cs.RONov 18, 2026

BEV-Diffusion: Camera-Only Traversability Navigation with BEV Memory and Efficient Cross-Robot Adaptation

Authors: Iana Zhura, Timofei Kozlov, Dmitrii Plotnikov, Ivan Valuev, Miguel Altamirano Cabrera, Dzmitry Tsetserukou

Organizations: The authors are with the Intelligent Space Robotics Laboratory Skolkovo Institute of Science and Technology Moscow, Russia

Abstract

Robot navigation requires both an understanding of the scene and an efficient adaptation to new robots, yet current methods rely on expensive LiDAR sensors, long mapping and modular pipelines. We present BEV-Diffusion, a camera-only model that learns a bird's-eye view (BEV) traversability map, its uncertainty and the path in a single network. A frozen DINOv2 backbone encodes consecutive RGB frames, which inverse perspective mapping and Bayesian fusion lift into the BEV, and a ranking loss keeps outdoor traversability graded rather than binary, separating asphalt from grass (median 0.94 vs. 0.75). On this map, a transformer denoiser generates polar waypoints in a few DDIM steps, and uncertainty-aware guidance refines the path and ends it where the map is no longer reliable. At deployment, a metric BEV memory keeps obstacles after they leave the camera view and warm starts each sample from the previous, ego-motion compensated path. Because the planner jointly learns the path, the map, and its uncertainty, it selects routes through terrain it can confidently traverse. In an unseen courtyard, a wheeled-legged robot autonomously traveled 120 m, completing 96% of the route without intervention, compared with 75-88% for the baselines. Even under low-light conditions after sunset, the proposed model completed the route without requiring any intervention. Retraining only the BEV head, about 3% of the parameters, adapts the model to a small legged robot in 2.3 min. Indoors, the memory gets this robot out of maze-like traps: it retains 62-66% of the nearby out-of-view obstacles, against at most 3% for the baselines, and the robot achieves 67-100% task progress, compared with 20-40% for the evaluated baselines.

Figures & tables

Explore similar work

CardsList
  1. EmbodiedDiffusion: End-to-End Traversability-Guided Visual Diffusion for Heterogeneous Robot Navigation

    Dec 2, 2025Iana Zhura, Sausar Karaf, Faryal Batool +7Robot Motion GenerationTrajectory Generation

  2. PathPainter: Transferring the Generalization Ability of Image Generation Models to Embodied Navigation

    May 8, 2026Yijin Wang, Yuru Tian, Xijie Huang +5Embodied NavigationRobot Navigation

  3. EchoNav: Evidential BEV Completion from Historical Observations for Visual Navigation

    Oct 20, 2026Diwen Liu, Yiyang Shao, Borui Wang +6Visual Robot Navigation