Publisher URL: | https://www.scitepress.org/Papers/2022/111408/111408.pdf |
Publisher DOI: | 10.5220/0011140800003271 |
Title: | Robust neural network for sim-to-real gap in end-to-end autonomous driving |
Language: | English |
Authors: | Pareigis, Stephan ![]() Maaß, Fynn |
Editor: | Gini, Giuseppina Nijmeijer, Henk Burgard, Wolfram Filev, Dimitar |
Keywords: | Sim-to-Real Gap; End-to-End Learning; Autonomous Driving; Artificial Neural Network; CARLA Simulator; Robust Control; PilotNet |
Issue Date: | 2022 |
Publisher: | SciTePress |
Part of Series: | Proceedings of the 19th International Conference on Informatics in Control, Automation and Robotics (ICINCO 2022) |
Volume number: | 1 |
Startpage: | 113 |
Endpage: | 119 |
Conference: | International Conference on Informatics in Control, Automation and Robotics 2022 |
Abstract: | A neural network architecture for end-to-end autonomous driving is presented, which is robust against discrepancies in system dynamics during the training process and in application. The proposed network architecture presents a first step to alleviate the simulation to reality gap with respect to differences in system dynamics. A vehicle is trained to drive inside a given lane in the CARLA simulat... |
URI: | http://hdl.handle.net/20.500.12738/13262 |
ISBN: | 978-989-758-585-2 |
ISSN: | 2184-2809 |
Institute: | Department Informatik Fakultät Technik und Informatik |
Type: | Chapter/Article (Proceedings) |
Appears in Collections: | Publications without full text |
Show full item record
Add Files to Item
Note about this record
Export
This item is licensed under a Creative Commons License