Hyperdimensional computing discovered to help AI robots create memories

New computing theory allows artificial intelligences to store memories.

  • 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" 

Credit: Perception and Robotics Group, University of Maryland.

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.

"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.

3D printing might save your life one day. It's transforming medicine and health care.

What can 3D printing do for medicine? The "sky is the limit," says Northwell Health researcher Dr. Todd Goldstein.

Northwell Health
Sponsored by Northwell Health
  • Medical professionals are currently using 3D printers to create prosthetics and patient-specific organ models that doctors can use to prepare for surgery.
  • Eventually, scientists hope to print patient-specific organs that can be transplanted safely into the human body.
  • Northwell Health, New York State's largest health care provider, is pioneering 3D printing in medicine in three key ways.
Keep reading Show less

Lama Rod Owens – the price of the ticket to freedom

An ordained Lama in a Tibetan Buddhist lineage, Lama Rod grew up a queer, black male within the black Christian church in the American south. Navigating all of these intersecting, evolving identities has led him to a life's work based on compassion for self and others.

Think Again Podcasts
  • "What I'm interested in is deep, systematic change. What I understand now is that real change doesn't happen until change on the inside begins to happen."
  • "Masculinity is not inherently toxic. Patriarchy is toxic. We have to let that energy go so we can stop forcing other people to do emotional labor for us."
Keep reading Show less

For most of history, humans got smarter. That's now reversing.

We were gaining three IQ points per decade for many, many years. Now, that's going backward. Could this explain some of our choices lately?

The Flynn effect appears to be in retrograde. (Credit: Shutterstock/Big Think)
popular

There's a new study out of Norway that indicates our—well, technically, their—IQs are shrinking, to the tune of about seven IQ points per generation.

Keep reading Show less

Lateral thinking: The reason you’ve heard of Nintendo and Marvel

Here's why generalists triumph over specialists in the new era of innovation.

Videos
  • Since the explosion of the knowledge economy in the 1990s, generalist inventors have been making larger and more important contributions than specialists.
  • One theory is that the rise of rapid communication technologies allowed the information created by specialists to be rapidly disseminated, meaning generalists can combine information across disciplines to invent something new.
  • Here, David Epstein explains how Nintendo's Game Boy was a case of "lateral thinking with withered technology." He also relays the findings of a fascinating study that found the common factor of success among comic book authors.
Keep reading Show less