In The Spotlight

The road ahead: Raquel Urtasun's startup to ‘unleash full power of AI’ on self-driving cars

rahul.kalvapalle — Thu, 10 Jun 2021 19:31:01 +0000

The road ahead: Raquel Urtasun's startup to ‘unleash full power of AI’ on self-driving cars

rahul.kalvapalle Thu, 06/10/2021 - 15:31

Cutline

Raquel Urtasun, a U of T professor of computer science and world-leading expert in machine learning and computer vision, has launched her own Toronto-based, self-driving vehicle company with more than $100 million in funding (photo by Natalia Dolan)

Rahul Kalvapalle

Topic

Our Community

In The Spotlight

Artificial Intelligence

Computer Science

Faculty of Arts & Science

Raquel Urtasun

Research & Innovation

Self-Driving Cars

Vector Institute

More than $100-million in funding. Two decades of artificial intelligence expertise. Ten years of experience in self-driving technology. A 40-strong team of scientists and engineers.

The list of resources at Raquel Urtasun’s fingertips as she takes the wheel of Waabi, an autonomous vehicle startup, is impressive to say the least. The goal? Use AI to finally resolve the technical and financial challenges that have hindered the full commercialization of self-driving technology.

It’s the first foray into entrepreneurship for Urtasun, a professor of computer science at the University of Toronto and one of the world’s leading experts in machine learning and computer vision. She says she was inspired to start her own company after four years as chief scientist and head of Uber ATG’s self-driving car lab in Toronto, where she realized need for a new generation of self-driving technologies that leverage AI’s full potential.

“The thought of what would be the best way to do this grew and grew in my head until it became clear that, if you really want to change technology, the best way to do it is to start a new company,” Urtasun says.

Urtasun’s new venture emerged from stealth mode earlier this week to announce one of the largest rounds of initial financing ever secured by a Canadian startup, raising more than $100 million from investors including Silicon Valley-based Khosla Ventures and Uber. Other investors include fellow U of T AI luminaries Geoffrey Hinton, a University Professor Emeritus, and Sanja Fidler, an associate professor of computer science, as well as Stanford University’s Fei-Fei Li and Pieter Abbeel of the University of California, Berkeley.

Urtasun says the self-driving industry’s current players aren’t taking full advantage of the power of AI.

“There is a little bit of AI there, but it doesn’t have a prominent role. Instead, it’s solving very specific sub-problems within the massive software stack – or brain of the self-driving car,” she says. “This causes difficulty in that it requires really complex, time-consuming manual tuning.

“As a consequence of this, scaling the technology is costly and technically very challenging.”

Waabi addresses this by utilizing “deep learning, probabilistic inference and complex optimization” to create a new class of algorithms, the likes of which Urtasun says have never been seen before in industry or academia.

Key to Waabi’s approach is its novel autonomous system – essentially, the software brain of the self-driving vehicle – that is “end-to-end trainable,” meaning the entire software stack can automatically learn from data, removing the need for constant manual tuning and tweaking.

The system is also “interpretable and explainable,” meaning it’s possible to deduce why it opts for certain manoeuvers over others – crucial for safety verification.

It’s also capable of complex reasoning, which Urtasun says is vital for eventual real-world applications.

“If you think about when you’re driving and arrive at an intersection, there’s a lot of things happening in your brain – you do very complex inference about what everybody’s doing at the intersection, how it will affect you, etc.” Urtasun says. “That’s what our new generation of algorithms provides – this ability to do really complex reasoning within the AI system.”

Waabi also has a revolutionary simulator system that can test the algorithms and software with “an unprecedented level of fidelity,” Urtasun says.

“When people in the industry say they test millions of miles of simulation, they’re really only testing the motion-planning component – which is one piece among this big software stack,” she says.

“Waabi has the ability to simulate how the world looks at scale, how sensors observe the scene and the behaviours of humans in a way that’s very realistic and in real time.”

That means significantly fewer hours of on-road drive testing.

“Typically, companies have hundreds of vehicles that they’re driving so that they can observe how the system works. And every time you change something, you change the behaviour, so you have to drive again and again and again,” Urtasun says. “[Waabi] can develop, test in simulation and reduce the need for driving in the real-world.”

It also means a system that’s safer because it can be trained to manage not only typical driving scenarios, but also ‘edge cases’ – situations that arise at extreme operating parameters.

“We can train the system to handle those edge cases in simulation,” Urtasun says. “So, you end up with a system that is much safer, that you can develop faster and that requires less capital to develop because you need very few people compared to the traditional approach – and less testing in the real world.

“[You] really unleash the power of AI.”

The company’s name reflects its approach. “Waabi” means “she has vision” in Ojibwe (“a new vision to help solve self-driving,” Urtasun says) and means “simple” in Japanese – an ode to the simplicity of the software stack.

“[It’s] a perfect definition of our technology and a perfect name for our company,” Urtasun says. “Plus, it sounds cool.”

