An integrated solution for lane level irregular driving detection on highways

Abstract

Global Navigation Satellite Systems (GNSS) has been widely used in the provision of Intelligent Transportation System (ITS) services. Current meter level system availability can fulfill the road level applications, such as route guide, fleet management and traffic control. However, meter level of system performance is not sufficient for the advanced safety applications. These lane level safety applications requires centimeter/decimeter positioning accuracy, with high integrity, continuity and availability include lane control, collision avoidance and intelligent speed assistance, etc. Detecting lane level irregular driv-ing behavior is the basic requirement for these safety related ITS applications. The two major issues involved in the lane level irregular driving identification are accessing to high accuracy positioning and vehicle dynamic parameters and extraction of erratic driving behaviour from this and other related information. This paper proposes an integrated solu-tion for the lane level irregular driving detection. Access to high accuracy positioning is enabled by GNSS and Inertial Navigation System (INS) integration using filtering with precise vehicle motion models and lane information. The detection of different types of irregular driving behaviour is based on the application of a Fuzzy Inference System (FIS). The evaluation of the designed integrated systems in the field test shows that 0.5 m accu-racy positioning source is required for lane level irregular driving detection algorithm and the designed system can detect irregular driving styles.

Integrated solution for anomalous driving detection based on BeiDou/GPS/IMU measurements

“…The new anomalous driving detection algorithm is extensively tested and compared with other state-of-the-art algorithms, including those from Sun et al (2015), Chang et al (2008), Dai et al (2010), and Krajewski et al (2009). Our experiments based on both simulated and field data show that the proposed FIS algorithm outperforms, by a discernible margin, all other methods in terms of timeliness of detection, availability, and correction rate.…”

“…In order to address these issues, Sun et al (2015) propose an integrated solution for lane-level anomalous driving detection, which takes advantage of high accuracy estimation of vehicle positions and dynamic parameters, and combines them with different types of anomalous driving identification method. That paper has identified a critical threshold (0.5 m) in terms of the positioning accuracy, where only positioning errors below this value ensure the validity and effectiveness of the lane-level anomalous driving detection.…”

“…Unfortunately, due to the insufficient accuracy of GPS positioning, it is impossible to achieve an accuracy of 0.5m for all instances, and the capability of any positioning mehtods to reach such accuracy is of critical importance to the successful detection of anomalous driving. In this paper, we have made considerable improvement over the method by Sun et al (2015) in terms of accuracy, reliability, and practicality. This is done through both technological innovation and algorithm advancement.…”

“…Furthermore, using the newly introduced BeiDou source, we further devise data fusion algorithms based on Unscented Kalman Filter (UKF) or Unscented Particle Filter (UPF), which provides substantial improvements over Extended Kalman Filter (EKF) and Particle Filter (PF) considered in Sun et al (2015); see Table 1 for more detailed comparison.…”

“…Due to the improvements made at individual stages of the framework as we briefly described above, the overall performance of the framework yields a significant improvement over our previous work (Sun et al, 2015). BeiDou data source, UKP/UPF data fusion models, and FIS-based anomalous driving detection, is analysed in detail using real-world data.…”