AI Learning for Control of Predictive Vehicle Dynamics

Dear Colleagues,

The control of the lateral dynamics of vehicles is a research topic that goes hand in hand with technological development. In recent years, optimization and artificial intelligence algorithms have revolutionized the world of research. A research challenge is that which aims to integrate the control theory of a system with machine learning both at a theoretical and applicative level. Furthermore, the design of autonomous and connected vehicles powered by different forms of energy poses problems of considerable importance and is attracting the attention of scholars from different points of view.

This SI aims to investigate the problems of the control of the dynamics of the modern vehicle equipped with advanced technologies that provide useful data in a predictive manner. Precisely, the data that are well treated by artificial intelligence algorithms can be used to design and/or refine the physical control laws often based on model-based design.

One of the major control techniques used is model predictive control (MPC). Future research aims to integrate all data from sensors and estimators into the MPC loop, and machine learning is the consolidated approach to manage, use, and process data with little computational burden.

This SI aims to publish new research and review articles focusing on control theories, communication methods, applications, and practical implementations relevant to designing vehicles dynamics control systems. This SI includes the following topics:

• Robust AI learning approach for vehicle dynamics control.
• Model predictive control with learned vehicle dynamics for autonomous vehicle path tracking.
• Human-centric AI for vehicle dynamics control.
• Data-driven vs. model-based vehicle dynamics control: Physics-informed neural network (PINN) approach in MPC framework.
• AI-based predictive algorithms for vehicle safety in extreme situations.
• AI-based predictive algorithms for minimizing vehicle energy consumption.
• Fault detection using machine learning approaches in vehicle dynamics control.
• Multi-agent reinforcement learning and distributed machine learning schemes in control systems for connected and autonomous vehicles.
• Integrated intelligent sensing, communications, and computing schemes in control systems for vehicle dynamics control.
• Machine learning approaches to the identification and/or control of autonomous vehicle systems.

Dr. Domenico Bianchi
Guest Editor

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. AI is an international peer-reviewed open access monthly 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 1600 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.

• vehicle dynamics control
• deep learning
• autonomous and connected vehicle control
• model predictive control
• physics-informed neural network
• safety
• energy consumption
• learning control
• integration of AI and control
• human-centric AI for vehicle dynamics control