Matsuo Institute: VLA for Autonomous Driving

Overview At Matsuo Institute, I am working on the development of a Vision Language Action (VLA) model for autonomous driving. This project builds upon existing research such as Simlingo and OpenEMMA. Key Activities Conducted closed loop autonomous driving verification using CARLA, an Unreal Engine based simulator. Focused on identifying failure cases and continuously improving the model's capabilities to navigate complex driving scenarios.