Dan Falk

It wasn’t that long ago that astronomers only knew of eight planets (nine before Pluto’s demotion back in 2006) – those here in our own solar system. Now we know of nearly 10,000 planets orbiting stars beyond our sun – known as exoplanets – and that flood of new worlds has ushered in something of a golden age for planetary scientists.

For astronomers like Marta Bryan, an assistant professor at the University of Toronto Mississauga and in the David A. Dunlap department of astronomy and astrophysics in the Faculty of Arts & Science, it means there’s no better time to be studying these distant worlds.

“This is such a dynamic field,” says Bryan, who joined �鶹ֱ��app in January after four years as a postdoctoral researcher at the University of California, Berkeley. Studying the properties of exoplanets provides “a unique opportunity to put ourselves and our world in the broadest of contexts – how does our solar system, our planet and our species fit into our universe?”

Bryan, who specializes in the study of planetary formation and evolution, was recently awarded the Annie Jump Cannon Award from the American Astronomical Society for her work on exoplanets.

As the tally of exoplanets began to grow, astronomers noticed how diverse planetary systems appear to be, with planets varying widely in size, composition and surface temperature. Some orbit very close to their host stars, while others follow orbits comparable to the Earth’s, or to the giant outer planets in our solar system.

“We’ve found thousands of exoplanets, with a huge diversity of properties,” Bryan says. “For me, one of the driving goals in the field is to understand where that diversity comes from. What does the process of planet formation and evolution look like?”

Marta Bryan uses a range of observational techniques to detect and characterize gas giant planets outside our solar system to explore how planetary systems form and evolve (photo by Nick Iwanyshyn)

While much research on exoplanets has focused on the search for Earth-like worlds, Bryan is interested in gas giant planets, analogous to Jupiter and Saturn in our own solar system. That’s because their sheer heft means they play an important role in determining how smaller planets in the same system evolve.

As Bryan puts it, gas giant planets “dominate the dynamics” of whatever system they’re in. Which means that learning about gas giants can, in fact, help us understand something about Earth-like planets – worlds whose evolution may have been affected by the presence of these much more massive bodies.

As a result, Bryan says, “gas giant planets are an obvious place to start if we want to understand the physics of planet formation.”

The gas giant planets in our own solar system are thought to have played a crucial role over the past five billion years. Jupiter, for example, is believed to have migrated inward before reversing direction and ending up in its current position. Jupiter’s foray into the inner part of the solar system is thought to have stunted the growth of the inner planets, particularly Mars, by scattering some of the gas and dust that might otherwise have been gravitationally pulled toward the red planet.

“We think that Jupiter and Saturn played a dominant role in the early history of our solar system, helping to shape the formation and evolution of our terrestrial planets,” Bryan says. “As a result, we want to understand in the broader extrasolar context what role gas-giant analogs to Jupiter and Saturn have played in shaping the lives of terrestrial worlds.”

The future looks bright – data from the James Webb Space Telescope is already pouring in. Bryan is especially excited about large, ground-based telescopes with mirrors up to 30 metres across, which are currently being planned. These next-generation telescopes may even reveal “biosignatures” on other worlds – signs of life that can be inferred from the composition of a planet’s atmosphere.

And if astronomers do end up finding conclusive evidence of life beyond our own planet, such a discovery “would definitely be transformational,” Bryan says.

Robots in the wild: �鶹ֱ��app's Florian Shkurti on overcoming 'edge cases' in machine learning

Christopher.Sorensen — Fri, 15 Oct 2021 16:45:31 +0000

Robots in the wild: �鶹ֱ��app's Florian Shkurti on overcoming 'edge cases' in machine learning

Christopher.Sorensen Fri, 10/15/2021 - 12:45

Cutline

(Photo by Drew Lesiuczok)

Topic

Research & Innovation

Robotics

Robots

�鶹ֱ��app Mississauga

The technology behind self-driving cars has been racing ahead – and as long as they are cruising along familiar streets, seeing familiar sights, they do very well.

But the University of Toronto’s Florian Shkurti says that when driverless vehicles encounter something unexpected, all that progress can come screeching to a halt.

He offers the example of a self-driving car that is following a large truck on a winter road.

“There’s a wind gust – and now the snow is coming at you, so you can’t see anything,” says Shkurti, an assistant professor in the department of mathematical and computational sciences at �鶹ֱ��app Mississauga who runs the Robot Vision and Learning (RVL) lab. “And suppose your LIDAR (light detection and ranging system) misperceives the snow as an array of objects, so it thinks there are a million small objects coming at the car.”

Shkurti’s research extends far beyond self-driving cars to autonomous systems in general. How do they learn? How we can make them learn better? How they can successfully navigate complex environments at the service of humans? That includes making sure that robots can handle so-called “edge cases,” like the snowy truck example – cases where the robot “comes across a rare scenario, for which there’s little or no training data.

“Then you have to either collect more data, or you have to accept that there will be these rare events that your perception system won’t recognize,” Shkurti says.

Simulation is an important training tool. Self-driving cars, for example, can be trained on simulated roads and highways before they’re let loose on actual city streets. But scalability remains a challenge. If an autonomous system has to be specially trained for every possible scenario it might encounter, progress will be haltingly slow; there will be no way to take what’s been learned from one scenario and scale it up so that the system can handle more general cases.

In an ideal world, Shkurti says, a robot could learn similar to the way a human would.

Take, for example, robots that help scientists collect data underwater – an effort Shkurti has been involved with for several years. A human diver “has to collect data manually, one data point at a time, one location at a time,” Shkurti says. “It’s painstaking work; it’s not scalable.”

An autonomous robot, on the other hand, could take over the data collection process if it’s capable of maneuvering underwater and equipped with a camera and other sensors. “If the robot could understand what it’s doing – if it has a model of what the scientist thinks is important to pay attention to in a particular environment – then the robot could collect data on behalf of the scientist.”

Such an approach has many benefits, according to Shkurti: It’s much cheaper to deploy additional robots than to train more scientists; and it frees up the scientist to look after higher-level tasks. “The scientist can give the robot some hints as to where to collect the data – but then the robot can take care of the rest,” he says.

Shkurti, who did his undergraduate studies at �鶹ֱ��app before earning his PhD in computer science at McGill in computer science, was hired by �鶹ֱ��app in 2018. He recently received a Connaught New Researcher Award for a project titled “Robotics and Machine Learning in the Wild: New Directions in Automated Environmental Monitoring.”

Hey says that while everything about computer science fascinates him, the field of robotics holds special appeal.

“Robotics lets you play in different ‘playgrounds,’ like control, perception, and machine learning,” he says. “It allows you to examine these different fields, and I really valued that – and I still value it.”

As for the lofty philosophical questions that sometimes crop up when people talk about advanced computer systems – such as whether machines could learn to “think” – Shkurti prefers to stay focused on the science. Machines can reason, he says, and they can try to act optimally as they strive to achieve their goals.

“If that’s thinking, then they’re doing it,” he says. “But I don’t spend very much time worrying about ‘consciousness.’ I have enough other things to worry about.”