仅用58万个可训练参数学习高效导航

中文摘要 AI 辅助

视觉导航的近期进展很大程度上由规模驱动：具有数亿参数的端到端策略在数十亿帧或大规模模拟数据上训练。我们探究单个任务族实际需要多少这种规模，以及什么结构可替代它。我们提出一种分解式导航模型，其中具有已知封闭形式结构的操作通过解析计算，并作为三个小学习模块之间的接口。该系统在总共2270万个参数中仅训练58万个，在不到一个GPU小时内用44k帧训练，在6060个点目标情节和60个环境的导航任务中接近最先进模型的性能，同时可训练参数少233倍，碰撞率最低，推理速度为50Hz。这种分解还可通过仅重新训练12.3万个参数的出口头部转移到无目标探索，其在传感器损坏下的故障模式是透明且可解析纠正的。

英文摘要

Visual navigation policies have grown to hundreds of millions of parameters trained on billions of frames, with geometry, mapping, and control learned implicitly. We propose a decomposed point-goal navigation system in which operations with known closed-form structure, such as projective geometry, occupancy, and coordinate transforms, are computed analytically and serve as interfaces between three small learned modules: an egress predictor that grounds the episode goal as a local subgoal in the current view, a navigation predictor that estimates a goal-conditioned posterior over where trajectories travel, and an endpoint-pinned residual diffusion generator that samples trajectory shapes from this posterior. Only 0.58M out of 23M parameters are trained, on 44k frames, in under one GPU-hour. Across 6060 point-goal episodes in 60 environments, the system attains competitive success rates with the lowest collision rate among evaluated methods. We further show that under this decomposition, the frozen image encoder can be replaced by a 0.54M MobileNetV2 at a -2.0 SR cost, bringing the full system under 1.2M parameters. It also transfers to no-goal exploration by retraining only the 123k-parameter egress head, and its failure modes under sensor corruption are transparent and analytically correctable. We deploy and evaluate the system zero-shot on a low-cost UGV, running navigation and localization on a Jetson Orin Nano in real-time.

发表机构

• College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）

机构由 AI 辅助整理，请以论文原文为准。

补充信息

备注

Under review