Redundant Multi-Object Detection for Autonomous Vehicles in Structured Environments
Redundant Multi-Object Detection for Autonomous Vehicles in Structured Environments
Author(s): Stefano Feraco, Angelo Bonfitto, Nicola Amati, Andrea TonoliSubject(s): Transport / Logistics
Published by: Žilinská univerzita v Žilině
Keywords: perception; autonomous driving; obstacle detection; point-cloud segmentation; single shot detector; LiDAR (Light Detection and Ranging);
Summary/Abstract: This paper presents a redundant multi-object detection method for autonomous driving, exploiting a combination of Light Detection and Ranging (LiDAR) and stereocamera sensors to detect different obstacles. These sensors are used for distinct perception pipelines considering a custom hardware/software architecture deployed on a self-driving electric racing vehicle. Consequently, the creation of a local map with respect to the vehicle position enables development of further local trajectory planning algorithms. The LiDAR-based algorithm exploits segmentation of point clouds for the ground filtering and obstacle detection. The stereocamera-based perception pipeline is based on a Single Shot Detector using a deep learning neural network. The presented algorithm is experimentally validated on the instrumented vehicle during different driving maneuvers.
Journal: Komunikácie - vedecké listy Žilinskej univerzity v Žiline
- Issue Year: 24/2022
- Issue No: 1
- Page Range: 1-17
- Page Count: 17
- Language: English