Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Helping robots learn to see in 3-D

17.07.2017

Robots need to guess what they're seeing better, even when parts are hidden from view

Autonomous robots can inspect nuclear power plants, clean up oil spills in the ocean, accompany fighter planes into combat and explore the surface of Mars.


When fed 3-D models of household items in bird's-eye view (left), a new algorithm is able to guess what the objects are, and what their overall 3-D shapes should be. This image shows the guess in the center, and the actual 3-D model on the right.

Courtesy of Ben Burchfiel

Yet for all their talents, robots still can't make a cup of tea.

That's because tasks such as turning the stove on, fetching the kettle and finding the milk and sugar require perceptual abilities that, for most machines, are still a fantasy.

Among them is the ability to make sense of 3-D objects. While it's relatively straightforward for robots to "see" objects with cameras and other sensors, interpreting what they see, from a single glimpse, is more difficult.

Duke University graduate student Ben Burchfiel says the most sophisticated robots in the world can't yet do what most children do automatically, but he and his colleagues may be closer to a solution.

Burchfiel and his thesis advisor George Konidaris, now an assistant professor of computer science at Brown University, have developed new technology that enables machines to make sense of 3-D objects in a richer and more human-like way.

A robot that clears dishes off a table, for example, must be able to adapt to an enormous variety of bowls, platters and plates in different sizes and shapes, left in disarray on a cluttered surface.

Humans can glance at a new object and intuitively know what it is, whether it is right side up, upside down or sideways, in full view or partially obscured by other objects.

Even when an object is partially hidden, we mentally fill in the parts we can't see.

Their robot perception algorithm can simultaneously guess what a new object is, and how it's oriented, without examining it from multiple angles first. It can also "imagine" any parts that are out of view.

A robot with this technology wouldn't need to see every side of a teapot, for example, to know that it probably has a handle, a lid and a spout, and whether it is sitting upright or off-kilter on the stove.

The researchers say their approach, which they presented July 12 at the 2017 Robotics: Science and Systems Conference in Cambridge, Massachusetts, makes fewer mistakes and is three times faster than the best current methods.

This is an important step toward robots that function alongside humans in homes and other real-world settings, which are less orderly and predictable than the highly controlled environment of the lab or the factory floor, Burchfiel said.

With their framework, the robot is given a limited number of training examples, and uses them to generalize to new objects.

"It's impractical to assume a robot has a detailed 3-D model of every possible object it might encounter, in advance," Burchfiel said.

The researchers trained their algorithm on a dataset of roughly 4,000 complete 3-D scans of common household objects: an assortment of bathtubs, beds, chairs, desks, dressers, monitors, nightstands, sofas, tables and toilets.

Each 3-D scan was converted into tens of thousands of little cubes, or voxels, stacked on top of each other like LEGO blocks to make them easier to process.

The algorithm learned categories of objects by combing through examples of each one and figuring out how they vary and how they stay the same, using a version of a technique called probabilistic principal component analysis.

When a robot spots something new -- say, a bunk bed -- it doesn't have to sift through its entire mental catalogue for a match. It learns, from prior examples, what characteristics beds tend to have.

Based on that prior knowledge, it has the power to generalize like a person would -- to understand that two objects may be different, yet share properties that make them both a particular type of furniture.

To test the approach, the researchers fed the algorithm 908 new 3-D examples of the same 10 kinds of household items, viewed from the top.

From this single vantage point, the algorithm correctly guessed what most objects were, and what their overall 3-D shapes should be, including the concealed parts, about 75 percent of the time -- compared with just over 50 percent for the state-of-the-art alternative.

It was also capable of recognizing objects that were rotated in various ways, which the best competing approaches can't do.

While the system is reasonably fast -- the whole process takes about a second -- it is still a far cry from human vision, Burchfiel said.

For one, both their algorithm and previous methods were easily fooled by objects that, from certain perspectives, look similar in shape. They might see a table from above, and mistake it for a dresser.

"Overall, we make a mistake a little less than 25 percent of the time, and the best alternative makes a mistake almost half the time, so it is a big improvement," Burchfiel said. "But it still isn't ready to move into your house. You don't want it putting a pillow in the dishwasher."

