Extraction of descriptive driving patterns from driving data using unsupervised algorithms

Abstract Understanding drivers’ behavioral characteristics is critical for the design of decision-making modules in autonomous vehicles (AVs) and advanced driver assistance systems (ADASs). Current relevant studies are mainly based on supervised learning methods which involve extensive human efforts in model development. This paper proposed a framework for automatic descriptive driving pattern extraction from driving sequence data using unsupervised algorithms. Based on the Bayesian multivariate linear regression model, two unsupervised algorithms were utilized to segment driving sequences into fragments. Three extended latent Dirichlet allocation models were applied to cluster the fragments into multiple descriptive driving patterns. The collected driving data from a naturalistic driving experiment was applied to examine the effectiveness of our proposed framework. Results show that the unsupervised segmentation algorithms could help effectively detect the switch characteristics between two continuous driving maneuvers along time, and the clustered patterns could effectively describe the characteristics of each driving maneuver. The proposed unsupervised framework provides an effective and efficient data mining solution to facilitating deep and comprehensive understanding on drivers’ behavioral characteristics, which will benefit the development of AVs and ADASs.

[1]  Hui Zhang,et al.  State Estimation of Discrete-Time Takagi–Sugeno Fuzzy Systems in a Network Environment , 2015, IEEE Transactions on Cybernetics.

[2]  Myoungho Sunwoo,et al.  Robust Lane-Change Recognition Based on An Adaptive Hidden Markov Model Using Measurement Uncertainty , 2019, International Journal of Automotive Technology.

[3]  Xingda Qu,et al.  Influence of traffic congestion on driver behavior in post-congestion driving. , 2020, Accident; analysis and prevention.

[4]  Guofa Li,et al.  Deep Learning Approaches on Pedestrian Detection in Hazy Weather , 2020, IEEE Transactions on Industrial Electronics.

[5]  Junqiang Xi,et al.  Learning and Inferring a Driver's Braking Action in Car-Following Scenarios , 2018, IEEE Transactions on Vehicular Technology.

[6]  Xin Pei,et al.  Dangerous Driving Behavior Recognition and Prevention Using an Autoregressive Time-Series Model , 2017 .

[7]  Paul Fearnhead,et al.  Exact and efficient Bayesian inference for multiple changepoint problems , 2006, Stat. Comput..

[8]  Wenshuo Wang,et al.  Cluster Naturalistic Driving Encounters Using Deep Unsupervised Learning , 2018, 2018 IEEE Intelligent Vehicles Symposium (IV).

[9]  Kenneth L Campbell.  The SHRP 2 Naturalistic Driving Study: Addressing Driver Performance and Behavior in Traffic Safety , 2012 .

[10]  Dongpu Cao,et al.  Modeling and validation of off-road vehicle ride dynamics , 2012 .

[11]  Gregor Heinrich.  Parameter estimation for text analysis , 2009 .

[12]  Stewart Worrall,et al.  An Unsupervised Approach for Inferring Driver Behavior From Naturalistic Driving Data , 2015, IEEE Transactions on Intelligent Transportation Systems.

[13]  John A. Michon,et al.  A critical view of driver behavior models: What do we know , 1985 .

[14]  Muhammad Qasim Khan,et al.  A Comprehensive Survey of Driving Monitoring and Assistance Systems , 2019, Sensors.

[15]  K Ch Chatzisavvas,et al.  Information entropy, information distances, and complexity in atoms. , 2005, The Journal of chemical physics.

[16]  Fridulv Sagberg,et al.  A Review of Research on Driving Styles and Road Safety , 2015, Hum. Factors.

[17]  Stewart Worrall,et al.  Bayesian model-based sequence segmentation for inferring primitives in driving-behavioral data , 2014, 17th International Conference on Information Fusion (FUSION).

[18]  Saeid Nahavandi,et al.  Driver Behaviour Prediction for Motion Simulators Using Changepoint Segmentation , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[19]  Praveen Edara,et al.  Modeling Mandatory Lane Changing Using Bayes Classifier and Decision Trees , 2014, IEEE Transactions on Intelligent Transportation Systems.

[20]  Kevin P. Murphy,et al.  Modeling changing dependency structure in multivariate time series , 2007, ICML '07.

[21]  Meixin Zhu,et al.  Impact on car following behavior of a forward collision warning system with headway monitoring , 2020 .

[22]  Sabine Schulte im Walde,et al.  A Multimodal LDA Model integrating Textual, Cognitive and Visual Modalities , 2013, EMNLP.

[23]  Dongpu Cao,et al.  Risk assessment based collision avoidance decision-making for autonomous vehicles in multi-scenarios , 2021 .

[24]  Chong Wang,et al.  Simultaneous image classification and annotation , 2009, CVPR.

