Heterogeneous multi-sensor tracking for an autonomous surface vehicle in a littoral environment.

Sensor fusion plays a key part in autonomous surface vehicles, however, the high cost of sensors makes the barrier of entry in this research field quite high. In this work, we present a complete system for sensor fusion on the milliAmpere autonomous ferry research platform as well as an open sensor fusion dataset for maritime tracking across two environments. Individual sensors and their detection pipelines are evaluated across various detection metrics. We also evaluate the tracking performance of the sensors both individually and in fusion using a multi-sensor extension of the JIPDA multi-target tracker. We find that the different environments have distinct challenges precluding the use of only a single sensor. Utilizing multiple sensors, either individually or in fusion, can mitigate these issues increasing the safety margins of the situational awareness system. • Experimental validation of a multi-sensor extension of the JIPDA multi-target tracker. • In-depth description of a complete sensor fusion pipeline from sensor data to detection and tracking. • Open sensor fusion dataset for maritime multi-target tracking with multiple environments and scenarios. • Multiple sensors improve safety margins across differing environments. [ABSTRACT FROM AUTHOR]