An integrated solution based irregular driving detection

• Main Author: Sun, Rui, (Author)
• Format: eBook
• Language: English
• Published: Cham, Switzerland : Springer, [2016]
• Series: Springer theses,
• Subjects: Intelligent transportation systems.; Motor vehicle driving.; Global Positioning System.; elektronické knihy; electronic books
• ISBN: 9783319449265; 9783319449258
• Physical Description: 1 online resource (xxviii, 127 pages) : illustrations (some color)
• ISSN: 2190-5053
• Access: Plný text je dostupný pouze z IP adres počítačů Univerzity Tomáše Bati ve Zlíně nebo vzdáleným přístupem pro zaměstnance a studenty

Global Navigation Satellite Systems (GNSS) are widely used in the provision ofIntelligent Transport System (ITS) services. Today, metre-level positioning accu-racy, which is required for many applications including route guidance, fleetmanagement and traffic control, can be fulfilled by GNSS-based systems. Becauseof this level of success and potential, there is an increasing demand for GNSS tosupport applications with more stringent positioning requirements. These includesafety-related applications that require centimetre/decimetre-level positioningaccuracy, with high integrity, continuity and availability such as lane control,collision avoidance and intelligent speed assistance. Detecting lane-level irregulardriving behaviour is the basic requirement for lane-level ITS applications. Currently, some research has addressed road-level irregular driving detection;however, very little research has been done in lane-level irregular driving detection.The two major issues involved in the lane-level irregular driving identification areaccess to high accuracy positioning and vehicle dynamic parameters, and extractionof erratic driving behaviour from this and the lane-related information. This thesis proposes an integrated solution for the detection of lane-levelirregular driving behaviour. Access to high accuracy positioning is enabled by GPSand its integration with an Inertial Navigation System (INS) using extended Kalmanfiltering (EKF) and particle filtering (PF) with precise vehicle motion models andlane centre line information. Four motion models are used in this thesis: constantvelocity (CV), constant acceleration (CA), constant turn rate and velocity (CTRV)and constant turn rate and acceleration (CTRA). The CV and CA models are usedon straight lanes and the CTRV and CTRA models on curved lanes. Lane centreline information is extracted from defined lane coordinates in the simulation and issurveyed and stored as sets of positioning points from the motorway in thefield test.The high accuracy vehicle positioning and dynamic parameters include yaw rate(omega) and lateral displacement (d) in addition to conventional navigationparameters such as position, velocity and acceleration. The detection of irregular driving behaviour is achieved by comparing thesorting rules of a driving classification indicator from the filter estimations withwhat is extracted from the reference. The detected irregular driving styles are characterized by weaving, swerving, jerky driving and normal driving on straightand curved lanes, based on the Fuzzy Inference System (FIS). The solution proposed in the thesis has been tested by simulation and validatedby real field data. The simulation results show that different types of lane-levelirregular driving behaviour can be correctly identified by the algorithms developedin this thesis. This is confirmed by the application of data from a field test duringwhich the dynamics of an instrumented vehicle supplied by Imperial CollegeLondon were captured in real time. The results show that the precise positioningalgorithms developed can improve the accuracy of GPS positioning and that theFIS-based irregular driving detection algorithms can detect the different types ofirregular driving. The evaluation of the designed integrated systems in the field testshows that a positioning accuracy of 0.5 m (95 %) source is required for lane-levelirregular driving detection, with a correct detection rate of 95 % and availability of94 % based on a 1 s output rate. This is useful for many safety-related applications including lane departure warnings and collision avoidance.