Scene Action Maps: Behavioural Maps for Navigation without Metric Information

TL;DR

This paper introduces Scene Action Maps (SAMs), a novel topological graph representation that enables navigation in 3D environments using abstract 2D maps without requiring detailed metric information.

Contribution

The paper presents a learnable method to parse various 2D maps into SAMs, facilitating navigation without detailed spatial data, and demonstrates its effectiveness on a quadrupedal robot.

Findings

SAMs enable effective navigation using abstract maps

The method successfully interprets diverse 2D maps into behavioral graphs

Robotic experiments validate the approach's practicality

Abstract

Humans are remarkable in their ability to navigate without metric information. We can read abstract 2D maps, such as floor-plans or hand-drawn sketches, and use them to navigate in unseen rich 3D environments, without requiring prior traversals to map out these scenes in detail. We posit that this is enabled by the ability to represent the environment abstractly as interconnected navigational behaviours, e.g., "follow the corridor" or "turn right", while avoiding detailed, accurate spatial information at the metric level. We introduce the Scene Action Map (SAM), a behavioural topological graph, and propose a learnable map-reading method, which parses a variety of 2D maps into SAMs. Map-reading extracts salient information about navigational behaviours from the overlooked wealth of pre-existing, abstract and inaccurate maps, ranging from floor-plans to sketches. We evaluate the performance of SAMs for navigation, by building and deploying a behavioural navigation stack on a quadrupedal robot. Videos and more information is available at: https://scene-action-maps.github.io.