Learning to Navigate with Minimal Parameters: Decomposing Visual Navigation Through Closed-Form Geometric Interfaces
Read the original on arXiv Computer Vision →The paper introduces a compact visual navigation system that decomposes the task into three analytically‑computed geometric interfaces and three small learned modules: an egress predictor, a navigation predictor, and an endpoint‑pinned residual diffusion generator. Only 0.58 M of the 23 M parameters are trained on 44 k frames, achieving competitive success rates and the lowest collision rate among evaluated methods across 6 060 point‑goal episodes in 60 environments. The design allows further parameter reduction by replacing the frozen image encoder with a 0.54 M MobileNetV2, supports zero‑shot deployment on a Jetson Orin Nano UGV, and enables transparent failure analysis under sensor corruption.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.