How safe is automated driving? Human driver models for safety performance assessment

Roesener, Christian; Hiller, Johannes; Weber, H.; Eckstein, Lutz

doi:10.1109/itsc.2017.8317706

Cited by 10 publications

(7 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The transportation domain has a long history of using simulation models to predict safety impacts of designs (e.g., Perel, 1982). More recently, simulation efforts have been used to assess the safety impacts of advanced driving assistance systems (Bärgman, Boda, & Dozza, 2017; Carter & Burgett, 2009; Gordon et al, 2010; Kusano, Gabler, & Gorman, 2014; Markkula, 2015; Page et al, 2015; Roesener, Hiller, Weber, & Eckstein, 2017; Van Auken et al, 2011). Although they differ in their specific methodologies, these assessments follow a process of integrating data and simulation models to predict safety outcomes.…”

Section: Introductionmentioning

confidence: 99%

“…In this framework, multiple candidate algorithms can be quickly assessed by iterating through this process while keeping the data and model constant. The driver model is a significant component of this process as poor model selection may undermine the accuracy of the safety-related predictions (Bärgman et al, 2017; Roesener et al, 2017). When well-suited models are used, this simulation method can produce accurate and precise results.…”

Section: Introductionmentioning

confidence: 99%

“…When well-suited models are used, this simulation method can produce accurate and precise results. For example, Roesener et al (2017) found their hidden Markov model-based simulation approach predicted actual crash occurrence within 3.5%. As mentioned, so far this type of methodology has been applied mainly to advanced driving assistance systems, but its importance in the context of automation seems even greater because conclusive proof of safety of an automated system under development will be very difficult to obtain from real-world testing alone (Kalra & Paddock, 2016).…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures

McDonald¹,

et al. 2019

View full text Add to dashboard Cite

Objective: This article provides a review of empirical studies of automated vehicle takeovers and driver modeling to identify influential factors and their impacts on takeover performance and suggest driver models that can capture them. Background: Significant safety issues remain in automated-to-manual transitions of vehicle control. Developing models and computer simulations of automated vehicle control transitions may help designers mitigate these issues, but only if accurate models are used. Selecting accurate models requires estimating the impact of factors that influence takeovers. Method: Articles describing automated vehicle takeovers or driver modeling research were identified through a systematic approach. Inclusion criteria were used to identify relevant studies and models of braking, steering, and the complete takeover process for further review. Results: The reviewed studies on automated vehicle takeovers identified several factors that significantly influence takeover time and post-takeover control. Drivers were found to respond similarly between manual emergencies and automated takeovers, albeit with a delay. The findings suggest that existing braking and steering models for manual driving may be applicable to modeling automated vehicle takeovers. Conclusion: Time budget, repeated exposure to takeovers, silent failures, and handheld secondary tasks significantly influence takeover time. These factors in addition to takeover request modality, driving environment, non-handheld secondary tasks, level of automation, trust, fatigue, and alcohol significantly impact post-takeover control. Models that capture these effects through evidence accumulation were identified as promising directions for future work. Application: Stakeholders interested in driver behavior during automated vehicle takeovers may use this article to identify starting points for their work.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures

McDonald¹,

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Process models can be used in a computational simulation framework and provide recommendations for automation design parameters (Biirgman et al, 2017;Roesener et al , 2017). By specifying the driver's control action, these models are able to predict the driver's behavior in a variety of emergency situations.…”

Section: Introductionmentioning

confidence: 99%

Role of Peripheral Vision in Brake Reaction Time During Safety Critical Events

Sarkar

Alambeigi

McDonald

et al. 2021

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

The criticality of a rear end event depends on the brake reaction time (BRT) of the driver. Therefore, distracted driving poses greater threat in such events. Evidence accumulation model (EAM) that uses looming of the lead vehicle as main stimuli has shown significant success in estimating drivers’ BR Ts. It is often argued that drivers collect evidence for braking through peripheral vision, especially during off-road glances, and transition to forward. In this work, we have modeled evidence accumulation as a function of gaze eccentricity for off-road glances while approaching safety critical events. The model is tested with real world crash and near crash event data from SHRP2 naturalistic study. Our model shows that linear relation between gaze eccentricity and evidence accumulation rate during off road glances helps to improve EAM estimation in predicting BRT. We have also shown that brake-light onset does not influence EAM in presence of active looming.

show abstract

“…From a research perspective most autonomous cars evaluation methodologies use base models to assess performance on specific tasks [3], [4]. Although this evaluation is interesting for development it is biased towards the base model and do not present a fair evaluation between acceptable solutions.…”

Section: Introductionmentioning

confidence: 99%

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment

Watanabe

Wolf

2018

2018 Latin American Robotic Symposium, 2018 Brazilian Symposium on Robotics (SBR) and 2018 Workshop on Robotics in Education (W

View full text Add to dashboard Cite

The autonomous car technology promises to replace human drivers with safer driving systems. But although autonomous cars can become safer than human drivers this is a long process that is going to be refined over time. Before these vehicles are deployed on urban roads a minimum safety level must be assured. Since the autonomous car technology is still under development there is no standard methodology to evaluate such systems. It is important to completely understand the technology that is being developed to design efficient means to evaluate it. In this paper we assume safety-critical systems reliability as a safety measure. We model an autonomous road vehicle as an intelligent agent and we approach its evaluation from an artificial intelligence perspective. Our focus is the evaluation of perception and decision making systems and also to propose a systematic method to evaluate their integration in the vehicle. We identify critical aspects of the data dependency from the artificial intelligence state of the art models and we also propose procedures to reproduce them.

show abstract

How safe is automated driving? Human driver models for safety performance assessment

Cited by 10 publications

References 13 publications

Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures

Toward Computational Simulations of Behavior During Automated Driving Takeovers: A Review of the Empirical and Modeling Literatures

Role of Peripheral Vision in Brake Reaction Time During Safety Critical Events

Verisimilar Percept Sequences Tests for Autonomous Driving Intelligent Agent Assessment

Contact Info

Product

Resources

About