Now the team is working on scaling up their approach to enable robots to distinguish between thousands of types of objects at a time.

"Researchers have been teaching robots to recognize 3-D objects for a while now," Burchfield said. What's new, he explained, is the ability to both recognize something and fill in the blind spots in its field of vision, to reconstruct the parts it can't see.

"That has the potential to be invaluable in a lot of robotic applications," Burchfiel said.

###

This research was supported in part by The Defense Advanced Research Projects Agency, DARPA (D15AP00104).

CITATION: "Bayesian Eigenobjects: A Unified Framework for 3D Robot Perception," Benjamin Burchfiel and George Konidaris. RSS 2017, July 12-16, 2017, Cambridge, Massachusetts.

Media Contact

Robin Ann Smith
ras10@duke.edu
919-681-8057

 @DukeU

http://www.duke.edu 

Robin Ann Smith | EurekAlert!

More articles from Information Technology:

nachricht Snake-inspired robot uses kirigami to move
22.02.2018 | Harvard John A. Paulson School of Engineering and Applied Sciences

nachricht Camera technology in vehicles: Low-latency image data compression
22.02.2018 | Fraunhofer-Institut für Nachrichtentechnik, Heinrich-Hertz-Institut, HHI

All articles from Information Technology >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: Attoseconds break into atomic interior

A newly developed laser technology has enabled physicists in the Laboratory for Attosecond Physics (jointly run by LMU Munich and the Max Planck Institute of Quantum Optics) to generate attosecond bursts of high-energy photons of unprecedented intensity. This has made it possible to observe the interaction of multiple photons in a single such pulse with electrons in the inner orbital shell of an atom.

In order to observe the ultrafast electron motion in the inner shells of atoms with short light pulses, the pulses must not only be ultrashort, but very...

Im Focus: Good vibrations feel the force

A group of researchers led by Andrea Cavalleri at the Max Planck Institute for Structure and Dynamics of Matter (MPSD) in Hamburg has demonstrated a new method enabling precise measurements of the interatomic forces that hold crystalline solids together. The paper Probing the Interatomic Potential of Solids by Strong-Field Nonlinear Phononics, published online in Nature, explains how a terahertz-frequency laser pulse can drive very large deformations of the crystal.

By measuring the highly unusual atomic trajectories under extreme electromagnetic transients, the MPSD group could reconstruct how rigid the atomic bonds are...

Im Focus: Developing reliable quantum computers

International research team makes important step on the path to solving certification problems

Quantum computers may one day solve algorithmic problems which even the biggest supercomputers today can’t manage. But how do you test a quantum computer to...

Im Focus: In best circles: First integrated circuit from self-assembled polymer

For the first time, a team of researchers at the Max-Planck Institute (MPI) for Polymer Research in Mainz, Germany, has succeeded in making an integrated circuit (IC) from just a monolayer of a semiconducting polymer via a bottom-up, self-assembly approach.

In the self-assembly process, the semiconducting polymer arranges itself into an ordered monolayer in a transistor. The transistors are binary switches used...

Im Focus: Demonstration of a single molecule piezoelectric effect

Breakthrough provides a new concept of the design of molecular motors, sensors and electricity generators at nanoscale

Researchers from the Institute of Organic Chemistry and Biochemistry of the CAS (IOCB Prague), Institute of Physics of the CAS (IP CAS) and Palacký University...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

2nd International Conference on High Temperature Shape Memory Alloys (HTSMAs)

15.02.2018 | Event News

Aachen DC Grid Summit 2018

13.02.2018 | Event News

How Global Climate Policy Can Learn from the Energy Transition

12.02.2018 | Event News

 
Latest News

Basque researchers turn light upside down

23.02.2018 | Physics and Astronomy

Finnish research group discovers a new immune system regulator

23.02.2018 | Health and Medicine

Attoseconds break into atomic interior

23.02.2018 | Physics and Astronomy

VideoLinks
Science & Research
Overview of more VideoLinks >>>