A robot can struggle to discover objects in its surroundings when it relies on computer vision alone. But by taking advantage of all of the information available to it — an object's location, size, shape and even whether it can be lifted — a robot can continually discover and refine its understanding of objects, say researchers at Carnegie Mellon University's Robotics Institute.
Carnegie Mellon University researchers have shown that a two-armed mobile robot, called HERB, can continually discover and refine its understanding of objects by taking advantage of all of the information available, including the object's location, size, shape and even whether it can be lifted.
Credit: Carnegie Mellon University
The Lifelong Robotic Object Discovery (LROD) process developed by the research team enabled a two-armed, mobile robot to use color video, a Kinect depth camera and non-visual information to discover more than 100 objects in a home-like laboratory, including items such as computer monitors, plants and food items. Normally, the CMU researchers build digital models and images of objects and load them into the memory of HERB — the Home-Exploring Robot Butler — so the robot can recognize objects that it needs to manipulate.
Virtually all roboticists do something similar to help their robots recognize objects. With the team's implementation of LROD, called HerbDisc, the robot now can discover these objects on its own. With more time and experience, HerbDisc gradually refines its models of the objects and begins to focus its attention on those that are most relevant to its goal — helping people accomplish tasks of daily living. Findings from the research study will be presented May 8 at the IEEE International Conference on Robotics and Automation in Karlsruhe, Germany.
The robot's ability to discover objects on its own sometimes takes even the researchers by surprise, said Siddhartha Srinivasa, associate professor of robotics and head of the Personal Robotics Lab, where HERB is being developed. In one case, some students left the remains of lunch — a pineapple and a bag of bagels — in the lab when they went home for the evening. The next morning, they returned to find that HERB had built digital models of both the pineapple and the bag and had figured out how it could pick up each one.
"We didn't even know that these objects existed, but HERB did," said Srinivasa, who jointly supervised the research with Martial Hebert, professor of robotics. "That was pretty fascinating."
Discovering and understanding objects in places filled with hundreds or thousands of things will be a crucial capability once robots begin working in the home and expanding their role in the workplace. Manually loading digital models of every object of possible relevance simply isn't feasible, Srinivasa said. "You can't expect Grandma to do all this," he added.
Object recognition has long been a challenging area of inquiry for computer vision researchers. Recognizing objects based on vision alone quickly becomes an intractable computational problem in a cluttered environment, Srinivasa said. But humans don't rely on sight alone to understand objects; babies will squeeze a rubber ducky, beat it against the tub, dunk it — even stick it in their mouth. Robots, too, have a lot of "domain knowledge" about their environment that they can use to discover objects.
Taking advantage of all of HERB's senses required a research team with complementary expertise — Srinivasa's insights on robotic manipulation and Hebert's in-depth knowledge of computer vision. Alvaro Collet, a robotics Ph.D. student they co-advised, led the development of HerbDisc. Collet is now a scientist at Microsoft.
Depth measurements from HERB's Kinect sensors proved to be particularly important, Hebert said, providing three-dimensional shape data that is highly discriminative for household items.
Other domain knowledge available to HERB includes location — whether something is on a table, on the floor or in a cupboard. The robot can see whether a potential object moves on its own, or is moveable at all. It can note whether something is in a particular place at a particular time. And it can use its arms to see if it can lift the object — the ultimate test of its "objectness."
"The first time HERB looks at the video, everything 'lights up' as a possible object," Srinivasa said. But as the robot uses its domain knowledge, it becomes clearer what is and isn't an object. The team found that adding domain knowledge to the video input almost tripled the number of objects HERB could discover and reduced computer processing time by a factor of 190. A HERB's-eye view of objects is available on YouTube.
HERB's definition of an object — something it can lift — is oriented toward its function as an assistive device for people, doing things such as fetching items or microwaving meals. "It's a very natural, robot-driven process," Srinivasa said. "As capabilities and situations change, different things become important." For instance, HERB can't yet pick up a sheet of paper, so it ignores paper. But once HERB has hands capable of manipulating paper, it will learn to recognize sheets of paper as objects.
