Polyline Generative Navigable Space Segmentation for Autonomous Visual Navigation

TL;DR

This paper introduces PSV-Net, a self-supervised learning framework using variational autoencoders to segment navigable space in visual data, enabling mapless navigation without extensive labeled datasets.

Contribution

The work presents a novel polyline-based segmentation method using VAE and AE that performs comparably to supervised methods with minimal or no labels.

Findings

PSV-Net achieves high accuracy with few or no labels.

The method enables efficient mapless navigation in real environments.

Self-supervised learning reduces reliance on pixel-level annotations.

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.