Adaptive Driving Agent: From Driving a Machine to Riding with a Friend

The successful integration of automation in systems that affect human experiences requires the user acceptance of those automated functionalities. For example, the human comfort felt during a ride is affected by the automated control behavior of the vehicle. The challenge presented in this paper is how to develop an intelligent agent that learns its users? driving preferences and adjusts the vehicle control in real time, accordingly, minimizing the number of otherwise required manual interventions. This is a hard problem since users? preferences can be complex, context dependent and do not necessarily translate to the language of machines in a simple and straightforward manner. Our solution includes (1) a simulation test bed, (2) an adaptive intelligent interface and (3) an adaptive agent that learns to predict user's driving discomfort and it also learns to compute corrective actions that maximize user acceptance of automated driving. Overall, we conducted three user studies with 94 subjects in simulated driving scenarios. Our results show that our intelligent agent learned to successfully predict how to adjust the automated driving style to increase user? acceptance by decreasing the number of user manual interventions.

[1]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[2]  Pan Zhao,et al.  A Scenario-Adaptive Driving Behavior Prediction Approach to Urban Autonomous Driving , 2017 .

[3]  Mandy Dotzauer,et al.  Should my car drive as I do? What kind of driving style do drivers prefer for the design of automated driving functions? , 2016 .

[4]  Jagat Jyoti Rath,et al.  Personalised lane keeping assist strategy: adaptation to driving style , 2019, IET Control Theory & Applications.

[5]  Nanning Zheng,et al.  Cognitive Cars: A New Frontier for ADAS Research , 2012, IEEE Transactions on Intelligent Transportation Systems.

[6]  Claudia V. Goldman,et al.  Learning Drivers’ Behavior to Improve Adaptive Cruise Control , 2015, J. Intell. Transp. Syst..

[7]  Joze Guna,et al.  Estimation of the Driving Style Based on the Users’ Activity and Environment Influence , 2017, Sensors.

[8]  Anil K. Jain,et al.  Algorithms for Clustering Data , 1988 .

[9]  Kent Larson,et al.  Expressive driver-vehicle interface design , 2011, DPPI.

[10]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[11]  Josef F. Krems,et al.  Driving comfort, enjoyment and acceptance of automated driving – effects of drivers’ age and driving style familiarity , 2018, Ergonomics.

[12]  Stephen J. Hoch,et al.  Time-inconsistent Preferences and Consumer Self-Control , 1991 .

[13]  Kristin E. Schaefer,et al.  Will passengers trust driverless vehicles? Removing the steering wheel and pedals , 2016, 2016 IEEE International Multi-Disciplinary Conference on Cognitive Methods in Situation Awareness and Decision Support (CogSIMA).

[14]  Mukesh Singhal,et al.  Do You Want Your Autonomous Car to Drive Like You? , 2015, 2017 12th ACM/IEEE International Conference on Human-Robot Interaction (HRI.

[15]  Orit Taubman-Ben-Ari,et al.  The multidimensional driving style inventory a decade later: Review of the literature and re-evaluation of the scale. , 2016, Accident; analysis and prevention.

[16]  Alex Fridman,et al.  What Can Be Predicted from Six Seconds of Driver Glances? , 2016, CHI.

[17]  L. Eboli,et al.  How drivers' characteristics can affect driving style , 2017 .

[18]  Charles X. Ling,et al.  Using AUC and accuracy in evaluating learning algorithms , 2005, IEEE Transactions on Knowledge and Data Engineering.

[19]  Claudia V. Goldman,et al.  Online Prediction of Exponential Decay Time Series with Human-Agent Application , 2016, ECAI.

[20]  Sarit Kraus,et al.  Predicting Human Decision-Making: From Prediction to Action , 2018, Predicting Human Decision-Making.

[21]  Frank E. Pollick,et al.  To Beep or Not to Beep?: Comparing Abstract versus Language-Based Multimodal Driver Displays , 2015, CHI.

[22]  Shai Ben-David,et al.  Understanding Machine Learning: From Theory to Algorithms , 2014 .

[23]  Hong Jiang,et al.  Establishing Style-Oriented Driver Models by Imitating Human Driving Behaviors , 2015, IEEE Transactions on Intelligent Transportation Systems.

[24]  Shiho Kim,et al.  Self-Driving like a Human driver instead of a Robocar: Personalized comfortable driving experience for autonomous vehicles , 2020, ArXiv.

[25]  Claudia V. Goldman,et al.  On Sensitivity and Holding in Automotive Systems , 2016 .