RangeNav: LiDAR range-image pretraining for navigation on arXiv

Our paper RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation is now available on arXiv.

RangeNav is a compact (183k parameters) LiDAR range-image encoder pretrained on synthetic data with navigation-aligned objectives, then frozen for policy learning. It was deployed on a wheeled-legged robot in dynamic crowds, low-light and construction environments. Joint work with Samuel Foo Enze, Manthan Patel, Fan Yang, Linus Kramer, Marco Hutter and Cesar Cadena.

Pascal Roth
Pascal Roth
Ph.D. in Robot Learning & Software Engineer

Research on learning-based navigation and autonomy for legged robots, with focus on perceptive planning and sim-to-real transfer.