Towards Robust and Reliable Autonomous Vehicles with Foundation Models
New York University (NYU) via YouTube
Overview
Explore cutting-edge developments in autonomous vehicle technology through this 53-minute seminar from New York University that delves into vision-centric and data-driven methodologies. Learn about the Hydra end-to-end architecture and its multi-target distillation paradigm, while discovering how Multi-modal Large Language Models (MLLMs) are revolutionizing autonomous driving systems. Examine Omnidrive, an innovative LLM-Agent that combines 3D perception, reasoning, and planning capabilities for enhanced vehicle control. Understand the implementation of SSE, a multimodal semantic data selection framework designed to optimize dataset scaling for autonomous vehicle model training. Gain valuable insights into current challenges facing the development of robust autonomous driving systems and the potential solutions being explored in the field.
Syllabus
ECE AI SEMINAR: Towards Robust and Reliable Autonomous Vehicles with Foundation Models
Taught by
NYU Tandon School of Engineering