Planning Paths through Occlusions in Urban Environments

TL;DR

This paper introduces a framework that uses inpainting of occluded lidar data to improve path planning in urban environments, enabling longer, more feasible routes that better match ground truth paths.

Contribution

The novel contribution is the integration of inpainting with dynamic path planning to handle occlusions in urban navigation scenarios.

Findings

Inpainting allows planning longer paths through occluded areas.

The approach yields paths closer to ground truth compared to existing methods.

Real-time lidar data demonstrates practical effectiveness.

Abstract

This paper presents a novel framework for planning in unknown and occluded urban spaces. We specifically focus on turns and intersections where occlusions significantly impact navigability. Our approach uses an inpainting model to fill in a sparse, occluded, semantic lidar point cloud and plans dynamically feasible paths for a vehicle to traverse through the open and inpainted spaces. We demonstrate our approach using a car's lidar data with real-time occlusions, and show that by inpainting occluded areas, we can plan longer paths, with more turn options compared to without inpainting; in addition, our approach more closely follows paths derived from a planner with no occlusions (called the ground truth) compared to other state of the art approaches.