Neural Topological SLAM for Visual Navigation

By Devendra Singh Chaplot, Ruslan Salakhutdinov, Abhinav Kumar Gupta, Saurabh Gupta. 2020

381 citations recorded by the source corpus.

This paper studies the problem of image-goal navigation which involves navigating to the location indicated by a goal image in a novel previously unseen environment. To tackle this problem, we design topological representations for space that effectively leverage semantics and afford approximate geometric reasoning. At the heart of our representations are nodes with associated semantic features, that are interconnected using coarse geometric information. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation. Experimental study in visually and physically realistic simulation suggests that our method builds effective representations that capture structural regularities and efficiently solve long-horizon navigation problems. We observe a relative improvement of more than 50% over existing methods that study this task.

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Continuous Scene Representations for Embodied AI (2022, methodology): “Neural graphbased [9, 10, 43, 58] and dense representations [8, 25] have been proposed to construct the map of the environment.”
A Survey of Embodied AI: From Simulators to Research Tasks (2021, neutral): “Many types of goals have been used for this task, such as points, objects, images [78, 79] and areas [17].”
How to Train PointGoal Navigation Agents on a (Sample and Compute) Budget (2020, methodology): “provements on ObjectNav [6], ImageNav [7], and PointNav without GPS+Compass [19].”
NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration (2023, methodology): “These policies have been trained with reinforcement learning to maximize coverage, predicting semantically rich regions, intrinsic rewards [13, 14, 18, 19], or by using planning in conjunction with latent variable and affordance models [17, 20, 21].”
Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI (2021, background): “A popular downstream application for large-scale 3D reconstruction datasets has been to use them with 3D simulation platforms [6, 14, 19] to study embodied AI tasks such as visual navigation [6, 27– 30].”
From Seeing to Moving: A Survey on Learning for Visual Indoor Navigation (VIN) (2020, methodology): “Map-like environment representations are always used for navigation tasks, such as non-parametric landmark graph [Savinov et al., 2018], top-down egocentric obstacle map [Gupta et al., 2017] and semantic map [Chaplot et al., 2020a] built from visual observations.”
Topological Planning with Transformers for Vision-and-Language Navigation (2020, methodology): “Similar to prior work [9, 36, 42], we represent the environment as a graph in which each node is an observation and each edge represents the connectivity (or reachability) between two nodes.”
Semantic Curiosity for Active Visual Learning (2020, neutral): “an image [12, 58], and navigating to a set of objects in order to answer a question [16, 25].”
Differentiable SLAM-net: Learning Particle SLAM for Visual Navigation (2021, background): “A number of learning based approaches has been proposed for visual navigation recently [23; 3; 43; 35; 60; 10; 11; 51].”
Object Goal Navigation using Goal-Oriented Semantic Exploration (2020, background): “shown to improve performance as well as sample efficiency over end-to-end learning-based methods for different navigation tasks [9, 11], however they learn semantics implicitly.”
Multi-Scale Gaussian-Language Map for Zero-shot Embodied Navigation and Reasoning (2026, unknown): “1, existing semantic map structures can be broadly categorized into grid maps [3], topological maps [4, 42], and dense geometric maps [8].”