Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data

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

doi:10.1109/itsc48978.2021.9564434

Cited by 7 publications

(4 citation statements)

References 17 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

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

show abstract

“…Another motivational factor behind those research studies was to derive indicators of how to conceive takeover strategies in simulation models and automated driving systems with respect to lead times and post-ToC behavior. Recently, studies have focused on human responses to prototypical Level 3 automated driving systems in terms of physiological effects, risk acceptance, comfort level, trust, and various other aspects from the perspective of being in a passenger role during Level 3 operation [12][13][14][15][16][17][18]. An extensive literature review examining various influential factors on takeover performance is given by [19].…”

Section: Transitions Of Controlmentioning

confidence: 99%

Control Transitions in Level 3 Automation: Safety Implications in Mixed-Autonomy Traffic

Alms,

Wagner

2023

Safety

View full text Add to dashboard Cite

Level 3 automated driving systems could introduce challenges to traffic systems as they require a specific lead time in their procedures to ensure the safe return of vehicle control to the driver. These processes, called ’transitions of control’, may particularly pose complications in accelerating traffic flows when regulations mandate control transitions due to an operational speed limitation of 60 km/h as established in recent certification processes based on UNECE regulations from 2021. To investigate these concerns, we conducted a comprehensive simulation study to examine potential safety implications arising from control transitions within mixed-autonomy traffic. The simulation results indicate adverse safety impacts due to increased safety-relevant interactions between vehicles caused by transitions of control in dynamic traffic flow conditions. Our findings also reveal that those effects could become stronger once string unstable ACC controllers are deployed as well.

show abstract

“…Due to the heterogeneity among human drivers, the reaction time can vary substantially under identical driving scenarios; for example, senior drivers might require more time to react. 1 How to incorporate individual variation under critical situations is an interesting problem.…”

mentioning

confidence: 99%

“…The paper proposed a model to predict latent driver state based on driver state and environment monitoring, which is crucial in the decision to issue an RtI request. Due to the heterogeneity among human drivers, the reaction time can vary substantially under identical driving scenarios; for example, senior drivers might require more time to react 1 . How to incorporate individual variation under critical situations is an interesting problem.…”

mentioning

confidence: 99%

Discussion of “some statistical challenges in automated driving systems”

Guo

2023

Appl Stoch Models Bus & Ind

View full text Add to dashboard Cite

Autonomous Vehicles that Alert Humans to Take-Over Controls: Modeling with Real-World Data

Cited by 7 publications

References 17 publications

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

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

Control Transitions in Level 3 Automation: Safety Implications in Mixed-Autonomy Traffic

Discussion of “some statistical challenges in automated driving systems”

Contact Info

Product

Resources

About