Sikai Lu

Title: Innovations in Vehicle-Road Cooperative Control: The Contributions of Sikai Lu

Introduction: Sikai Lu, an inventive mind based in Zhenjiang, China, has made significant strides in the field of vehicle-road cooperative control systems. His innovative approach to addressing complex intersections demonstrates the potential of federated reinforcement learning techniques in improving traffic management and vehicle communication.

Latest Patents: One of Sikai Lu's notable patents is titled "Multi-intelligence federated reinforcement learning-based vehicle-road cooperative control system and method at complex intersection." This patent introduces a comprehensive control framework that integrates static processing modules from Road Side Units (RSU) with dynamic processing modules from vehicles. The framework utilizes historical road information provided by the RSU module and employs the Federated Twin Delayed Deep Deterministic policy gradient (FTD3) algorithm. This innovative algorithm facilitates the connection between federated learning and reinforcement learning while safeguarding privacy by transmitting only neural network parameters instead of vehicle samples.

Career Highlights: Sikai Lu is affiliated with Jiangsu University, where his research and development efforts have been pivotal in advancing cooperative vehicle control systems. His work not only enhances the efficiency of traffic systems but also contributes towards creating safer driving environments through intelligent communication between vehicles and road infrastructure.

Collaborations: Throughout his career, Sikai Lu has collaborated with esteemed colleagues such as Yingfeng Cai and Long Chen. These partnerships have played a vital role in pushing the boundaries of research in vehicle-road cooperative systems and have fostered an environment for innovative problem-solving.

Conclusion: Sikai Lu's contributions to the domain of vehicle-road cooperative control systems showcase the fusion of advanced algorithms and practical applications in real-world traffic scenarios. His patent on the federated reinforcement learning framework not only underscores his inventive spirit but also sets a path towards the future of intelligent transportation systems.