Exploring the who, what, when, where, and why of automated vehicle disengagements.

Automated vehicles are emerging on the transportation networks as manufacturers test their automated driving system (ADS) capabilities in complex real-world environments in testing operations like California's Autonomous Vehicle Tester Program. A more comprehensive understanding of the ADS safety performances can be established through the California Department of Motor Vehicle disengagement and crash reports. This study comprehensively examines the safety performances (159,840 disengagements, 124 crashes, and 3,669,472 automated vehicle miles traveled by the manufacturers) documented since the inauguration of the testing program. The reported disengagements were categorized as control discrepancy, environmental conditions and other road users, hardware and software discrepancy, perception discrepancy, planning discrepancy, and operator takeover. An applicable subset of disengagements was then used to identify and quantify the 5 W's of these safety-critical events: who (disengagement initiator), when (the maturity of the ADS), where (location of disengagement), and what/why (the facts causing the disengagement). The disengagement initiator, whether the ADS or human operator, is linked with contributing factors, such as the location, disengagement cause, and ADS testing maturity through a random parameter binary logit model that captured unobserved heterogeneity. Results reveal that compared to freeways and interstates, the ADS has a lower likelihood of initiating the disengagement on streets and roads compared to the human operator. Likewise, software and hardware, and planning discrepancies are associated with the ADS initiating the disengagement. As the ADS testing maturity advances in months, the probability of the disengagement being initiated by the ADS marginally increases when compared to human-initiated. Overall, the study contributes by understanding the factors associated with disengagements and exploring their implications for automated systems.

[1]  Baoshan Huang,et al.  Multivariate random-parameters zero-inflated negative binomial regression model: an application to estimate crash frequencies at intersections. , 2014, Accident; analysis and prevention.

[2]  Chandra R. Bhat,et al.  Unobserved heterogeneity and the statistical analysis of highway accident data , 2016 .

[3]  Raja Parasuraman,et al.  Humans and Automation: Use, Misuse, Disuse, Abuse , 1997, Hum. Factors.

[4]  Ali Farhadi,et al.  A latent model of discriminative aspect , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[5]  Ward Vanlaar,et al.  Automated vehicles and behavioural adaptation in Canada , 2017 .

[6]  Nazanin Nader,et al.  Autonomous vehicles' disengagements: Trends, triggers, and regulatory limitations. , 2018, Accident; analysis and prevention.

[7]  Sven Beiker,et al.  Road Vehicle Automation 4 , 2015 .

[8]  Ching-Yao Chan,et al.  Acceptance of Full Driving Automation: Personally Owned and Shared-Use Concepts , 2020, Hum. Factors.

[9]  Asad J Khattak,et al.  The role of pre-crash driving instability in contributing to crash intensity using naturalistic driving data. , 2019, Accident; analysis and prevention.

[10]  Niklas Strand,et al.  Semi-automated versus highly automated driving in critical situations caused by automation failures , 2014 .

[11]  Don MacKenzie,et al.  Help or hindrance? The travel, energy and carbon impacts of highly automated vehicles , 2016 .

[12]  Jordan J. Louviere,et al.  Combining sources of preference data , 1998 .

[13]  Daniel J. Fagnant,et al.  Preparing a Nation for Autonomous Vehicles: Opportunities, Barriers and Policy Recommendations , 2015 .

[14]  Ravishankar K. Iyer,et al.  Hands Off the Wheel in Autonomous Vehicles?: A Systems Perspective on over a Million Miles of Field Data , 2018, 2018 48th Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN).

[15]  Natasha Merat,et al.  Transition to manual: driver behaviour when resuming control from a highly automated vehicle , 2014 .

[16]  Santokh Singh,et al.  Critical Reasons for Crashes Investigated in the National Motor Vehicle Crash Causation Survey , 2015 .

[17]  Nazanin Nader,et al.  Examining accident reports involving autonomous vehicles in California , 2017, PloS one.

[18]  Tarek Sayed,et al.  Accident prediction models with random corridor parameters. , 2009, Accident; analysis and prevention.

[19]  Raja Parasuraman,et al.  Performance Consequences of Automation-Induced 'Complacency' , 1993 .

[20]  C. Bhat.  Simulation estimation of mixed discrete choice models using randomized and scrambled Halton sequences , 2003 .

[21]  Mica R. Endsley,et al.  The Out-of-the-Loop Performance Problem and Level of Control in Automation , 1995, Hum. Factors.

[22]  William H. Greene,et al.  NLOGIT version 3.0 : reference guide , 2002 .

[23]  Victoria A Banks,et al.  Keep the driver in control: Automating automobiles of the future. , 2016, Applied ergonomics.