The potential applications for Waabi’s technology are wide-ranging, Urtasun says, but the initial focus will be the long-haul trucking sector – a departure from her time at Uber, where she worked on passenger vehicles. She notes that truck-driving is recognized as one of the most dangerous occupations, and that the industry suffers from a shortage of drivers. “Automation can serve those industry needs,” she says.

Urtasun adds that long-haul trucking is also a prudent area to focus on because there’s less complexity involved with highway driving than is the case in cities.

“Highways are still very difficult – don’t get me wrong – but they’re less complex compared to a city like Toronto, with all the things that might happen and how people follow the rules – well, very few people follow the rules. So, you need to handle all that complexity.”

Toronto’s notoriously bad traffic aside, Urtasun says there’s nowhere else she’d rather set up an AI company.

“When people ask me, ‘Why here?’ I say, ‘Why not?’ I love Toronto, I love Canada. It’s an amazing place to do innovation – there’s incredible talent and support from the government,” she says, pointing to Toronto’s emergence as a world-leading AI hub thanks to initiatives such as the Vector Institute for Artificial Intelligence, which she co-founded.

“It’s been incredible to see the transformation that the city has gone through,” she says. “It was the case that people were leaving and going to California. Now, not only are we retaining talent but so much incredible talent is coming in – even from Silicon Valley,”

There’s also plenty of talent to be tapped at U of T, Urtasun adds.

“We have amazing U of T students who are doing great work within the company,” she says. “I really look forward to partnering closely with U of T to provide opportunities to the incredible talent that the university has. For me, it’s always been very important to [help develop] students – so that continues to be the case.”

As the CEO of an AI-powered autonomous vehicle startup, Urtasun says it’s important for her to set an example for women and girls interested in pursuing careers in technology.

“I think it’s very important that young girls, in particular, realize that this is not a man’s world. Technology is going to change the world and they definitely have a say,” she says.

She adds Waabi and other technology companies benefit immensely from diverse leadership and perspectives – and so do their customers.

“It’s important that in order to solve complex problems, we have diversity of opinions, approaches and backgrounds,” she says. “Waabi excels at all three types of diversity, which I think is the way to build incredible technology as well as showcase the diversity of the users who are going to use the technology at the end of the day.”

How a slender, snake-like robot could give doctors new ways to save lives

Christopher.Sorensen — Wed, 12 May 2021 17:28:09 +0000

How a slender, snake-like robot could give doctors new ways to save lives

Christopher.Sorensen Wed, 05/12/2021 - 13:28

Cutline

Jessica Burgner-Kahrs, director of the Continuum Robotics Lab at the U of T Mississauga, and her team are building very slender, flexible and extensible robots for use in surgery and industry (photo by Nick Iwanyshyn)

Andrew Snook

Topic

Our Community

In The Spotlight

Research & Innovation

Robotics

U of T Mississauga

You might call it “zoobotics.”

Jessica Burgner-Kahrs, the director of the Continuum Robotics Lab at the University of Toronto Mississauga, and her team are building very slender, flexible and extensible robots, a few millimetres in diameter, for use in surgery and industry.

Unlike humanoid robots, so-called continuum robots feature a long, limbless body – not unlike a snake’s – that allows them to access difficult-to-reach places.

Consider a neurosurgeon who needs to remove a brain tumour. Using a traditional, rigid surgical tool, the surgeon has to reach the cancerous mass by following a straight path into the brain, and risk poking through – and damaging – vital tissue.

The “tendon-driven” continuum robots depicted here are, in real life, about seven millimetres in diameter and are built in sections that can range in length from 15 to 70 millimetres. Other models can be even narrower. All exhibit a tentacle-like motion.

An associate professor of mathematical and computational sciences at U of T Mississauga, Burgner-Kahrs envisions a day when one of her snake-like robots, guided by a surgeon, would be able to take a winding path around the vital tissue but still reach the precise surgical site. Previously inoperable brain tumours might suddenly become operable.

“It could revolutionize surgery,” she says.

Threads running through the robot’s “body” attach to a thicker disk at the end of each body segment. These threads are pulled to control individual segments of the robot and bend them in different directions. Magnets within each disk, arranged with alternating polarities, ensure that the disks remain equidistant no matter the length of the robot segment. This helps the robot to bend as desired and to traverse a curvilinear path in a “follow-the-leader” motion – the snake-like “body” follows the path of the “head.” The lab has developed a sheath of overlapping scales sandwiched between two layers of silicone. When a vacuum is applied between the silicone layers, the normally flexible robot becomes stiff (illustration by Colin Hayes)

Burgner-Kahrs is developing different kinds of continuum robots that could be used in keyhole surgeries, causing even less trauma to patients than current minimally invasive surgical techniques (illustration by Colin Hayes)

Burgner-Kahrs, a computer scientist and mechanical engineer, says her lab is also developing a more advanced generation of continuum robots that are equipped with sensors and can partially steer themselves. A surgeon would have to operate the robot remotely with a computer, but the robot would know how to avoid obstacles and recognize its destination. A surgeon could deploy one of these robots to collect a tissue sample from the abdomen, for instance, or inject a cancer drug directly into a tumour in the lungs.

