dc.description.abstract | Salmon is today a big part of the food commodities traded from aquaculture industry. However, there are several challenges with the industry today, and increasing yield and cutting costs throughout the supply chain is essential. Salmon roe is stored in trays and has a mortality rate which corresponds to millions of dead roe yearly. When roe dies, it will rot which in turn pollutes the surroundings and harms the remaining roe. Therefore, it is vital to remove the dead roe to minimize wastage. Today, they are removed by hand, which is a costly process that introduces a lot of stress to the fry and roe.
The aim of this thesis is to develop a robot as a proof of concept, for the optimization of early stage fish farming. In order to perform this task, the robot will require a high level of precision and accuracy. Furthermore, the technique aims to reduce the amount of stress the roe is exposed to as this can lead to abnormal growth.
The results left us confident that we have proved the concept, as well as creating a substantial foundation for a full-scale operation in an industrialized context. This project shows that locating and removing dead roe is possible by the use of robots and automated systems, and that the solutions and technology presented in this thesis can be used to reduce the cost in salmon production. | nb_NO |