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.

Lateral thinking: How to workshop innovative ideas

Don't underestimate the power of play when it comes to problem-solving.

Videos
  • As we get older, the work we consistently do builds "rivers of thinking." These give us a rich knowledge of a certain kind of area.
  • The problem with this, however, is that as those patterns get deeper, we get locked into them. When this happens it becomes a challenge to think differently — to break from the past and generate new ideas.
  • How do we get out of this rut? One way is to bring play and game mechanics into workshops. When we approach problem-solving from a perspective of fun, we lose our fear of failure, allowing us to think boldly and overcome built patterns.

Are these 100 people killing the planet?

Controversial map names CEOs of 100 companies producing 71 percent of the world's greenhouse gas emissions.

Image: Jordan Engel, reused via Decolonial Media License 0.1
Strange Maps
  • Just 100 companies produce 71 percent of the world's greenhouse gases.
  • This map lists their names and locations, and their CEOs.
  • The climate crisis may be too complex for these 100 people to solve, but naming and shaming them is a good start.
Keep reading Show less

Straight millennials are becoming less accepting of LGBTQ people

The surprising results come from a new GLAAD survey.

Photo credit: Clem Onojeghuo on Unsplash
Culture & Religion
  • The survey found that 18- to 34-year-old non-LGBTQ Americans reported feeling less comfortable around LGBTQ people in a variety of hypothetical situations.
  • The attitudes of older non-LGBTQ Americans have remained basically constant over the past few years.
  • Overall, about 80 percent of Americans support equal rights for LGBTQ people.
Keep reading Show less