Planning Paths Through Unknown Space by Imagining What Lies Therein

TL;DR

This paper introduces a framework that uses image inpainting on semantically-annotated point clouds to model unknown spaces, improving path planning performance in environments with occlusions.

Contribution

It proposes a novel method combining semantic point clouds and neural inpainting to better predict unknown areas for path planning.

Findings

Enhanced pathfinding performance in unknown environments

Effective use of neural inpainting for semantic point cloud data

Significant improvement over optimistic assumptions in path planning

Abstract

This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an image inpainting neural network to generate a reasonable model of unknown space as free or occupied. Our validation campaign shows that it is possible to greatly increase the performance of standard pathfinding algorithms which adopt the general optimistic assumption of treating unknown space as free.