Robot with Tactile Sensors Beats Humans at Identifying Textures

Monday, June 18th, 2012 Robot Beats Human at Touch

SynTouch LLC (Los Angeles) and the University of Southern California jointly announced a major advance in robotics today. In an article appearing in Frontiers in Neurorobotics today, Jeremy Fishel and Gerald Loeb describe a specialized robot equipped with a new sensor that mimics the sensitivity of the human fingertip. The robot outperformed humans in identifying a wide range of natural materials according to their textures.

The research team at SynTouch combined their BioTac® sensor with a new algorithm that imitates the exploratory strategies that humans use to identify objects. The specialized robot was trained on 117 common materials gathered from fabric, stationery and hardware stores. When confronted with one material at random, it could identify the exact material 95% of the time, after intelligently selecting and making an average of five exploratory movements. It was much less likely to be confused by a pair of similar textures than human subjects making their own exploratory movements.

“This demonstrates the potential of tactile sensing to revolutionize both industrial robots and prosthetic hands, which have lacked such sensing,” said Dr. Fishel, Director of Research at SynTouch. Researchers throughout the world are starting to use the company’s BioTac sensors to enable human-like dexterity.

The research article from Frontiers in Neurorobotics is available HERE

The press release from the University of Southern California is available HERE

Start a Conversation