Making Our Tech Safe: A Researcher’s Quest

Imagine a world where the gadgets we rely on every day, like cars and medical devices, aren’t just smart but also incredibly safe. That’s the vision that Lu, a Ph.D. candidate at the University of Pennsylvania, is working hard to make a reality.

Cyber-physical systems (CPS) are at the heart of our modern life, allowing technology to interact intelligently with the physical world. These systems are crucial for everything from the automobiles we drive to the heating and cooling in our buildings and even the smart grids that power our electricity. Lu’s research aims to enhance the reliability and safety of these systems.

Under the guidance of the director of the PRECISE Center, Cecilia Fitler Moore, and another research professor in the computer and information science department, Lu focuses on a major challenge: making sure that these advanced systems don’t just work well but are also safe and can react properly in real time.

Lu, who joined the University of Pennsylvania in 2019, uses groundbreaking techniques in neural network repair. By doing this, he’s able to ensure that the systems meet strict safety standards. “I believe my research could have significant implications for the future use of deep models in safety-critical applications,” Lu says.

His work demonstrates how deep learning models can be adapted to uphold safety in crucial settings, leading the way for the integration of these technologies into life-saving devices like autonomous vehicles and medical instruments.