The National Science Foundation has awarded professor Guanpeng Li of the University of Iowa’s Department of Computer Science a $600,000 grant to develop advanced algorithms aimed at improving the safety of autonomous vehicles.
The funding supports a project titled “Collaborative Research: MELIOREM: An Integrated Evaluation Cyberinfrastructure towards Safe and Dependable Autonomous Driving Systems.”
The MELIOREM platform will provide a comprehensive testing platform for autonomous vehicles (AVs), simulating a wide range of everyday driving conditions encountered on public roads. By using large-scale computing resources, the project will enable developers to identify safety vulnerabilities and rigorously test AV systems under different scenarios.
Traditional methods for testing AVs often struggle to meet the substantial computational demands of real-world simulations, leading to state space explosions and hindering the detection of critical safety issues. AV software is complex, making it time-consuming to identify and address errors quickly.
MELIOREM aims to overcome these challenges, offering a cutting-edge solution to enhance AV safety, while also serving as a tool for academia and industry to advance transportation safety.
Mr. Li’s research extends beyond AV safety, with interests in high-performance computing (HPC) fault tolerance, lossy data compression for HPC, machine learning dependability, and approximate computing.
