Reinforcement Learning for Optimal Experiment Design in Parameter Identification of Mechatronic Systems
This work addresses the need for automated, safe excitation signal design in system identification, reducing reliance on expert knowledge.
The paper proposes a reinforcement learning agent for optimal experiment design in parameter identification of mechatronic systems, achieving competitive estimation accuracy across three parameters with only 0.75% safety violations, outperforming classical baselines.
Informative excitation signals are critical for accurate system identification of mechatronic systems, yet classical system identification (SI) approaches require expert knowledge and hand-crafted signal design to respect hardware safety constraints, limiting their generalizability. We propose a reinforcement learning (RL) agent that learns optimal excitation signals for a Quanser Aero 2 testbed while autonomously enforcing safety constraints through reward shaping. Evaluated across 10 independent training seeds, our comprehensive agent achieves competitive estimation accuracy across all three identified parameters, outperforming classical baselines while incurring only 0.75% safety violations.