[24]  N A Stanton,et al.  What's skill got to do with it? Vehicle automation and driver mental workload , 2007, Ergonomics.

[25]  Ziqi Song,et al.  A New Method for Microsimulation Model Calibration: A Case Study of I-710 , 2019 .

[26]  Asad J. Khattak,et al.  Safety Impacts of Automated Vehicles in Mixed Traffic , 2018 .

[27]  Dipak Ghosal,et al.  Security vulnerabilities of connected vehicle streams and their impact on cooperative driving , 2015, IEEE Communications Magazine.

[28]  Zhixia Li,et al.  Exploring causes and effects of automated vehicle disengagement using statistical modeling and classification tree based on field test data. , 2019, Accident; analysis and prevention.

[29]  Atorod Azizinamini,et al.  Improved Support Vector Machine Models for Work Zone Crash Injury Severity Prediction and Analysis , 2019, Transportation Research Record: Journal of the Transportation Research Board.

[30]  David A. Hensher,et al.  The Mixed Logit Model: the State of Practice and Warnings for the Unwary , 2001 .

[31]  Lee Skrypchuk,et al.  Analysis of autopilot disengagements occurring during autonomous vehicle testing , 2018, IEEE/CAA Journal of Automatica Sinica.

[32]  Ragunathan Rajkumar,et al.  Towards a viable autonomous driving research platform , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[33]  William J. Horrey,et al.  Automated driving: Safety blind spots , 2018 .

[34]  Steven E. Shladover,et al.  Connected and automated vehicle systems: Introduction and overview , 2018, J. Intell. Transp. Syst..

[35]  K. Train.  Discrete Choice Methods with Simulation , 2003 .

[36]  Bart van Arem,et al.  Policy and society related implications of automated driving: A review of literature and directions for future research , 2017, J. Intell. Transp. Syst..

[37]  Asad J. Khattak,et al.  A heterogeneity based case-control analysis of motorcyclist's injury crashes: Evidence from motorcycle crash causation study. , 2018, Accident; analysis and prevention.

[38]  Marcelo H. Ang,et al.  Perception, Planning, Control, and Coordination for Autonomous Vehicles , 2017 .

[39]  Neville A. Stanton,et al.  Takeover Time in Highly Automated Vehicles: Noncritical Transitions to and From Manual Control , 2017, Hum. Factors.

[40]  Behram Wali,et al.  Exploratory analysis of automated vehicle crashes in California: A text analytics & hierarchical Bayesian heterogeneity-based approach. , 2019, Accident; analysis and prevention.

[41]  Lorrie Faith Cranor,et al.  A Framework for Reasoning About the Human in the Loop , 2008, UPSEC.

[42]  Sherali Zeadally,et al.  Autonomous Cars: Research Results, Issues, and Future Challenges , 2019, IEEE Communications Surveys & Tutorials.

[43]  Kaan Ozbay,et al.  Developments in connected and automated vehicles , 2017, J. Intell. Transp. Syst..

[44]  Natasha Merat,et al.  Behavioural changes in drivers experiencing highly-automated vehicle control in varying traffic conditions , 2013 .

[45]  Asad J. Khattak,et al.  Development of Safety Performance Functions: Incorporating Unobserved Heterogeneity and Functional Form Analysis , 2018 .

[46]  Klaus Bengler,et al.  How Traffic Situations and Non-Driving Related Tasks Affect the Take-Over Quality in Highly Automated Driving , 2014 .

[47]  Mashrur Chowdhury,et al.  Risk Analysis of Autonomous Vehicles in Mixed Traffic Streams , 2017 .

[48]  Steven E. Shladover,et al.  Potential Cyberattacks on Automated Vehicles , 2015, IEEE Transactions on Intelligent Transportation Systems.

[49]  H. Bozdogan.  Model selection and Akaike's Information Criterion (AIC): The general theory and its analytical extensions , 1987 .

[50]  Kevin Heaslip,et al.  CPS: an efficiency-motivated attack against autonomous vehicular transportation , 2013, ACSAC.

[51]  Natasha Merat,et al.  Highly Automated Driving, Secondary Task Performance, and Driver State , 2012, Hum. Factors.

[52]  Yan Huang,et al.  Camera calibration and vehicle tracking: Highway traffic video analytics , 2014 .

[53]  I. Nourbakhsh,et al.  On the future of transportation in an era of automated and autonomous vehicles , 2019, Proceedings of the National Academy of Sciences.

[54]  Sai Chand,et al.  Autonomous Vehicles: Disengagements, Accidents and Reaction Times , 2016, PloS one.

[55]  Abolfazl Mohammadian,et al.  Simultaneous estimation of battery electric vehicle adoption with endogenous willingness to pay , 2019, eTransportation.