Deep Learning Applications for Autonomous Driving
Licentiatavhandling, 2018
Driving path generation was accomplished with an FCN that integrated LIDAR top-views with GPS-IMU data and driving directions. This system was designed to simultaneously carry out perception and planning using as training data real driving sequences that were annotated automatically. By testing several combinations of input data, it was shown that the FCN having access to all the available sensors and the driving directions obtained the best overall accuracy with a MaxF score of 88.13%, about 4.7 percentage points better than the FCN that could use only LIDAR data.
sensor fusion
computer vision
deep learning
autonomous driving
robotic perception and planning
Författare
Luca Caltagirone
Chalmers, Mekanik och maritima vetenskaper, Fordonsteknik och autonoma system
Fast LIDAR-based road detection using fully convolutional neural networks
IEEE Intelligent Vehicles Symposium, Proceedings,;(2017)p. 1019-1024
Paper i proceeding
LIDAR-based Driving Path Generation Using Fully Convolutional Neural Networks
IEEE 20th International Conference on Intelligent Transportation Systems,;Vol. 2018-March(2017)p. 1-6
Paper i proceeding
Caltagirone, L., Bellone, M., and Wahde, M., LIDAR-Camera Fusion for Road Detection using Fully Convolutional Neural Networks
Styrkeområden
Transport
Ämneskategorier
Datorseende och robotik (autonoma system)
Utgivare
Chalmers
Lecture hall GD, Chalmers Tvärgata 5, Chalmers
Opponent: Prof. Jim Tørresen, Department of Informatics, University of Oslo, Norway