Compact lidar model improves robot navigation in crowded environments
RangeNav: Task-Aligned LiDAR Range-Image Pretraining for Robot Navigation
RoboticsMachine Learning
Summary
Robots moving through crowded or complex places need to see all around them to avoid obstacles. The researchers created RangeNav, a small and efficient computer program that helps robots understand 360-degree lidar images. They trained RangeNav using fake data to recognize distances, object types, and overhead views, which improves robot navigation success. This new method works better than previous approaches and even performs well in real-world tests with a robot dog going through crowds and tricky spots.
What this means in practice
- •For mobile robot developers: Train compact lidar perception models that improve navigation success in complex surroundings without heavy resource demands.
- •For robotics simulation engineers: Run many parallel robot navigation simulations efficiently by using a memory-light lidar encoder pretrained on synthetic data.
- •For autonomous vehicle operators: Deploy robot navigation systems that function reliably in difficult real-world environments like crowds and low-light conditions.$Commercial implications: Enables sale of robust robot navigation software for autonomous vehicles operating in complex, dynamic environments.
Authors
Samuel Foo Enze, Manthan Patel, Fan Yang, Linus Kramer, Pascal Roth, Marco Hutter, Cesar Cadena
Abstract
Autonomous mobile robots operating in dense crowds and cluttered sites require $360^\circ$ perception to react to surrounding hazards. While panoramic LiDAR offers full-surround coverage, learning representations within reinforcement learning (RL) is sample-inefficient under sparse rewards, and existing 3D pretrained point-cloud encoders are too memory-heavy for massively parallel RL simulation. We present RangeNav, a compact (183k parameters) LiDAR range-image encoder pretrained entirely on synthetic data. RangeNav uses anisotropic convolutions and circular padding to handle the extreme aspect ratio and azimuthal seam of range images. We pretrain the network using a navigation-aligned objective combining range reconstruction, semantic segmentation, and bird's-eye-view (BEV) prediction, then freeze it for policy learning. In simulation, adding semantic and BEV supervision increases success rates over a reconstruction-only baseline by an average of 32.03 and 23.73 percentage points (pp) in procedurally generated training and out-of-distribution realistic test environments, respectively. Zero-shot real-world deployments on a Unitree B2-W quadruped demonstrate robust navigation through dense crowds, low-light settings, and construction zones where limited-field-of-view depth policies struggle. Code and models will be open-sourced.