September 14, 2017
Continuing the momentum of collaboration between artificial intelligence and transportation academics and technology and car companies, Berkeley DeepDrive hosted a retreat on Oct. 19, 2016 to bring academics and industry together, while reporting out project progress.
“These retreats help bridge the gap between researchers and industry and offer a chance for interaction and conversation,” says BDD Director Trevor Darrell.
Led Darrell, with Professor Ken Goldberg and Thomas West serving as associate directors, the BDD Industry Consortium investigates state-of-the-art technologies in computer vision and machine learning for automotive applications. By partnering with private industry sponsors, faculty and researchers from multiple departments and centers develop new and emerging technologies with real-world applications in the automotive industry.
Research highlighted at the meeting included: Toward Safe, Feasible and Human-Like Motion Generation for Urban Autonomous Driving; Implicit Communication through a Car’s Motion and Verifiable Control for (Semi) Autonomous Cars that Learns from Human (Re) Actions; Augmenting Autonomous Vehicle Technology with Infrastructure-to-Vehicle Information; Unsupervised Representation Learning for Autonomous Driving; Recent Results in Visual Perception for Driving; Expert Level Control of Ramp Metering based on Multi-task Deep Reinforcement Learning; Autonomous Driving Model Cars: Learning to drive in unstructured conditions; Understanding Driver Awareness For Smart Vehicles; Secure and Privacy-Preserving Deep Learning; Deep Reinforcement Learning; Offline vs. Online Learning for Deep Robot Control; FPGA PRET Accelerators of Deep Learning Classifiers for Autonomous Vehicles; Improving the Scaling of Deep Learning Networks by Characterizing and Exploiting Soft Convexity; Design Space Exploration for Deep Neural Nets for Advanced Driver Assistance Systems; and Dataset Infrastructure.
Research is proposed by UC Berkeley faculty and approved by a BDD advisory board made up of faculty and sponsor representatives. Although dramatic progress has been made in the field of computer visioning, many of these technologies and theories have yet to carry over to the automotive field. Thus, the need and driving force behind the Berkeley DeepDrive Center.