Hyperdimensional computing discovered to help AI robots create memories

New computing theory allows artificial intelligences to store memories.

Hyperdimensional computing discovered to help AI robots create memories

The researchers' lab through the DVS (dynamic vision sensor).

Credit: Perception and Robotics Group, University of Maryland.
  • To become autonomous, robots need to perceive the world around them and move at the same time.
  • Researchers create a theory of hyperdimensional computing to help store robot movement in high-dimensional vectors.
  • This improvement in perception will allow artificial intelligences to create memories.

Do androids dream of electric sheep? Philip K. Dick famously wondered that in his stories that explored what it meant to be human and robot in the age of advanced and widespread artificial intelligence. We aren't quite in "Blade Runner" reality just yet, but now a team of researchers came up with a new way for robots to remember that may close the gap between robots and us for good.

For robots to be as proficient as humans in various tasks, they need to coordinate sensory data with motor capabilities. Scientists from the University of Maryland published a paper in the journal Science Robotics describing a potentially revolutionary approach to improve how AI handles sensorimotor representation using hyperdimensional computing theory.

What the researchers set out to create was a way to improve a robot's "active perception" - its ability to integrate how it perceives the world around it with how it moves in that world. As they wrote in their paper, "we find that action and perception are often kept in separated spaces," which they attribute to traditional thinking.

They proposed instead "a method of encoding actions and perceptions together into a single space that is meaningful, semantically informed, and consistent by using hyperdimensional binary vectors (HBVs). "

As their press release explains, HBVs work in very high-dimensional spaces, containing a plethora of information about different discrete items like an image or a sound or a command. These can be further grouped into sequences of discrete items and groupings of items and sequences.

By utilizing these vectors, the researchers look to keep all sensory information the robot receives in one place, essentially creating its memories. As more information gets stored, "history" vectors would be created, increasing the robot's memory content.

The scientists think that active perception and memories would make the robots better at autonomous decisions, expecting future situations and completing tasks.

The Hyperdimensional "pipeline" 

This "pipeline" describes how data from a drone flight is recorded and translated into binary vectors that are integrated into memory through vector operations. This memory can then be recalled.

Credit: Perception and Robotics Group, University of Maryland.

"An active perceiver knows why it wishes to sense, then chooses what to perceive, and determines how, when and where to achieve the perception," said Aloimonos. "It selects and fixates on scenes, moments in time, and episodes. Then it aligns its mechanisms, sensors, and other components to act on what it wants to see, and selects viewpoints from which to best capture what it intends. Our hyperdimensional framework can address each of these goals."

Outside of robots, the scientists also see an application of their theories in deep learning AI methods employed in data mining and visual recognition.

To test the theory, the team employed a dynamic vision sensor (DVS) which continually captures the edges of objects in event clouds as they move by. By quickly focusing on the contours of the scene and the movement, this sensor is well-suited for autonomous navigation of robots. The data from the event clouds is stored in binary vectors, allowing the scientists to apply hyperdimensional computing.

Here’s a video of how DVS works:

The research was carried out by the computer science Ph.D. students Anton Mitrokhin and Peter Sutor, Jr., along with Cornelia Fermüller, an associate research scientist with the University of Maryland Institute for Advanced Computer Studies, as well as the computer science professor Yiannis Aloimonos. He advised Mitrokhin and Sutor.

Check out their paper "Learning sensorimotor control with neuromorphic sensors: Toward hyperdimensional active perception" in Science Robotics.

Were the ancient Egyptians black or white? Scientists now know

This is the first successful DNA sequencing on ancient Egyptian mummies, ever.

 

Ancient Egyptian Statues

Getty Images
Surprising Science

Egyptologists, writers, scholars, and others, have argued the race of the ancient Egyptians since at least the 1970's. Some today believe they were Sub-Saharan Africans. We can see this interpretation portrayed in Michael Jackson's 1991 music video for “Remember the Time" from his "Dangerous" album. The video, a 10-minute mini-film, includes performances by Eddie Murphy and Magic Johnson.

Keep reading Show less

'Ghost forests' visible from space spread along the coast as sea levels rise

Seawater is raising salt levels in coastal woodlands along the entire Atlantic Coastal Plain, from Maine to Florida.

Photo by Anqi Lu on Unsplash
Surprising Science
Trekking out to my research sites near North Carolina's Alligator River National Wildlife Refuge, I slog through knee-deep water on a section of trail that is completely submerged.
Keep reading Show less

Why professional soccer players choke during penalty kicks

A new study used functional near-infrared spectroscopy (fNIRS) to measure brain activity as inexperienced and experienced soccer players took penalty kicks.

PORTLAND, OREGON - MAY 09: Diego Valeri #8 of Portland Timbers reacts after missing a penalty kick in the second half against the Seattle Sounders at Providence Park on May 09, 2021 in Portland, Oregon.

Abbie Parr via Getty Images
Mind & Brain
  • The new study is the first to use in-the-field imaging technology to measure brain activity as people delivered penalty kicks.
  • Participants were asked to kick a total of 15 penalty shots under three different scenarios, each designed to be increasingly stressful.
  • Kickers who missed shots showed higher activity in brain areas that were irrelevant to kicking a soccer ball, suggesting they were overthinking.
Keep reading Show less
Quantcast