Abstract

In recent years, Self-driving technology received extensive attention of the society from all walks of life. The self-driving cars developed by major technology companies in the whole world have been able to drive on the road. At the same time, the concept of autonomous vessel has been proposed in the past few years. Without any prior information, the SLAM (Simultaneous Localization and Mapping) algorithm, comprises the simultaneous estimation of the state of a robot equipped with on-board sensors and the construction of a model (the map) of the environment that the sensors are perceiving, SLAM is becoming one of the most important components of the driverless sensing module. In this paper, the First part introduces the concept of the autonomous vessel, and then discusses its perception module in detail. After that, it summarizes relevant concepts about SLAM algorithms. The Second part, this paper makes a specific analysis of the current two kinds of monocular visual SLAM(V-SLAM) methods and collects the video data in the harbor environment to carry out experiments, then analyzes and records the relevant experimental results. In the third part, through the analysis and comparison of the experimental results, we discussed the possibility of V-SLAM method applied to autonomous vessel, as well as the problems that may arise in the actual process and attempt to propose some prospective solutions.

Full Text
Published version (Free)

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 call