Researchers have introduced BATON, a new large-scale dataset designed to capture multimodal data related to driving automation transitions. The dataset includes front-view video, in-cabin video, vehicle dynamics, and route context from 127 drivers over 136.6 hours of driving. Three benchmark tasks—driving action understanding, handover prediction, and takeover prediction—were defined and evaluated, showing that combining visual data with vehicle and route context significantly improves prediction accuracy over using visual input alone. AI
IMPACT This dataset could advance the development of more proactive and context-aware human-machine interfaces for assisted driving systems.
RANK_REASON The cluster contains an academic paper detailing a new dataset and benchmark for a specific research area. [lever_c_demoted from research: ic=1 ai=0.7]
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
