Integration and training of a ROS autonomous driver for human-like driving style in a complex multi-component driving simulator
Authors:
Albert Solernou, Richard Romano, Ioannis Souflas, Foroogh Hajiseyedjavadi, Evangelos Paschalidis, Natasha Merat
Keywords:
ROS communication, AI, human-like, synthetic occupancy grid, simulation testing platform
Abstract:
The advances of the last decade towards a level 4 autonomous car have been remarkable, and still the challenges to reach full automation are numerous. Amongst these, ride experience is regarded as crucial for the general acceptance of such vehicles, while assessing safety and reliability is lacking from a holistic approach. Aiming to address these two issues in parallel, we integrate a motion planner (MP) previously used on a real world car to the University of Leeds Driving Simulator (UoLDS) using the ROS messaging system. We argue that, together with the software stack developed, the UoLDS resulted in a platform suitable for development, testing and safe evaluation of MPs. Furthermore, aiming to capture a human-like driving style, the MP was trained using data coming from the driving simulator. The resulting driving style was ultimately evaluated by a number of participants at the driving simulator with encouraging results.
Cite this article
Solernou A.; Romano R.; Souflas I.; Hajiseyedjavadi F.; Paschalidis E. and Merat N. Integration and training of a ROS autonomous driver for human-like driving style in a complex multi-component driving simulator In: Proceedings of the Driving Simulation Conference 2020 Europe VR, Driving Simulation Association, Antibes, France, 2020, pp. 11-18
@inproceedings{Solernou2020,
title = {Integration and training of a ROS autonomous driver for human-like driving style in a complex multi-component driving simulator},
author = {Albert Solernou and Richard Romano and Ioannis Souflas and Foroogh Hajiseyedjavadi and Evangelos Paschalidis and Natasha Merat},
editor = {Andras Kemeny and Jean-Rémy Chardonnet and Florent Colombet},
year = {2020},
date = {2020-09-09},
booktitle = {Proceedings of the Driving Simulation Conference 2020 Europe VR},
pages = {11-18},
address = {Antibes, France},
organization = {Driving Simulation Association},
abstract = {The advances of the last decade towards a level 4 autonomous car have been remarkable, and still the challenges to reach full automation are numerous. Amongst these, ride experience is regarded as crucial for the general acceptance of such vehicles, while assessing safety and reliability is lacking from a holistic approach. Aiming to address these two issues in parallel, we integrate a motion planner (MP) previously used on a real world car to the University of Leeds Driving Simulator (UoLDS) using the ROS messaging system. We argue that, together with the software stack developed, the UoLDS resulted in a platform suitable for development, testing and safe evaluation of MPs. Furthermore, aiming to capture a human-like driving style, the MP was trained using data coming from the driving simulator. The resulting driving style was ultimately evaluated by a number of participants at the driving simulator with encouraging results.},
keywords = {AI, human-like, ROS communication, simulation testing platform, synthetic occupancy grid},
}
TY - CONF TI - Integration and training of a ROS autonomous driver for human-like driving style in a complex multi-component driving simulator AU - Solernou, Albert AU - Romano, Richard AU - Souflas, Ioannis AU - Hajiseyedjavadi, Foroogh AU - Paschalidis, Evangelos AU - Merat, Natasha C1 - Antibes, France C3 - Proceedings of the Driving Simulation Conference 2020 Europe VR DA - 2020/09/09 PY - 2020 SP - 11 EP - 18 LA - en-US PB - Driving Simulation Association L2 - https://proceedings.driving-simulation.org/proceeding/dsc-2020/integration-and-training-of-a-ros-autonomous-driver-for-human-like-driving-style-in-a-complex-multi-component-driving-simulator ER -
A Driving Simulation Association membership is required in order to download the papers.