Abstract
Autonomous surface vehicles and maritime autonomous surface ships must rely on sense-and-avoid systems for navigating safely among other ships. The main objective of this paper is to present examples of such systems, and their verification in full-scale collision avoidance experiments as part of the research project “Sensor fusion and collision avoidance for autonomous surface vehicles” (Autosea). Lessons learned from the progression of experiments have led to increasing robustness of the methods, and provide a foundation for several important topics of further research in the near future.
Highlights
Autonomous ship technology has emerged as a nascent research area in recent years
The main objective of this paper is to present examples of such systems, and their verification in full-scale collision avoidance experiments as part of the research project “Sensor fusion and collision avoidance for autonomous surface vehicles” (Autosea)
The purpose of the present paper is to provide the reader with a bird-eye overview of these developments and experiments, which is not available from the previous publications of the project
Summary
Autonomous ship technology has emerged as a nascent research area in recent years. Building upon successful demonstrations and commercial products in exhibiting high degrees of autonomy in aerial, underwater and automotive systems, it is hoped that increased autonomy in shipping can lead to cost reductions and improved safety. A key prerequisite for this is a trustworthy collision avoidance (COLAV) system. The systems must use onboard sensors to perceive obstacles in the surroundings. The motion of other obstacles (ships) is in general non-zero and unknown, and must be estimated. Tracking methods must perform data association in order to link detections from subsequent images, so that tracks can be established and their kinematic attributes can be estimated. Most established tracking methods are variations of multiple hypothesis tracking (MHT) or joint probabilistic data association (JPDA) [1]. In MHT, the method attempts to enumerate all association hypotheses with significant probability involving several scans, or to search more directly for the best hypothesis. In JPDA, the method merges all the association hypotheses into a single hypothesis after every scan is received
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
