Safe Control Transitions: Machine Vision Based Observable Readiness Index and Data-Driven Takeover Time Prediction

Greer, Ross; Deo, Nachiket; Rangesh, Akshay; Gunaratne, Pujitha; Trivedi, Mohan M.

doi:10.48550/arxiv.2301.05805

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A key component to understanding driver readiness is hand activity, as a distracted driver often has their hands off the wheel or on other devices like a phone. Rangesh et al (Rangesh et al, 2021) and Deo & Trivedi (Deo & Trivedi, 2019) show that driver hand activity is the most important component of models for prediction of driver readiness and takeover time, two metrics critical to safe control transitions in autonomous vehicles (Greer et al, 2023) (Cummings & Bauchwitz, 2021). Such driver-monitoring models take hand activity classes and held-object classes as input, among other components, as illustrated in Figure 1.…”

Section: Safety and Advanced Driver Assistance Systemsmentioning

confidence: 99%

Multi-View Ensemble Learning With Missing Data: Computational Framework and Evaluations using Novel Data from the Safe Autonomous Driving Domain

Greer¹,

Lulua²,

Gopalkrishnan³

et al. 2023

Preprint

View full text Add to dashboard Cite

Real-world applications with multiple sensors observing an event are expected to make continuously-available predictions, even in cases where information may be intermittently missing. We explore methods in ensemble learning and sensor fusion to make use of redundancy and information shared between four camera views, applied to the task of hand activity classification for autonomous driving. In particular, we show that a late-fusion approach between parallel convolutional neural networks can outperform even the best-placed single camera model. To enable this approach, we propose a scheme for handling missing information, and then provide comparative analysis of this late-fusion approach to additional methods such as weighted majority voting and model combination schemes.

show abstract