A LiDAR-based real-time capable 3D Perception System for Automated Driving in Urban Domains

TL;DR

This paper introduces a real-time LiDAR-based 3D perception system for urban autonomous driving, capable of modeling environment elements and handling complex scenarios with enhanced accuracy.

Contribution

The system extends current methods with detailed enhancements for perceiving complex urban environments, including non-flat surfaces and overhanging objects, while maintaining real-time performance.

Findings

Effective perception of road users and drivable areas in complex urban scenarios

Robust object tracking with occlusion and ambiguity handling

Real-time processing achieved on urban traffic datasets

Abstract

We present a LiDAR-based and real-time capable 3D perception system for automated driving in urban domains. The hierarchical system design is able to model stationary and movable parts of the environment simultaneously and under real-time conditions. Our approach extends the state of the art by innovative in-detail enhancements for perceiving road users and drivable corridors even in case of non-flat ground surfaces and overhanging or protruding elements. We describe a runtime-efficient pointcloud processing pipeline, consisting of adaptive ground surface estimation, 3D clustering and motion classification stages. Based on the pipeline's output, the stationary environment is represented in a multi-feature mapping and fusion approach. Movable elements are represented in an object tracking system capable of using multiple reference points to account for viewpoint changes. We further enhance the tracking system by explicit consideration of occlusion and ambiguity cases. Our system is evaluated using a subset of the TUBS Road User Dataset. We enhance common performance metrics by considering application-driven aspects of real-world traffic scenarios. The perception system shows impressive results and is able to cope with the addressed scenarios while still preserving real-time capability.