Sense Of Touch Developed For Robots
With the right sensors, actuators and software, robots can now be given a tactile sense that imitates that of the sense of touch in humans.
A specially designed robot is able to outperform humans in the identification of a wide range of materials based on their textures, according to new research from the University of Southern California’s Viterbi School of Engineering. This will lead to advancements in prostheses, personal assistive robots, and consumer product testing.
Equipped with a new type of tactile sensor, the robot is built to mimic the function of a human fingertip. It also employs a newly designed algorithm that helps to make decisions, using strategies similar to the ones humans use, about the exploration of the outside environment.
The robotic sensor is also capable of other human sensations, such as telling where and from what direction forces are applied to the fingertip sensor, and the relative temperature of the object being touched.
Similar to a human finger, the BioTac® sensor is covered in a soft and flexible skin, over a liquid filling. The skin also employs ‘fingerprints’ on its surface, which greatly enhances the sensor’s sensitivity to vibration.
While the sensor slides over a textured surface, the ‘skin’ of the sensor vibrates in characteristic ways. “These vibrations are detected by a hydrophone inside the bone-like core of the finger. The human finger uses similar vibrations to identify textures, but the robot finger is even more sensitive.”
Humans use a variety of different exploratory movements, based on their prior experiences with similar objects, to identify an object by touch. “A famous theorem by 18th century mathematician Thomas Bayes describes how decisions might be made from the information obtained during these movements. Until now, however, there was no way to decide which exploratory movement to make next.”
The study authors created a new theorem for solving this general problem as “Bayesian Exploration.”
The specialized robot they made “was trained on 117 common materials gathered from fabric, stationery and hardware stores. When confronted with one material at random, the robot could correctly identify the material 95% of the time, after intelligently selecting and making an average of five exploratory movements. It was only rarely confused by pairs of similar textures that human subjects making their own exploratory movements could not distinguish at all.”
The authors “point out that while their robot is very good at identifying which textures are similar to each other, it has no way to tell what textures people will prefer. Instead, they say this robot touch technology could be used in human prostheses or to assist companies who employ experts to assess the feel of consumer products and even human skin.”
The study authors Gerald Loeb and Jeremy Fishel are partners in SynTouch LLC, a company that develops and “manufactures tactile sensors for mechatronic systems that mimic the human hand.” The company was started in 2008 by researchers from USC’s Medical Device Development Facility. They are now selling their BioTac sensors to other scientists and to manufacturers of industrial robots and prosthetic hands.
The research has just been published in the journal Frontiers In Neurorobotics.
Source and Image: University of Southern California