Our Seattle Forecast: Cloudy, with a 100% Chance of Robotics Innovation

by Allison Toh

Rain, Mount Rainier and, now, robots.

The Seattle landscape is getting another feature with the opening of our AI Robotics Research Lab. NVIDIA CEO Jensen Huang was there to celebrate, mixing with man and machine alike.

Leading the facility is Dieter Fox, senior director of robotics research at NVIDIA and professor at the University of Washington Paul G. Allen School of Computer Science and Engineering.

Dieter Fox, a roboticist and University of Washington professor, leads the new AI Robotics Research Lab in Seattle.

“We wanted a location that keeps us close to UW to enable easy collaboration with the university,” said Fox. “For example, we often invite students from the UW robotics community to spend time here and attend seminars with external speakers.”

The lab opened in November with 14 researchers and expects to triple in size by midyear, including visiting faculty and interns.

Fox is a leading researcher in robotics and AI. His current research is in interactive manipulation, where robots, called “cobots,” can perform complex tasks and work alongside humans.

While current industrial manipulators are separated from humans and are limited to performing repetitive actions, Fox sees cobots as the next step for robotics, playing a significant role in manufacturing, healthcare, in the home, and helping people with physical disabilities.

NVIDIA CEO Jensen Huang at Seattle Robotics Lab opening
Huang mixing with all things machine at our lab opening.

“We want to develop robots that can naturally perform tasks alongside people,” said Fox. “To do that, they need to be able to understand what a person wants to do and figure out how to help her achieve a goal.”

The robotics lab is working on around a dozen research projects, the main one being a robot that can operate in a real-life kitchen. The “kitchen manipulator” integrates state-of-the-art AI and deep learning techniques to detect and track objects, keep track of the positions of doors and drawers in the kitchen, and open/close them to get access to objects for manipulation. For more details, check out our Developer News Center story.

Fox sees the kitchen as an ideal testing platform, representing a wide range of other application domains. While it’s a structured environment, it’s easy to introduce new variables to the robot in the form of more complex tasks, such as dealing with unknown objects or assisting a person who is cooking a meal.

The robot kitchen assistant (“kitchen manipulator”) in action.

“All of this is working toward enabling the next generation of smart manipulators that can also operate in open-ended environments where not everything is designed specifically for them,” said Fox. “By pulling together recent advances in perception, control, learning and simulation, we can help the research community solve some of the greatest challenges in robotics.”

Earlier this year, NVIDIA also opened an AI research lab in Toronto, led by Sanja Fidler, a leading computer vision research scientist and University of Toronto professor.

The NVIDIA Research team consists of more than 200 scientists around the globe, focusing on areas including AI, computer vision, self-driving cars, robotics and graphics.