Learning Exactly Linearizable Deep Dynamics Models
This work addresses the need for theoretically guaranteed safety in practical engineering applications of machine-learning-based control, though it appears incremental as it builds on existing control theories.
The paper tackled the problem of ensuring safety and high performance in control systems using machine-learning models by proposing a learning method for exactly linearizable dynamical models, which demonstrated good predictive performance and stable control under constraints in real-time automotive engine control.
Research on control using models based on machine-learning methods has now shifted to the practical engineering stage. Achieving high performance and theoretically guaranteeing the safety of the system is critical for such applications. In this paper, we propose a learning method for exactly linearizable dynamical models that can easily apply various control theories to ensure stability, reliability, etc., and to provide a high degree of freedom of expression. As an example, we present a design that combines simple linear control and control barrier functions. The proposed model is employed for the real-time control of an automotive engine, and the results demonstrate good predictive performance and stable control under constraints.