Now at the Massachusetts Institute of Technology (MIT), professor Brian Williams and his team at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) are working with ExxonMobil scientists and engineers to create self-learning, submersible robots for ocean exploration. The robots’ software, their “intelligence,” will allow them to operate autonomously in conditions as harsh as any on Mars and to change their mission parameters on their own volition to explore strange anomalies.
“Our goal is to have these submersibles embody the reasoning of the scientists that program them,” said Williams. “You want the explorer to do the science without the scientist there. They need to be able to analyze data, keep themselves out of harm’s way and determine novel solutions in novel situations that go beyond basic mission programming. They need to have some common sense and the ability to learn from their mistakes.”
The immediate application of this technology would be to monitor the oceans, mapping deep regions while analyzing how they change over time and gauging their health. But for Williams and his team, the possibilities reach back out into the solar system.
“Europa is a moon of Jupiter with ice-covered oceans,” said Williams. “This technology could be used in a mission to explore for life under the ice. That’s a really exciting idea where this explorer technology, which will be able to operate autonomously in harsh environments, could be a part of discoveries that change the way we look at the universe.”
It’s the far-reaching possibilities that drew Williams’ team to the program. Postdoctoral fellow Tiago Vaquero and graduate research assistant Ben Ayton are intrigued by where the technology can go from here.
“In addition to ExxonMobil, we are working with Woods Hole Oceanographic Institution, one of the organizations that, among other things, discovered the wreck of the Titanic and helped search for the lost Air France plane in the Atlantic Ocean,” said Ayton. “Woods Hole is interested in developing submersible miniaturized chemical sensors to analyze the oceans, a perfect application for our technology. But it could be used anywhere that’s hard to reach that we know little about.”
For Vaquero, the benefit is the amount of science that can be done with the deployment of these robots. “The trend is to use smaller, less-expensive vehicles like ours, that you can deploy more of and use fewer people to monitor,” he said. “That means we collect more data and do more science, exponentially increasing our understanding of the oceans or space.”
A spectrum of research
It’s likely that artificially intelligent robotics is not where you would expect ExxonMobil to invest time and capital. But ExxonMobil, a pioneer in the science of natural seep detection and characterization, is part of the team now seeking to take this technology to the next level.
Slow moving and quiet, these robots navigate many feet above the ocean floor. Thus, they can help safeguard the ecosystems, as well as detect and analyze naturally seeping hydrocarbons, which could be an indicator for where best to find energy resources.
The use of sensors and data collection, not unlike cell phones and related technology, can come together in surprising ways to help deliver energy more efficiently and effectively – and under the most challenging conditions.
Part of the company’s ongoing collaboration with MIT through the MIT Energy Initiative is to explore adjacent technologies that are outside the realm of ExxonMobil’s core energy business today, but can inform its business in the future. Call it curiosity.
“We work with MIT on a spectrum of programs, intentionally opening the aperture of our lens to look at things we normally wouldn’t look at,” said Hans Thomann, ExxonMobil senior scientific advisor and a visiting scholar at MIT. “We focus on fundamental science, working with experts across diverse fields at the university to gain deep knowledge and advance those fields.”
The collaboration with MIT is two-way, with ExxonMobil funding research on a wide range of projects as well as providing access to technical personnel like Thomann, who spends 50 percent of his time on campus. And the MIT Energy Initiative establishes 10 ExxonMobil Energy Fellows per year – graduate students and postdocs like Ayton and Vaquero who can pursue research while working with industry counterparts to alert them to real-world problems and opportunities for progress.
“Students are curious about how their research will have an impact in the world,” said Lori Summa, ExxonMobil’s former primary investigator on the MIT submersible robot project. “And we’re curious about new innovations that can push the envelope of energy research to meet the challenges of the future.”
Above header image caption: Learnings from the Mars Curiosity Rover, like the robot pictured here, helped researchers develop self-learning, submersible robots for ocean exploration.