Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation

Abstract

Detecting navigable space is a fundamental capability for mobile robots navigating in unknown or unmapped environments. In this work, we treat visual navigable space segmentation as a scene decomposition problem and propose Polyline Segmentation Variational autoencoder Network (PSV-Net), a representation learning-based framework for learning the navigable space segmentation in a self-supervised manner. Current segmentation techniques heavily rely on fully-supervised learning strategies which demand a large amount of pixel-level annotated images. In this work, we propose a framework leveraging a Variational AutoEncoder (VAE) and an AutoEncoder (AE) to learn a polyline representation that compactly outlines the desired navigable space boundary. Through extensive experiments, we validate that the proposed PSV-Net can learn the visual navigable space with no or few labels, producing an accuracy comparable to fully-supervised state-of-the-art methods that use all available labels. In addition, we show that integrating the proposed navigable space segmentation model with a visual planner can achieve efficient mapless navigation in real environments.

References in corpus (15)

• Neural Discrete Representation Learning
• EdgeConnect: Generative Image Inpainting with Adversarial Edge Learning
• Recent Advances in Autoencoder-Based Representation Learning
• Multi-Object Representation Learning with Iterative Variational Inference
• MONet: Unsupervised Scene Decomposition and Representation
• Wasserstein Auto-Encoders
• SNE-RoadSeg: Incorporating Surface Normal Information into Semantic Segmentation for Accurate Freespace Detection
• GENESIS: Generative Scene Inference and Sampling with Object-Centric Latent Representations
• SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
• Unifying Map and Landmark Based Representations for Visual Navigation
• Unsupervised Object Segmentation by Redrawing
• Learning Disentangled Joint Continuous and Discrete Representations
• Joint Semantic Segmentation and Boundary Detection using Iterative Pyramid Contexts
• Situational Fusion of Visual Representation for Visual Navigation
• Distantly Supervised Road Segmentation