Enhanced Target Ship Tracking With Geometric Parameter Estimation for Unmanned Surface Vehicles

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 77
  • Download : 0
Autonomous collision detection and avoidance is a crucial requirement for the safe navigation of unmanned surface vehicles (USVs) in maritime traffic situations. Automatic identification system (AIS) is used to obtain the motion information of surrounding ships and their dimensional specifications. With AIS information, appropriate collision risk assessment between two ships can be performed; further, collision avoidance can be achieved by defining a safe radius of avoidance, which can be determined considering the shape parameters of a target ship. However, AIS data are often unreliable and some commercial fishing vessels intentionally turn off the public tracking system to hide their location. Under these circumstances, marine radars are used to detect and estimate the motion information of nearby ships. However, most existing target tracking studies model the target as a point object without any spatial extent, and thus, its physical dimensions cannot be identified. In this paper, a target tracking method that uses a marine radar is proposed to simultaneously estimate the motion states (i.e., position, course, and speed) of a target ship and its geometric parameter (length) in the framework of an extended Kalman filter (EKF). The proposed approach enhances collision avoidance by providing the kinematic and length parameters to evaluate collision risk and generate an appropriate collision-free path. Real-sea experiments using a developed USV system were conducted to verify and demonstrate the feasibility of the proposed algorithm; the results are presented and discussed in this paper.
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Issue Date
2021-03
Language
English
Article Type
Article
Citation

IEEE ACCESS, v.9, pp.39864 - 39872

ISSN
2169-3536
DOI
10.1109/ACCESS.2021.3063836
URI
http://hdl.handle.net/10203/282195
Appears in Collection
ME-Journal Papers(저널논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0