[25]  Rong Chen,et al.  Population distributions of time to collision at brake application during car following from naturalistic driving data. , 2015, Journal of safety research.

[26]  Jun Gao,et al.  Personalized detection of lane changing behavior using multisensor data fusion , 2019, Computing.

[27]  Tadahiro Taniguchi,et al.  Unsupervised drive topic finding from driving behavioral data , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[28]  Xingda Qu,et al.  Drivers' visual scanning behavior at signalized and unsignalized intersections: A naturalistic driving study in China. , 2019, Journal of safety research.

[29]  Mathias Perrollaz,et al.  Learning-based approach for online lane change intention prediction , 2013, 2013 IEEE Intelligent Vehicles Symposium (IV).

[30]  Dong In Kim,et al.  Optimal Energy Management Policy of Mobile Energy Gateway , 2016, IEEE Transactions on Vehicular Technology.

[31]  Bo Cheng,et al.  Estimation of driving style in naturalistic highway traffic using maneuver transition probabilities , 2017 .

[32]  Paul Fearnhead,et al.  Exact Bayesian curve fitting and signal segmentation , 2005, IEEE Transactions on Signal Processing.

[33]  Li Li,et al.  Preferred time-headway of highway drivers , 2001, ITSC 2001. 2001 IEEE Intelligent Transportation Systems. Proceedings (Cat. No.01TH8585).

[34]  Bin Ran,et al.  A Novel Car-Following Control Model Combining Machine Learning and Kinematics Models for Automated Vehicles , 2019, IEEE Transactions on Intelligent Transportation Systems.

[35]  Stewart Worrall,et al.  Automated extraction of driver behaviour primitives using Bayesian agglomerative sequence segmentation , 2014, 17th International IEEE Conference on Intelligent Transportation Systems (ITSC).

[36]  Manish Pal,et al.  Preferred time headway of drivers on two-lane highways with heterogeneous traffic , 2019 .

[37]  Dario D. Salvucci.  Modeling Driver Behavior in a Cognitive Architecture , 2006, Hum. Factors.

[38]  Imad L. Al-Qadi,et al.  Feasibility of Using Friction Indicators to Improve Winter Maintenance Operations and Mobility Prepared for: National Cooperative Highway Research Program Transportation Research Board of the National Academies , 2002 .

[39]  Bo Cheng,et al.  Detection of road traffic participants using cost-effective arrayed ultrasonic sensors in low-speed traffic situations , 2019, Mechanical Systems and Signal Processing.

[40]  Zheng Chen,et al.  A Novel Lane Change Decision-Making Model of Autonomous Vehicle Based on Support Vector Machine , 2019, IEEE Access.

[41]  Jianguo Wu,et al.  A new fuzzy c-means clustering-based time series segmentation approach and its application on tunnel boring machine analysis , 2019, Mechanical Systems and Signal Processing.

[42]  S. Fairclough,et al.  The effect of time headway feedback on following behaviour. , 1997, Accident; analysis and prevention.

[43]  Liu Zheng,et al.  MMDF-LDA: An improved Multi-Modal Latent Dirichlet Allocation model for social image annotation , 2018, Expert Syst. Appl..

[44]  Geoffrey Hinton.  The Next Generation of Neural Networks , 2020, SIGIR.

[45]  Tomoaki Nakamura,et al.  Grounding of word meanings in multimodal concepts using LDA , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[46]  Neville A. Stanton,et al.  Recognizing driving styles based on topic models , 2019, Transportation Research Part D: Transport and Environment.

[47]  Klaus-Dieter Kuhnert,et al.  A lane change detection approach using feature ranking with maximized predictive power , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.

[48]  Dongpu Cao,et al.  Development of a new integrated local trajectory planning and tracking control framework for autonomous ground vehicles , 2017 .

[49]  Chang Liu,et al.  Kalman filter-based tracking of moving objects using linear ultrasonic sensor array for road vehicles , 2018 .

[50]  Edwin Olson,et al.  Multipolicy decision-making for autonomous driving via changepoint-based behavior prediction: Theory and experiment , 2017, Auton. Robots.

[51]  Michael I. Jordan,et al.  Latent Dirichlet Allocation , 2001, J. Mach. Learn. Res..

[52]  Klaus-Robert Müller,et al.  The LDA beamformer: Optimal estimation of ERP source time series using linear discriminant analysis , 2016, NeuroImage.

[53]  Dongpu Cao,et al.  A deep learning based image enhancement approach for autonomous driving at night , 2020, Knowl. Based Syst..

[54]  Heiko Wersing,et al.  Personalization in advanced driver assistance systems and autonomous vehicles: A review , 2017, 2017 IEEE 20th International Conference on Intelligent Transportation Systems (ITSC).

[55]  Guofa Li,et al.  Effectiveness of Flashing Brake and Hazard Systems in Avoiding Rear-End Crashes , 2014 .