Semi-parametric Topological Memory for Navigation
Nikolay Savinov ETH Zürich、Alexey Dosovitskiy∗ Intel Labs、Vladlen Koltun Intel Labs Shared first authorship
Abstract
We introduce a new memory architecture for navigation in previously unseen environments, inspired by landmark-based navigation in animals. The proposed semi-parametric topological memory (SPTM) consists of a (non-parametric) graph with nodes corresponding to locations in the environment and a (parametric) deep network capable of retrieving nodes from the graph based on observations. The graph stores no metric information, only connectivity of locations corresponding to the nodes. We use SPTM as a planning module in a navigation system. Given only 5 minutes of footage of a previously unseen maze, an SPTM-based navigation agent can build a topological map of the environment and use it to confidently navigate towards goals. The average success rate of the SPTM agent in goal-directed navigation across test environments is higher than the best-performing baseline by a factor of three.
中文速览
动物导航时依赖地标而非精确地图，研究者受此启发，提出了一种名为"半参数化拓扑记忆"（Semi-Parametric Topological Memory，SPTM）的导航记忆架构：用一张只记录地点连通关系（不存储任何度量坐标）的图来表示环境，再配合一个能根据视觉观测在图中定位节点的深度神经网络。具体做法是：给智能体看一段5分钟的迷宫探索视频，它便自动建起一张拓扑地图，之后只需借助"检索网络"定位自身与目标、在图上规划最短路径、再由"运动网络"执行短程移动，就能在此前从未见过的迷宫中找到目标位置。在仿真三维迷宫的目标导航测试中，SPTM智能体的平均成功率是最强基线方法的三倍。这项工作的意义在于，它不依赖相机位姿、运动里程计或任何人工标注，仅凭纯视觉输入就能在连续空间中高效导航，为构建更鲁棒、更仿生的视觉导航系统提供了新思路。
原文 arXiv:1803.00653;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1803.00653v1