Song Ma

Biography

Song Ma is an MSc student in the Department of Mechanical Engineering at UCL. He received his Bachelor of Engineering degree in mechanical design, manufacturing & their automation in 2018 from Dalian University of Technology, China. His research interest is in the area of the autonomous system and its interfaces with machine learning.

Introduction to research

Task management, as a high-level decision making strategy, is able to intelligently assign a number of different tasks to an autonomous system by adhering to certain constraints. By successfully developing a task management algorithm and integrating the algorithm into an autonomous system, the autonomous level of the system can be greatly improved. In recent decades, unmanned surface vehicles (USVs) are attracting increasing attention due to its underlying capability in autonomously undertaking complex maritime tasks in constrained environments. However, the autonomy level of USVs is still limited, especially when being deployed to conduct multiple tasks simultaneously. This work, therefore, aims to improve USVs’ autonomy level by investigating and developing an effective and efficient task management system for multi-USV systems. By dividing task management into two sub-missions, i.e. task assignment and task planning, the unsupervised learning strategy has been adopted in this work, and an improved K-means algorithm is proposed to first assign different tasks for a multi-USV system. Then, the self-organising map (SOM) is implemented to deal with the task planning problem based upon the assigned tasks for each USV.  Differing to other work, the communication problem that is crucial for USVs in a constrained environment has been specifically resolved by developing a new competition strategy for K-means algorithm. Key factors that will influence the communication capability in practical applications have been taken into account. A holistic task management architecture has been designed by integrating both the task assignment and task planning algorithms, and vast simulations in both simulated and practical maritime environments have been carried out to validate the effectiveness of the proposed algorithms.

Why did you choose maritime as your area of study and research?

I have had a keen interest in the area of autonomous system for a while, and the current researches about the unmanned surface vehicle and autonomous underwater vehicle do attract me because of their excellent development potential and practical value.

What do you hope to get out of participating in the Maritime Masters programme?

I want to broaden my outlook of the maritime field from both the academic community and the industry. I also hope that I can communicate with other people sharing and discussing our ideas together.