RT Journal Article
SR Electronic
A1 Feraco, Stefano
A1 Bonfitto, Angelo
A1 Amati, Nicola
A1 Tonoli, Andrea
T1 Redundant Multi-Object Detection for Autonomous Vehicles in Structured Environments
JF Communications - Scientific Letters of the University of Zilina
YR 2022
VO 24
IS 1
SP C1
OP C17
DO 10.26552/com.C.2022.1.C1-C17
UL https://komunikacie.uniza.sk/artkey/csl-202201-0009.php
AB 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.