Addressing the need to reduce human error in ship navigation, which resulted in up to nearly 40% of all marine accidents in 2017, the researchers say they are developing an automated system that instead relies on both data analytics and AI.
"One main intention for autonomous ships is really for the safety purpose," says Professor Yan Jin, member of the Department of Aerospace and Mechanical Engineering and project lead. "We're all human and sometimes we make mistakes due to different situations. But if we have an autonomous kind of decision-making computer program, it would constantly make suggestions to humans."
Knowing the locations of other ships and objects, the system, say the researchers, can predict those ship's movements and determine their best possible course of action that minimizes the chance of collision. The AI portion of the system uses reinforcement learning - using simulations of different boating scenarios - to teach the computer how to achieve its goal of not hitting another object.
"At first the computer agent doesn't know anything," says mechanical engineering PhD student Xiongqing "Vincent" Liu, who was responsible for developing the AI portion of their system. "It has to explore the simulated environment by itself. If the agent collides with the obstacles, then it will receive a negative penalty. But if it reaches the goal, then it receives a very positive reward."
After running the simulation thousands of times, the agent learns from its past experiences what trajectory to take to avoid a collision - similar to how a human learns.
"From this process, we can demonstrate that, as the agent trains itself, it can generate some intelligence," says Liu. "And this kind of intelligence is what humans use to make decisions – it's kind of their intuition. And this kind of human intuition can be learned by a computer agent."
The AI system alone is not fully error-proof as it relies on the inputted scenarios -