Our research in the Smart, Reliable, and Interpretable Systems Lab primarily focuses on Interpretable Fault Diagnosis and Control with Formal Methods and Their Applications in complex electromechanical systems, aiming to enhance system intelligence, reliability, and interpretability.

• Interpretable Fault Diagnosis aims to provide transparent and understandable explanations for system faults through advanced interpretability techniques. Our work encompasses diverse directions, including symbolic neural networks, sparse temporal logic explanations, and explainable machine learning for reliable fault analysis.
• Control Synthesis with Temporal Logic aims to develop robust control strategies that adhere to specified temporal logic constraints. Our research spans key areas such as signal temporal logic-based control design, logic graph construction, and real-time implementations in safety-critical systems.
• Robot Control with Machine Learning aims to enhance the adaptability and precision of robotic systems using state-of-the-art machine learning techniques. Our work includes reinforcement learning for dynamic motion control, imitation learning for human-like coordination, and transfer learning for sim-to-real performance.
• Intelligent Task Scheduling and Planning focuses on optimizing the assignment of tasks and resources in complex environments using intelligent algorithms. Our research covers adaptive scheduling methods, multi-agent planning, and real-time decision-making in constrained scenarios.
• Intelligent Signal Processing aims to extract, analyze, and interpret valuable information from complex and noisy signals using advanced processing methods. Our work includes instantaneous frequency analysis, fault signal modeling, and interpretable signal processing techniques for industrial applications.
• System Design and Inverse Dynamic Problems aim to tackle the complexities of designing and analyzing advanced systems under dynamic conditions. Our work encompasses a wide range of directions, including complex system modeling and parameter estimation, dynamic behavior analysis, optimization-based inverse dynamics, and robust performance evaluation.