Samuel Foo Enze, Manthan Patel, Fan Yang, Linus Kramer, Pascal Roth, Marco Hutter, César Cadena · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.29845 · cited by 0 works (OpenAlex) · open-access PDF
Autonome Navigationsroboter, die in dichten Massen und verwirrten Standorten arbeiten, erfordern eine Wahrnehmung von 360 $, um auf umgebende Gefahren zu reagieren. Während panoramische LiDAR eine vollständige Surround-Abdeckung bietet, ist das Lernen von Repräsentationen innerhalb von Verstärkungslernen (RL) unter spärlichen Belohnungen ineffizient, und bestehende 3D-Punktwolken-Predraining-Codecs sind für die massive parallele RL-Simulation zu schwer im Speicher. Wir präsentieren RangeNav, einen kompakten (183k-Parameter) LiDAR-Range-Image-Codec, der vollständig auf synthetische Daten vorbereitet ist. RangeNav verwendet anisotropische Convolutions
Machine translation (Meta M2M100); the English original follows.
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.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Lidar, Computer science, Artificial intelligence, Computer vision, Encoder, Ranging
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29845, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange