A Behavioral Approach to Visual Navigation with Graph Localization Networks

Abstract

Inspired by research in psychology, we introduce a behavioral approach for visual navigation using topological maps. Our goal is to enable a robot to navigate from one location to another, relying only on its visual input and the topological map of the environment. We propose using graph neural networks for localizing the agent in the map, and decompose the action space into primitive behaviors implemented as convolutional or recurrent neural networks. Using the Gibson simulator, we verify that our approach outperforms relevant baselines and is able to navigate in both seen and unseen environments.

Video: https://youtu.be/nN3B1F90CFM

References in corpus (15)

• Adam: A Method for Stochastic Optimization
• Sequence to Sequence Learning with Neural Networks
• Semi-Supervised Classification with Graph Convolutional Networks
• End to End Learning for Self-Driving Cars
• Joint 2D-3D-Semantic Data for Indoor Scene Understanding
• How Powerful are Graph Neural Networks?
• Building Generalizable Agents with a Realistic and Rich 3D Environment
• Modular Multitask Reinforcement Learning with Policy Sketches
• MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
• Neural Map: Structured Memory for Deep Reinforcement Learning
• Unifying Map and Landmark Based Representations for Visual Navigation
• Semi-parametric Topological Memory for Navigation
• One-Shot Hierarchical Imitation Learning of Compound Visuomotor Tasks
• Visual Semantic Navigation using Scene Priors
• Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration

Cited by in corpus (5)

• Mapless Navigation among Dynamics with Social-safety-awareness: a reinforcement learning approach from 2D laser scans
• Learning Object Relation Graph and Tentative Policy for Visual Navigation
• Graph Attention Memory for Visual Navigation
• Bayesian Relational Memory for Semantic Visual Navigation
• Deep Visual MPC-Policy Learning for Navigation