LiDAR Based Semantic Perception for Forklifts in Outdoor Environments

TL;DR

This paper introduces a LiDAR-based semantic segmentation framework for autonomous forklifts in outdoor environments, utilizing dual LiDAR sensors to improve obstacle detection and scene understanding for safe navigation.

Contribution

The study presents a novel dual LiDAR system and a lightweight segmentation approach tailored for industrial forklift navigation in complex outdoor settings.

Findings

High segmentation accuracy achieved

Real-time performance demonstrated

Effective obstacle detection in dynamic environments

Abstract

In this study, we present a novel LiDAR-based semantic segmentation framework tailored for autonomous forklifts operating in complex outdoor environments. Central to our approach is the integration of a dual LiDAR system, which combines forward-facing and downward-angled LiDAR sensors to enable comprehensive scene understanding, specifically tailored for industrial material handling tasks. The dual configuration improves the detection and segmentation of dynamic and static obstacles with high spatial precision. Using high-resolution 3D point clouds captured from two sensors, our method employs a lightweight yet robust approach that segments the point clouds into safety-critical instance classes such as pedestrians, vehicles, and forklifts, as well as environmental classes such as driveable ground, lanes, and buildings. Experimental validation demonstrates that our approach achieves high segmentation accuracy while satisfying strict runtime requirements, establishing its viability for safety-aware, fully autonomous forklift navigation in dynamic warehouse and yard environments.