Modeling Eye-Gaze Behavior of Electric Wheelchair Drivers via Inverse Reinforcement Learning

It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eyegaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

[1]  Wolfram Burgard,et al.  Monte Carlo localization for mobile robots , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[2]  Anind K. Dey,et al.  Maximum Entropy Inverse Reinforcement Learning , 2008, AAAI.

[3]  Jianwei Gong,et al.  An Efficient Model for Driving Focus of Attention Prediction using Deep Learning , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[4]  Mohan M. Trivedi,et al.  Gaze fixations and dynamics for behavior modeling and prediction of on-road driving maneuvers , 2017, 2017 IEEE Intelligent Vehicles Symposium (IV).

[5]  Bernhard Schölkopf,et al.  Learning strategies in table tennis using inverse reinforcement learning , 2014, Biological Cybernetics.

[6]  Hirokatsu Kataoka,et al.  Predicting driving behavior using inverse reinforcement learning with multiple reward functions towards environmental diversity , 2015, 2015 IEEE Intelligent Vehicles Symposium (IV).

[7]  Hiroshi Murase,et al.  Mobile Robot Localization Considering Class of Sensor Observations , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Dushyant Rao,et al.  Large-scale cost function learning for path planning using deep inverse reinforcement learning , 2017, Int. J. Robotics Res..

[9]  David Whitney,et al.  Predicting Driver Attention in Critical Situations , 2017, ACCV.

[10]  Masamichi Shimosaka,et al.  Modeling risk anticipation and defensive driving on residential roads with inverse reinforcement learning , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[11]  Jean Underwood,et al.  Visual attention while driving: sequences of eye fixations made by experienced and novice drivers , 2003, Ergonomics.

[12]  Riender Happee,et al.  Changes of driving performance and gaze behavior of novice drivers during a 30-min simulator-based training , 2015 .

[13]  Wolfram Burgard,et al.  Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters , 2007, IEEE Transactions on Robotics.

[14]  Hironobu Fujiyoshi,et al.  Attention Branch Network: Learning of Attention Mechanism for Visual Explanation , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[15]  Hiroshi Murase,et al.  An Analysis of How Driver Experience Affects Eye-Gaze Behavior for Robotic Wheelchair Operation , 2019, 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW).

[16]  Hiroshi Murase,et al.  Safety Criteria Analysis for Negotiating Blind Corners in Personal Mobility Vehicles Based on Driver’s Attention Simulation on 3D Map , 2019, 2019 IEEE Intelligent Transportation Systems Conference (ITSC).

[17]  Hironobu Fujiyoshi,et al.  Visual Explanation by Attention Branch Network for End-to-end Learning-based Self-driving , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).

[18]  Martial Hebert,et al.  Activity Forecasting , 2012, ECCV.

[19]  Alexander Pollatsek,et al.  Using Eye Movements To Evaluate Effects of Driver Age on Risk Perception in a Driving Simulator , 2005, Hum. Factors.

[20]  Andrea Palazzi,et al.  Predicting the Driver's Focus of Attention: The DR(eye)VE Project , 2017, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[21]  Hironobu Fujiyoshi,et al.  Can AI predict animal movements? Filling gaps in animal trajectories using inverse reinforcement learning , 2018, Ecosphere.

[22]  E. Hartman,et al.  Driver vision requirements , 1970 .

[23]  José Eugenio Naranjo,et al.  Study of a driver assistance interface for merging situations on highways , 2018, 2018 IEEE International Conference on Vehicular Electronics and Safety (ICVES).

[24]  Manfred K. Warmuth,et al.  Exponentiated Gradient Versus Gradient Descent for Linear Predictors , 1997, Inf. Comput..

[25]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[26]  Hiroshi Murase,et al.  Driving Behavior Modeling Based on Hidden Markov Models with Driver's Eye-Gaze Measurement and Ego-Vehicle Localization , 2019, 2019 IEEE Intelligent Vehicles Symposium (IV).