Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation
This addresses the problem of reducing annotation costs for autonomous navigation in unknown environments, though it is incremental as it builds on existing segmentation and VAE techniques.
The paper tackles visual navigable space segmentation for mobile robots by proposing PSV-Net, a self-supervised framework using polyline representations, achieving accuracy comparable to fully-supervised state-of-the-art methods with no or few labels.
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.