Title: An Integrated Algorithm Based on BeiDou/GPS/IMU and its Application for Anomalous Driving Detection
Author(s): Rui Sun, Ke Han, Jun Hu, Hongyang Bai, Washington Y. Ochieng
Published in: Proceedings of the 29th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2016)
September 12 - 16, 2016
Oregon Convention Center
Portland, Oregon
Pages: 1885 - 1890
Cite this article: Sun, Rui, Han, Ke, Hu, Jun, Bai, Hongyang, Ochieng, Washington Y., "An Integrated Algorithm Based on BeiDou/GPS/IMU and its Application for Anomalous Driving Detection," Proceedings of the 29th International Technical Meeting of The Satellite Division of the Institute of Navigation (ION GNSS+ 2016), Portland, Oregon, September 2016, pp. 1885-1890.
Full Paper: ION Members/Non-Members: 1 Download Credit
Sign In
Abstract: Recent years have seen a booming of safety-related Intelligent Transportation System (ITS) applications, which have placed increasingly stringent requirements on the performance of Global Navigation Satellite Systems (GNSS). Examples include lane control, collision avoidance, and intelligent speed assistance. Detecting the lane level anomalous driving behavior is crucial for these safety critical ITS applications. The two major issues associated with the lane-level irregular driving identification are (1) accessibility to high accuracy positioning and vehicle dynamic parameters, and (2) extraction of anomalous driving behavior from these parameters. This paper introduces an integrated algorithm for detecting lane-level anomalous driving. Lane-level high accuracy vehicle positioning is achieved by fusing GPS and Beidou feeds with Inertial Measurement Unit (IMU) using Unscented Particle Filter (UPF). Anomalous driving detection is achieved based on the application of a newly designed Fuzzy Inference System. Computer simulation and real-world field test demonstrate the advantage of the proposed approach over existing ones from previous studies.