CHANNELS

Aerospace

Automotive

Automated & Autonomous Vehicles

Battery & Electrification Technology

Defense

Drone TV

Electronics

Manufacturing & Prototyping

Materials

Medical

Motion Control

RF & Microwave Technology

Robotics & Automation

Sensors & IoT

Test & Measurement

Aerospace
Automotive
Automated & Autonomous Vehicles
Battery & Electrification Technology
Defense
Drone TV
Electronics
Manufacturing & Prototyping
Materials
Medical
Motion Control
RF & Microwave Technology
Robotics & Automation
Sensors & IoT
Test & Measurement
Aerospace & Defense
Search Results

Robots Get A Feel For The World

Researchers at the University of Southern California's Viterbi School of Engineering have demonstrated that a specially designed robot can outperform humans in identifying a wide range of natural materials according to their textures - paving the way for advancements in prostheses, personal assistive robots, and consumer product testing. The robot was equipped with a new type of tactile sensor built to mimic the human fingertip. It also used a newly designed algorithm to make decisions about how to explore the outside world by imitating human strategies.

Topics:
Automation Implants & Prosthetics Medical Motion Control Robotics Sensors

More From SAE Media Group

    Transcript

    00:00:02 [Music] I would say a bit rough compared to the first one but I can't tell the difference so it problem that we've been asking is how do you judge textures and can we get a robot to do the same thing if you have ever had your finger is so numb from the cold that you couldn't feel things uh your hands are almost useless even though your muscles are

    00:00:36 perfectly functional if you can't feel what you're touching it slips you can't identify things it's as if your hands are paralyzed uh and so by adding tactile sensing to prosthetic hands we can overcome that problem and start to have prosthetic hands that really do have some functionality so the biotac is a fluid filled fingertip that's the same size as the human finger we've also

    00:00:59 implemented finger PR on the surface of the biotac so that it uh is able to sense textures the same way that humans can and in particular it's very good at picking up the vibrations that you actually get as you run your finger over different textured surfaces and those patterns of vibrations are what you use to identify say a piece of cotton from a piece of wool couch is a startup company

    00:01:20 that I and several of the people in my laboratory started to develop the tactile sensing technology the hard part of the problem is replacing the stuff between the ears of a human Observer not their fingers when humans explore objects by touch there are a great number of exploratory movements that you can make for instance you can grasp the object to figure out at shape or explore

    00:01:39 it to figure out its texture so you have to make Intelligent Decisions about which movements would give you the most information which is what we've done with Asian exploration so in our experiments we used 117 different textures uh what the algorithm does is it first makes one exploratory movement and from that information it determines that it could be a number of textures

    00:01:59 and with the these types of intelligent strategies we were able to obtain a 95% classification accuracy well I'm excited because it's a new class of device um it's a difficult problem because when you build a new capability a disruptive technology you don't already have pre-existing markets there are no tactile sensors on prosthetic hands or on Industrial robots because there

    00:02:24 haven't been any sensors so coming up with the applications the algorithms the kind of work that we're producing in this paper are the opportunity now to do things that have never been done before [Music]