There are uses outside the human body, too.

A continuum robot could slide through the interior of a jet engine, inspecting it for damage. The lab is experimenting with novel forms that are even more dexterous and extensible. One recent design, with potential search-and-rescue applications, is inspired by origami: it’s very light, and can elongate up to 10 times further than other designs.

The robots could be equipped with cameras, allowing the operator to see where the robot is. Tiny surgical tools could be mounted as needed, including forceps, a laser or a suction device (illustration by Colin Hayes)

Next-generation continuum robots

To develop robots that can be used safely in a variety of medical and other applications, Burgner-Kahrs aims to answer the following questions:

How can we control continuum robots so they move even more precisely through constrained and tortuous environments?
How can we design a more intuitive interface between human and robot? Can we achieve a fully autonomous robot?
How can we use multiple continuum robots in tandem to complete a task collaboratively?

This story first appeared in the Spring 2021 issue of University of Toronto Magazine.

Nanoparticles show promise in defeating antibiotic-resistant bacteria, U of T researchers find

Christopher.Sorensen — Mon, 24 Aug 2020 16:03:10 +0000

Nanoparticles show promise in defeating antibiotic-resistant bacteria, U of T researchers find

Christopher.Sorensen Mon, 08/24/2020 - 12:03

Cutline

Ruby Sullan, an assistant professor at U of T Scarborough, says her team has designed an approach that can curb the onset of drug resistance in bacteria (photo by Ken Jones)

Topic

Research & Innovation

U of T Scarborough

A new therapy developed by researchers at the University of Toronto may bring us one step closer to effectively killing deadly drug-resistant superbugs.

“The threat posed by pathogens that are increasingly becoming resistant to all known antibiotics is an alarming and pressing health care problem,” says Ruby Sullan, assistant professor in the department of physical and environmental sciences at U of T Scarborough.

“It’s resulting in hundreds of thousands of deaths and billions of dollars in health-care costs annually, so there’s an urgent need to seek alternatives to antibiotic-only therapies.”

The therapy developed by Sullan and post-doctoral researcher Nesha Andoy uses nanoparticles made from polydopamine, a naturally occurring hormone and neurotransmitter that makes it highly compatible with the human body.

The therapy can kill bacteria in two ways. The surfaces of the nanoparticles are coated with an antimicrobial peptide (AMP) that targets and kills bacteria by binding to its membranes and destabilizing them. Since the dopamine-based particles are also highly photosensitive, they are able to heat up when exposed to low-powered laser light, killing the bacteria through heat.

The research is published in the journal Advanced Functional Materials.

Sullan says a major benefit of using these nanoparticles is that it allows the bacteria to be killed at a lower temperature using lasers, leaving the surrounding healthy cells unharmed.

“Since the mechanisms that this therapy use are different from most antibiotics, we envision that they can be designed and developed to target other drug-resistant bacteria,” she says.

Antimicrobial resistance happens when bacteria or fungi evolve to become immune to antibiotic drugs. While Sullan and her team tested this therapy on E.coli as part of their research – some strains can cause serious health problems in humans – it may eventually be used to kill a range of drug-resistant pathogens, including the bacteria that result in hospital staph infections.

Sullan says the team drew inspiration from cancer therapies.

“Polydopamine is a well-studied nanomaterial for anti-tumor applications, but our twist is that we used it to target infection caused by bacteria,” she says.

Sullan notes that the therapy doesn’t eliminate bacterial resistance, which is likely impossible. Bacteria were among the first life forms on earth, can be found living in the most extreme environments and will likely survive long after we’re gone.

“The technology we’ve developed is designed to curb the onset in which bacteria resistance develops,” says Sullan, whose research explores bacterial adhesion.

“If we can confuse the bacteria by killing it several different ways, it will have difficulty evolving quickly enough to develop resistance to these different types of mechanisms that can kill it.”

Sullan’s lab is looking at ways to decrease the size of the nanoparticle to make it more suitable for use in living organisms and exploring ways to improve its efficiency. Since the system the team has developed is highly modular, she says it can be modified to change its killing mechanisms, including changing the coating to different antimicrobial agents or loading it with antibiotic drugs.

“That could make a third bacteria-killing mechanism, so it would really enhance it as a multi-functional therapy for drug-resistant pathogens.”

The research received funding from the Canada Foundation for Innovation, Natural Sciences and Engineering Research Council of Canada, the Ontario Ministry of Research, Innovation and Science, U of T Connaught Fund and the U of T Scarborough Research Competitiveness Fund.