BROOK Dataset: A Playground for Exploiting Data-Driven Techniques in Human-Vehicle Interactive Designs

Junyu Liu, Yicun Duan, Zhuoran Bi, Xiaoxing Ming, Wangkai Jin, Zilin Song, and Xiangjun Peng

Designed and proposed BROOK dataset, a multi-modal dataset with facial video records through a year-long study, aiming to deliver effective building block for exploring data-driven Human-Vehicle Interaction designs. BROOK dataset comprehensively covering 11 dimensions of data for 34 drivers. Two example studies are carried out using BROOK to justify the applicability of BROOK dataset. We also identify key learning lessons from building BROOK dataset, and discuss about possible follow-up studies.