Introduction
The PIA project is a collaborative talent management project, a joint endeavor of the Continental Autonomous Mobility Hungary Kft and the Faculty of Electrical Engineering and Informatics of the Budapest University of Technology and Economics (BME). The project was initiated in 2018 when Continental created a Deep Machine Learning Competence Center in Budapest.
The PIA project supports young talents and researchers in working on the challenges of deep machine learning algorithms with applications related to autonomous mobility to provide safe, robust, and cost-effective solutions. The program contributes to sustaining BME’s world-class competencies in the field. Two departments are primarily involved in the project: Telecommunications and Artificial Intelligence and Control Engineering and Information Technology.
Thanks to the generous support of more than 80 mHUF provided by Continental, the PIA program supported many scholarships. A total of 16 mHUF was provided to BME researchers, 19 mHUF was provided to PhD students, and more than 80 scholarships were granted to BSc and MSc students (up to June 2024). In addition to scholarships, the program also offers access to cloud-based infrastructure suitable for developing deep learning algorithms. A laboratory was also equipped with a „Duckie Town” featuring mobile robots. Support for successful students to participate in international competitions was also part of the PIA project, and such opportunities are continuously sought. PIA students are also encouraged and supported to present their results at scientific conferences, publish jornal papers and participate at the Student Scientific Conferences (TDK and OTDK).
Continental encourages the talents enrolled in the PIA project by providing them with internship opportunities and later job offers where they can challenge their knowledge in a professional industrial environment.
More than three decades have passed since the first computer-controlled vehicle rolled out from Carnegie Mellon University’s research lab in 1986 named Navlab 1. More interestingly, another great advance in the field was presented with ALVINN (Autonomous Land Vehicle In a Neural Network) in 1989, which serves as ground truth for machine learning tackling the domain. Now we call them self-driving vehicles and with the advances in electrical engineering, the technology became commercially available. Advanced Driver Assistance Systems (ADAS) reached maturity to provide a wide variety of solutions for automated driving with the combination of classic and modern signal processing and control engineering methods, but the gap between automated and autonomous driving is not bridged yet. One of the major requirement for an autonomous vehicle is reasoning in the most severe driving scenarios. We believe that the best way to obtain reasoning in a computer system is via deep reinforcement learning (DRL), thus our PIA research group focuses on delivering autonomous driving solutions with the power of deep learning and reinforcement learning.
The PIA project actions are discussed, evaluated and defined based on project KPIs at steering committee meeting organized twice a year.
First steering board meeting of the PIA project (March 2019), from left to right: Prof. Géza Németh (BME TMIT), Dr. Bálint Gyires-Tóth (BME TIMT), Mr. Robert Móni (BME TMIT), Prof. László Jakab (BME VIK, Dean), Mr. András Róka (Continental), Dr. Róbert Keszte (Continental Automotive Hungary Ltd., CEO), Jens Brüning (Continental, Deep Learning Competence Center, COO)