Towards an Autonomous Sailing Trainer

Speaker:
Ella Bolshinsky, M.Sc. Thesis Seminar
Date:
Wednesday, 25.2.2015, 12:30
Place:
Taub 601
Advisor:
Prof. R. Friedman

This work aims to design and implement a software/hardware bundle that could serve as a technical sailing trainer for the sailors of the Laser dinghy sailboat (or single-handed, main sail boats). This trainer should allow sailors, especially in the youth level, to practice in a genuine environment even when a human trainer is not available. Trying to keep the trainer simple and affordable, the bundle is composed of a smartphone and a small set of Wi-Fi enabled cameras placed in designated places on a Laser dinghy sailboat. Computationally expensive tasks might be processed on a remote server. The bundle analyzes the current condition of the boat by processing the pictures taken by the cameras and the smartphone sensors' reading and based on this analysis acts as a human trainer by supplying remarks. The recommendations were generated by a combination of a hueristic based expert system with machine learning based mechanism. Some of the main challenges that the image processing aspects had to deal with included extreme changes in lighting and weather conditions, shifts in cameras locations due to winds and waves, tracking multiple moving objects, and finishing to handle each set of images in real-time before the next set of images and sensor readings arrives. A prototype of the bundle was created, in which major parts of it were implemented and their performance and limitations were studied. In this process, we have accumulated some interesting insights about building real-life autonomous systems.

Back to the index of events