Berkeley DeepDrive

Berkeley DeepDrive

UC Berkeley PATH is pleased to announce the creation of the Berkeley DeepDrive (BDD) Industry Consortium. This research alliance will investigate state-of-the-art technologies in computer vision and machine learning for automotive applications. Professor Trevor Darrell, Faculty Director of PATH, will lead the BDD center, with Ken Goldberg and Thomas West serving as associate directors.

Visit BDD's website to learn more about the Consortium's work, partners, and researchers.

The multi-disciplinary Center brings new faculty and researchers together from PATH, the Electrical Engineering and Computer Science Department, Center for Information Technology Research in the Interest of Society (CITRIS) robotics, and the Berkeley Vision and Learning Center (BVLC) to investigate state-of-the-art technologies merging computer vision and machine learning for automotive applications.

The BDD center will guide the next generation of research on deep automotive perception through the integration of two very important technologies: vision and vehicles. The center’s work will comprise fundamental research, embedded/hardened implementation, and real-world demonstrations and will focus on several key research themes, including:

  • Low power and embedded CAFFE development
  • Efficient pedestrian detection
  • Pedestrian intent detection
  • Deep Driving Control policies
  • Scene classification and scene affordance estimation

The CAFFE framework, developed at UC Berkeley by Prof. Darrell’s lab, will serve as the foundation for much of the center’s work. CAFFE is a deep learning framework with expression, speed, and modularity at its core. CAFFE has been applied at scale in a wide range of industries, however, embedded applications of deep learning needed for the automotive world were not a focus area until now.

The Berkeley DeepDrive Center will bring deep automotive perception to the forefront. Conventional deployed technology for automotive computer vision is three to five years removed from the research state-of-the-art. Although dramatic progress has been made in the field of computer vision, the applications have yet to carry over to the automotive field. Thus the need, and driving force behind the Berkeley DeepDrive Center.