Inspired by bees, scientists teach robots to communicate with ‘motion dances’

An international team of researchers was inspired by bees to teach robots to understand human gestures and transmit them with their “motion dance”.

Bees communicate the location of flower spots using an elaborate dance. (Illustrative image) (Image credit: Pixabay)

Taking inspiration from bees, an international team of researchers have developed gesture recognition that will allow robots to communicate with each other by “dancing” with a coordinated set of gestures to convey information. The research is published in the journal Frontiers.

In nature, once a honey bee finds a patch of flower where it can extract nectar, it returns to the hive to warn other bees. Once there, he performs a “dance dance” to tell the other bees about the location of the flower part. Other bees interpret the movements and duration of the dance to understand where the flower part is in relation to the hive. Researchers used a similar technique to ‘teach’ two robots to communicate with a dance.

“A visual communication system has been developed for robots with onboard cameras, using algorithms that allow the robots to interpret what they see. Humans and robots communicate using gestures, such as a raised hand with a closed fist,” Abhra Roy Chowdhury, senior author of the paper, told in an email interaction. Chowdhury is the head of the Laboratory of Robotics Innovation at the Center for Product Design and Manufacturing at the Indian Institute of Science in Bengaluru.

Chowdhury and his co-author Kaustubh Joshi, a doctoral student and research assistant at the University of Maryland, developed a proof-of-concept for this communication system using two robots that served as proxies for package-handling robots.

First, a human operator used hand gestures, such as a raised or clenched fist, to convey a coded message containing the location of a ‘package’. A robot detected these gestures and decoded the message to understand the location of the package based on a map of the environment that was encoded in it. It was then able to relay the same information to a second robot through a jump. The robots were able to successfully interpret and transmit information 93.33 percent of the time during the experiments.

Robots usually communicate with each other using various digital networks, including wireless communication. But according to Chowdhury, there may be situations where network communications are not available but robotic work is required, such as in disaster areas or during spacewalks. Since the robots in the study used simple cameras to identify gestures, the technology has the potential for scalability.

Chowdhury told that he and Joshi are now working to make the technology more accurate and powerful so that it can be used to convey more complex messages, tasks and instructions.

Express explained
Go beyond the news. Understand the titles with our explained stories

  • The Indian Express website has been rated GREEN for its reliability and credibility by Newsguard, a global service that rates news sources for their journalistic standards.

© IE Online Media Services Pvt Ltd

Leave a Comment

Your email address will not be published.