Bolei Zhou, an assistant professor of computer science at the UCLA Samueli School of Engineering, has received a three-year, $960,000 grant from the National Science Foundation to lead the development of MetaDriverse – a new open-source simulation platform aiming to democratize AI research of autonomous driving.
The promised benefits of autonomous driving powered by artificial intelligence, like safer transportation and more efficient mobility, is transforming daily life and the economy. Driving simulators provide a cost-effective and safe alternative for the development and evaluation of new AI algorithms. However, existing driving simulators with limited assets and complexity cannot accommodate the needs of the rapidly progressing AI fields.
MetaDriverse is built upon the existing open-source MetaDrive simulator developed in Zhou’s lab, with substantial extensions of new features and capabilities such as importing open assets from the real world and realistic visual rendering. This new platform will facilitate compelling research opportunities in various disciplines, including computer vision, computer graphics, machine learning, and human-machine interaction.
This research project is a part of the $1.86 million collaborative grant between Zhou’s lab at UCLA and the research groups of Trevor Darrell and Angjoo Kanazawa at UC Berkeley’s Electrical Engineering and Computer Science Department, with Zhou as the overall principal investigator of the joint effort. Zhou’s lab has been pioneering interpretable AI for computer vision and machine autonomy. He also holds an appointment in the UCLA Computational Medicine Department.
MetaDriverse aims to grow into a community research infrastructure and bring significant impacts on the burgeoning autonomous driving industry. Additionally, it will provide interactive teaching toolkits for STEM education, particularly for students from underserved communities with limited computation resources.