EMMA: An innovative autonomous driving model

EMMA, the full name of which is End-to-End Multimodal Model for Autonomous Driving, is an autonomous driving model based on a large multimodal language model. It can directly map raw camera sensor data to various driving-specific outputs, such as planning trajectories, perceived objects, and road map elements. EMMA has demonstrated performance comparable to state-of-the-art methods in tasks such as motion planning and 3D object detection, and has achieved competitive results in multiple benchmarks.