Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Technology Development of Autonomous Vehicles
share announcement

Technology Development of Autonomous Vehicles

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Robotics and Automation".

Deadline for manuscript submissions: closed (31 January 2023) | Viewed by 4231

Special Issue Editors

Dr. Jonathan Brembeck

E-Mail Website1 Website2
Guest Editor
Institute of System Dynamics and Control, Robotics and Mechatronics Center, German Aerospace Center (DLR), 82234 Weßling, Germany
Interests: autonomous vehicles; system dynamics and simulation; vehicle dynamics control; nonlinear state estimation; machine learning; reinforcement learning; Modelica
Dr. Ricardo De Castro

E-Mail Website
Guest Editor
Department of Mechanical Engineering, University of California, Merced, CA 95343, USA
Interests: vehicle dynamics; vehicle control; electric vehicles; hybrid-electric vehicles; autonomous driving
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Basilio Lenzo

E-Mail Website
Guest Editor
Department of Industrial Engineering, University of Padova, 35131 Padova, Italy
Interests: vehicle dynamics; vehicle control; vehicle state estimation; robotics; control theory
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As the possibilities of autonomous vehicles are broadening the potential development perspectives, the requirements for the necessary technologies to fulfill safe and reliable operations are significantly increasing. The development of AI-driven technologies has long been seen as a key aspect of coping with these requirements. At present, other research fields are emerging, such as robotics inspired by-wire systems for holistic system integration or the safeguard of the developed functionalities. The mechatronic systems and advanced control methods developed for autonomous vehicle control applications have also brought great benefits in terms of ride quality as well as increasingly safe and comfortable autonomous vehicles. For such objectives, several autonomous vehicle subsystems need to be tackled, including braking, steering, suspension, powertrain, on-board network system, data acquisition, sensor fusion, cloud-connectivity etc. Aiming at spreading the latest research in this field, we are pleased to announce a Special Issue on "Technology Development of Autonomous Vehicles". This Special Issue will synergize original and high-quality articles through an international standard peer-review process with the following main topics (not an exhaustive list):

  • Development of autonomous (test) vehicles.
  • Data acquisition of autonomous vehicles with cloud connectivity.
  • Vehicle system dynamics for autonomous vehicles.
  • Simulation and assessment of autonomous vehicles' performance.
  • Planning, execution and validation of experiments.
  • System architecture design, including mechatronic system, controller network etc.
  • Safeguard processes in experiments with autonomous functionalities.
  • Experiment design for validation, especially for AI-based control functions.
  • System design of multi-sensor data fusion (including but not limited to cameras, lidar etc.).
  • Standardization.
  • Virtual function development and testing in xIL experimental setups for autonomous vehicles.

We look forward to your valuable contributions.

Dr. Jonathan Brembeck
Dr. Ricardo De Castro
Prof. Dr. Basilio Lenzo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • autonomous test vehicles
  • trajectory control
  • vehicle dynamics for autonomous cars
  • autonomous vehicle dynamics control
  • path planning
  • experimental assessment
  • standardization
  • maneuvers
  • xIL testing

Published Papers (2 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

24 pages, 4682 KiB  
Article
Reinforcement Learning-Based Path Following Control with Dynamics Randomization for Parametric Uncertainties in Autonomous Driving
by Kenan Ahmic, Johannes Ultsch, Jonathan Brembeck and Christoph Winter
Appl. Sci. 2023, 13(6), 3456; https://doi.org/10.3390/app13063456 - 08 Mar 2023
Viewed by 1516
Abstract
Reinforcement learning-based controllers for safety-critical applications, such as autonomous driving, are typically trained in simulation, where a vehicle model is provided during the learning process. However, an inaccurate parameterization of the vehicle model used for training heavily influences the performance of the reinforcement [...] Read more.
Reinforcement learning-based controllers for safety-critical applications, such as autonomous driving, are typically trained in simulation, where a vehicle model is provided during the learning process. However, an inaccurate parameterization of the vehicle model used for training heavily influences the performance of the reinforcement learning agent during execution. This inaccuracy is either caused by changes due to environmental influences or by falsely estimated vehicle parameters. In this work, we present our approach of combining dynamics randomization with reinforcement learning to overcome this issue for a path-following control task of an autonomous and over-actuated robotic vehicle. We train three independent agents, where each agent experiences randomization for a different vehicle dynamics parameter, i.e., the mass, the yaw inertia, and the road-tire friction. We randomize the parameters uniformly within predefined ranges to enable the agents to learn an equally robust control behavior for all possible parameter values. Finally, in a simulation study, we compare the performance of the agents trained with dynamics randomization to the performance of an agent trained with the nominal parameter values. Simulation results demonstrate that the former agents obtain a higher level of robustness against model uncertainties and varying environmental conditions than the latter agent trained with nominal vehicle parameter values. Full article
(This article belongs to the Special Issue Technology Development of Autonomous Vehicles)
►▼ Show Figures

Figure 1

20 pages, 4226 KiB  
Article
AI-For-Mobility—A New Research Platform for AI-Based Control Methods
by Julian Ruggaber, Kenan Ahmic, Jonathan Brembeck, Daniel Baumgartner and Jakub Tobolář
Appl. Sci. 2023, 13(5), 2879; https://doi.org/10.3390/app13052879 - 23 Feb 2023
Viewed by 1457
Abstract
AI-For-Mobility (AFM) is the new research platform to investigate and implement novel control methods based on Artificial Intelligence (AI) within the Department of Vehicle System Dynamics at the German Aerospace Center (DLR). A production hybrid vehicle serves as a base platform. Since AI-based [...] Read more.
AI-For-Mobility (AFM) is the new research platform to investigate and implement novel control methods based on Artificial Intelligence (AI) within the Department of Vehicle System Dynamics at the German Aerospace Center (DLR). A production hybrid vehicle serves as a base platform. Since AI-based methods are data-driven, the vehicle is equipped with manifold sensors to provide the required data. They measure the vehicle’s state holistically and perceive the surrounding environment, while high performance on-board CPUs and GPUs handle the sensor data. A full by-wire control system enables the vehicle to be used for applications in the field of automated driving. Despite all modifications, it is approved for public road use and meets the driving dynamics properties of a standard road vehicle. This makes it an attractive research and test platform, both for automotive applications and technology demonstrations in other scientific fields (e.g., robotics, aviation, etc.). This paper presents the vehicle’s design and architecture in a detailed manner and shows a promising application potential of AFM in the context of AI-based control methods. Full article
(This article belongs to the Special Issue Technology Development of Autonomous Vehicles)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-2
Back to TopTop