xuesu Xiao
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