Though not yet implemented, HERB and other robots could use the Internet to create an even richer understanding of objects. Earlier work by Srinivasa showed that robots can use crowdsourcing via Amazon Mechanical Turk to help understand objects. Likewise, a robot might access image sites, such as RoboEarth, ImageNet or 3D Warehouse, to find the name of an object, or to get images of parts of the object it can't see.
Bo Xiong, a student at Connecticut College, and Corina Gurau, a student at Jacobs University in Bremen, Germany, also contributed to this study.
HERB is a project of the Quality of Life Technology Center, a National Science Foundation engineering research center operated by Carnegie Mellon and the University of Pittsburgh. The center is focused on the development of intelligent systems that improve quality of life for everyone while enabling older adults and people with disabilities.
The Robotics Institute is part of Carnegie Mellon's School of Computer Science. Follow the school on Twitter @SCSatCMU.
About Carnegie Mellon University: Carnegie Mellon is a private, internationally ranked research university with programs in areas ranging from science, technology and business, to public policy, the humanities and the arts. More than 12,000 students in the university's seven schools and colleges benefit from a small student-to-faculty ratio and an education characterized by its focus on creating and implementing solutions for real problems, interdisciplinary collaboration and innovation. A global university, Carnegie Mellon has campuses in Pittsburgh, Pa., California's Silicon Valley and Qatar, and programs in Africa, Asia, Australia, Europe and Mexico. The university has exceeded its $1 billion campaign, titled "Inspire Innovation: The Campaign for Carnegie Mellon University," which aims to build its endowment, support faculty, students and innovative research, and enhance the physical campus with equipment and facility improvements. The campaign closes June 30, 2013.
Byron Spice | EurekAlert!
A Dream for the Future: “Flying with Green Fuel"
25.07.2018 | Universität Bremen
Investigating cell membranes: researchers develop a substance mimicking a vital membrane component
25.05.2018 | Westfälische Wilhelms-Universität Münster
New design tool automatically creates nanostructure 3D-print templates for user-given colors
Scientists present work at prestigious SIGGRAPH conference
Most of the objects we see are colored by pigments, but using pigments has disadvantages: such colors can fade, industrial pigments are often toxic, and...
Scientists at the University of California, Los Angeles present new research on a curious cosmic phenomenon known as "whistlers" -- very low frequency packets...
Scientists develop first tool to use machine learning methods to compute flow around interactively designable 3D objects. Tool will be presented at this year’s prestigious SIGGRAPH conference.
When engineers or designers want to test the aerodynamic properties of the newly designed shape of a car, airplane, or other object, they would normally model...
Researchers from TU Graz and their industry partners have unveiled a world first: the prototype of a robot-controlled, high-speed combined charging system (CCS) for electric vehicles that enables series charging of cars in various parking positions.
Global demand for electric vehicles is forecast to rise sharply: by 2025, the number of new vehicle registrations is expected to reach 25 million per year....
Proteins must be folded correctly to fulfill their molecular functions in cells. Molecular assistants called chaperones help proteins exploit their inbuilt folding potential and reach the correct three-dimensional structure. Researchers at the Max Planck Institute of Biochemistry (MPIB) have demonstrated that actin, the most abundant protein in higher developed cells, does not have the inbuilt potential to fold and instead requires special assistance to fold into its active state. The chaperone TRiC uses a previously undescribed mechanism to perform actin folding. The study was recently published in the journal Cell.
Actin is the most abundant protein in highly developed cells and has diverse functions in processes like cell stabilization, cell division and muscle...
17.08.2018 | Event News
08.08.2018 | Event News
27.07.2018 | Event News
17.08.2018 | Physics and Astronomy
17.08.2018 | Information Technology
17.08.2018 | Life Sciences