There are few environments as unforgiving as the ocean. Its unpredictable weather patterns and communications limitations have left vast stretches of the ocean unexplored and shrouded in mystery.
“The ocean is a fascinating environment with a number of ongoing challenges such as microplastics, algal blooms, coral bleaching, and rising temperatures,” says Wim van Rees, professor of ABS career development at MIT. . “At the same time, the ocean holds countless opportunities – from aquaculture to energy harvesting and exploring the many ocean creatures we have yet to discover.”
Ocean engineers and mechanical engineers, like van Rees, use advances in scientific computing to address the ocean’s many challenges and seize its opportunities. These researchers are developing technologies to better understand our oceans and how human-made organisms and vehicles can move through them, from micro to macro scales.
Bio-inspired underwater devices
An intricate dance takes place as the fish swim through the water. The flexible fins flap in the water currents, leaving a trail of whirlpools in their wake.
“Fish have complex internal musculature to adapt the precise shape of their body and fins. This allows them to propel themselves in different ways, far beyond what any man-made vehicle can do in terms of maneuverability, agility or adaptability,” explains van Rees.
According to van Rees, thanks to advances in additive manufacturing, optimization techniques and machine learning, we are closer than ever to reproducing flexible, morphing fish fins for use in underwater robotics. As such, it is more necessary to understand how these soft fins impact propulsion.
Van Rees and his team develop and use numerical simulation approaches to explore the design space of underwater devices that have increased degrees of freedom, for example due to deformable fish-like fins.
These simulations help the team better understand the interplay between the fluid and structural mechanics of soft and flexible fish fins as they move through fluid flow. As a result, they are able to better understand how deformations in the shape of fins can impair or improve swimming performance. “By developing precise numerical techniques and scalable parallel implementations, we can use supercomputers to solve what exactly is happening at this interface between flow and structure,” adds van Rees.
By combining his simulation algorithms for flexible underwater structures with optimization and machine learning techniques, van Rees aims to develop an automated design tool for a new generation of autonomous underwater devices. This tool could help engineers and designers develop, for example, robotic fins and underwater vehicles that can intelligently adapt their shape to better achieve their immediate operational goals, whether it’s swimming faster and more efficiently or perform shunting operations.
“We can use this optimization and AI to reverse design across the entire parameter space and build smart, adaptable devices from scratch, or use precise individual simulations to identify the physical principles that drive why one shape works better than another,” says van Rees. .
Swarming algorithms for robotic vehicles
Like van Rees, lead researcher Michael Benjamin wants to improve the way vehicles maneuver through water. In 2006, while a post-doctoral fellow at MIT, Benjamin launched an open-source software project for an autonomous piloting technology that he was developing. The software, which has been used by companies such as Sea Machines, BAE/Riptide, Thales UK and Rolls Royce, as well as the US Navy, uses a new multi-objective optimization method. This optimization method, developed by Benjamin during his doctorate, allows a vehicle to autonomously choose the course, speed, depth and direction in which it must go to achieve several simultaneous objectives.
Today, Benjamin is taking this technology further by developing swarming and obstacle avoidance algorithms. These algorithms would allow dozens of unmanned vehicles to communicate with each other and explore a given part of the ocean.
To begin, Benjamin is researching how best to disperse autonomous vehicles in the ocean.
“Suppose you want to launch 50 vehicles into a section of the Sea of Japan. We want to know: Does it make sense to drop all 50 vehicles in one place, or have a mothership drop them off at certain points in a given area? explains Benjamin.
He and his team have developed algorithms that answer this question. Using swarming technology, each vehicle periodically communicates its position to other nearby vehicles. Benjamin’s software allows these vehicles to disperse in an optimal distribution for the part of the ocean in which they operate.
The ability to avoid collisions is central to the success of swarm vehicles. Collision avoidance is complicated by international maritime rules known as COLREGS – or “Collision Regulations”. These rules determine which vehicles have the “right of way” when they pass each other, posing a unique challenge for Benjamin’s swarming algorithms.
COLREGS are written with the perspective of avoiding another single contact, but Benjamin’s swarming algorithm had to account for multiple unmanned vehicles trying to avoid colliding with each other.
To solve this problem, Benjamin and his team created a multi-object optimization algorithm that ranked specific maneuvers on a scale of zero to 100. A zero would be a direct collision, while 100 would mean the vehicles completely avoided the collision. .
“Our software is the only marine software where multi-objective optimization is the basic mathematical basis for decision making,” says Benjamin.
While researchers like Benjamin and van Rees are using machine learning and multi-objective optimization to address the complexity of vehicles moving through ocean environments, others like Pierre Lermusiaux, Professor Nam Pyo Suh at MIT, are using machine learning to better understand the ocean environment itself.
Improving ocean modeling and forecasting
The oceans are perhaps the best example of what is called a complex dynamic system. Fluid dynamics, changing tides, weather patterns and climate change make the ocean an unpredictable environment that differs from moment to moment. The ever-changing nature of the ocean environment can make forecasting incredibly difficult.
Researchers have used dynamical systems models to make predictions about ocean environments, but as Lermusiaux explains, these models have their limitations.
“You can’t account for every water molecule in the ocean when building models. The resolution and accuracy of models, as well as ocean measurements are limited. There could be a model data point every 100 meters, every kilometer, or if you look at global ocean climate models, you could have a data point every 10 kilometers or so. This can have a big impact on the accuracy of your prediction,” says Lermusiaux.
Graduate student Abhinav Gupta and Lermusiaux have developed a new machine learning framework to help compensate for the lack of resolution or precision in these models. Their algorithm takes a simple low-resolution model and can fill in the gaps, emulating a more accurate and complex model with a high degree of resolution.
For the first time, Gupta and Lermusiaux’s framework learns and introduces time delays into existing approximate models to improve their predictive capabilities.
“Things in the natural world don’t happen instantly; however, all common models assume that things happen in real time,” says Gupta. “To make an approximate model more accurate, machine learning and the data you enter into the equation should represent the effects of past states on future prediction.”
The team’s “neural closure model”, which explains these delays, could potentially lead to better predictions for things like a loop current hitting an oil rig in the Gulf of Mexico, or the amount of phytoplankton in a given part of the ocean. .
As computational technologies such as Gupta and Lermusiaux’s neural closure model continue to improve and advance, researchers can begin to unravel more ocean mysteries and develop solutions to the many challenges facing our oceans. .