This article is part of our series highlighting IEEE Fellows in celebration of the Fellow program’s 50th anniversary year.
Although they are often depicted as dangerous enemies in science fiction movies, robots have not taken over the world yet, or even tried to. In fact, they have made a significant and positive impact. Four IEEE Fellows are developing technologies that make robots safe to operate, durable, and smart enough to perform many of the tasks people are unable, or too busy, to do.
IEEE Fellow Rodney A. Brooks [above] wants people to be able to work as seamlessly with robots as we do with other technologies, like computers. That’s why he founded Rethink Robotics, a start-up in Boston that manufactures industrial robots. He was elevated to IEEE Fellow in 2013 “for contributions to theory and practice of behavioral robotics and artificial intelligence.”
In 2012, the company unveiled Baxter, a stationary helper robot with two arms and an array of safety mechanisms and sensors to protect the factory workers it assists. Baxter also avoids injuring people by slowing down or pausing when it senses that someone is approaching. But perhaps Baxter’s most striking feature is its set of virtual “eyes.” A tablet-size computer screen sits atop the machine and displays human-like eyes that turn to look at you if, for example, you touch one of its arms. This feature is meant to make the machine seem friendly and interactive.
A BETTER LOOK
A driving force in the field of robotics for more than four decades, IEEE Life Fellow Ruzena Bajcsy has helped robots achieve humanlike performance through her pioneering work on machine vision and perception. She was elevated to Fellow in 1992 “for contributions to machine perception and robotics.”
During the 1980s, Bajcsy was the first to recognize that active perception was needed to improve a robot’s computer vision and image acquisition. Active perception enables robots to control the positions and angles of their built-in cameras instead of having them remain motionless. Bajcsy and her colleagues at the University of Pennsylvania, in Philadelphia, built a robot that could automatically zoom in on objects, turn its head and “look” at things, which helped it better sense and explore unfamiliar environments and avoid obstacles in its way.
Bajcsy was a computer science professor for 30 years at UPenn, where she founded the General Robotics, Automation, Sensing, and Perception Laboratory. Since 2001 she has been a professor of computer science and electrical engineering at the University of California, Berkeley, where her research focuses on computer version, artificial intelligence (AI), and robotics. You can read her oral history on the IEEE Global History Network.
PAVING THE WAY
Autonomous robots would have a difficult time finding their way if it wasn’t for IEEE Fellow Lydia Kavraki’s pioneering advances in the field. She was elevated in 2012 “for contributions to robot-motion planning and computational biology.”
A professor of computer science and bioengineering at Rice University, in Houston, Kavraki developed the Probabilistic Roadmap Method, which uses randomizing and sampling-based motion algorithms to help robots move around while avoiding obstacles. She authored Principles of Robot Motion (MIT Press, 2005), a preeminent textbook on the subject. Kavraki also helped develop the Open Motion Planning Library software, which uses sampling-based algorithms to program AI robots. Her research has had numerous applications, including solving problems such as how to teach surgical robots to tie sutures.
If she wasn’t busy enough, Kavraki also researches the structure and flexibility of molecules at her laboratory at Rice, which is named in her honor. It focuses on robotics and biomedical computing.
CARRYING THE LOAD
IEEE Fellow Martin Buehler was elevated to Fellow in 2013 “for contributions to design and control of legged robots.” One of the most notable of these is BigDog, which was developed by Boston Dynamics, where Buehler was director of robotics. It was funded by the U.S. Defense Advanced Research Projects Agency.
BigDog is a four-legged robot that’s about a meter high. It’s meant to serve as a sort of pack mule to accompany soldiers as they travel through terrain that is too rough or steep for conventional vehicles. Moving at up to about 7 kilometers per hour, the robot can climb slopes of up to 35 degrees and trudge through rubble, mud, and snow—all while carrying a payload of up to 180 kilograms. Last year it was outfitted with a mechanical arm that can pick up and toss aside heavy objects in its way that are about the size of 20-kilogram cinder blocks.
Buehler is now senior director of research and development at Covidien, a medical technology company, in Mansfield, Mass., where he helps develop surgical robots that perform minimally invasive procedures.