Imitation Learning for Vision-based Lane Keeping Assistance
Paper i proceeding, 2017

This paper aims to investigate direct imitation learning from human drivers for the task of lane keeping assistance in highway and country roads using grayscale images from a single front view camera. The employed method utilizes convolutional neural networks (CNN) to act as a policy that is driving a vehicle. The policy is successfully learned via imitation learning using real-world data collected from human drivers and is evaluated in closed-loop simulated environments, demonstrating good driving behaviour and a robustness for domain changes. Evaluation is based on two proposed performance metrics measuring how well the vehicle is positioned in a lane and the smoothness of the driven trajectory.

Författare

Christopher Innocenti

Zenuity

Henrik Linden

Zenuity

Ghazaleh Panahandeh

Zenuity

Lennart Svensson

Chalmers, Signaler och system, Signalbehandling och medicinsk teknik, Signalbehandling

Nasser Mohammadiha

Zenuity

IEEE International Conference on Intelligent Transportation Systems-ITSC

2153-0009 (ISSN)

20th IEEE International Conference on Intelligent Transportation Systems (ITSC)
Yokohama, Japan,

Ämneskategorier

Infrastrukturteknik

Robotteknik och automation

Datorseende och robotik (autonoma system)