Deep learning of vehicle dynamics⁎⁎This project has received funding from the European Defence Fund programme under grant agreement number No 101103386 and has also been supported by the Air Force Office of Scientific Research under award number FA8655-23-1-7061. Views and opinions expressed are however those of the authors only and do not necessarily reflect those of the European Union or the European Commission. Neither the European Union nor the granting authority can be held responsible for

• Published in: IFAC-PapersOnLine Vol. 58; no. 15; pp. 283 - 288
• Main Authors: Szécsi, M., Györök, B., Weinhardt-Kovács, Á., Beintema, G.I., Schoukens, M., Péni, T., Tóth, R.
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 2024
• Subjects: Automotive system identification; Deep learning; modelling; Nonlinear system identification; UAVs; Deep learning; Nonlinear system identification; Automotive system identification; modelling; UAVs
• ISSN: 2405-8963; 2405-8963
• DOI: 10.1016/j.ifacol.2024.08.542

Recent advances in deep-learning-based identification of dynamic systems have resulted in a new generation of approaches utilizing state-space neural models with innovation noise structure, improved reformulation of multiple shooting, batch optimization, and a subspace identification-inspired form of encoders. The latter is used to learn a reconstructability map to estimate model states from past inputs and outputs. By using the SUBNET approach, which belongs to the state-of-the-art of these methods, we show how to effectively use these approaches to identify reliable vehicle models from data both in continuous and discrete time, respectively. We showcase the approach on the identification of the dynamics of a Crazyflie 2.1 nano-quadcopter and an F1tenth electric car both in a high-fidelity simulation environment, and in case of the electric car, on real measured data. The results indicate that new-generation of deep-learning methods offer Efficient system identification of vehicle dynamics in practice.