AI News, Finally: Robots Learn What 'Squishy' Really Means
Finally: Robots Learn What 'Squishy' Really Means
Humans use all sorts of bizarre, abstract terms to describe how objects feel, and it’s endlessly frustrating to robots.
Translating such sensor data into something that a human can understand is especially difficult, but in a paper presented this week, a PR2 robot equipped with an innovative finger sensor from SynTouch has been taught to use touch exploration to associate objects with 'tactile adjectives.'
After training the PR2 by correlating haptic sensor data with adjectives from humans who touched the same objects, the robot was tested out on a series of objects that it had never experienced before to see whether it would be able to derive the same haptic adjectives as humans do.
As shown in the video above (although it flashes past pretty quickly at the end), humans described the folded satin pillowcase as 'compact, compressible, deformable, smooth, and squishy,' while the robot thought it was 'compact, compressible, crinkly, smooth, and squishy.'
Furthermore, we have shown that these object properties can be related to subjective human labels in the form of haptic adjectives, a task that has rarely been explored in the literature, though it stands to beneﬁt a wide range of future applications in robotics.
PR2 Robot Has Been Taught The Meaning Of Tactile Adjectives (+VIDEO)
In our daily communication we use various abstract terms to describe, how objects feel.
Translating such sensor data into something that a human can understand is rather difficult, though a PR2 robot equipped with an innovative finger sensor from SynTouch has been taught to use touch exploration to associate objects with “tactile adjectives.”
The researchers had a PR2 with the BioTac tactile finger sensor perform a series of procedures on the same set of objects, including tapping, squeezing, holding, and both slow and fast sliding.
- On Thursday, February 27, 2020
Human Robot Collaboration based on Tactile Sensors
This is a video showing the experimental results in the paper "Human Intention Estimation with Tactile Sensors in Human-Robot Collaboration" submitted to 2017 ASME Dynamic Systems and Control...
Robot Learns How to Describe Objects with Tactile Adjectives
Vision researchers and their colleagues showed that it was possible for a robot equipped with rich multi-channel tactile sensors to learn to associate certain objects with appropriate "tactile...
Robot using touch sensor
This is a primary robot made with the help of a touch sensor.
KRISS Robot Fingertip Module for tactile sensing (touch location and pressure)
This video clip shows a Robot Fingertip Module made by KRISS(Korea Research Institute of Standards and Science) in Rep. of Korea. [ Feature of KRISS Robot Fingertip Module ] 1. Human-like...
IEEE Presentation: Flexible and Conformable Capacitive Tactile Sensors from R&D to Commercialization
Presentation given by PPS founder Dr. Jae Son at the IEEE / Northeastern University Workshop on Printed, Flexible, Fabric Sensors and Systems October 13, 2016.
An affordable and flexible tactile sensor giving a robot gripper the ability to touch @ TAIROS 2014
How does it feel to "touch" something for a robot? ITRI developed a flexible and low cost tactile sensor array. This sensor array can be attached to a robot griper and can generate a pressure...
Tactile Robotics (BRL) - Exploiting sensory symmetry for generalized tactile perception
Contour following, but using training data gathered over 30 degrees and generalized to 360 degrees. Published in: B. Ward-Cherrier, L. Cramphorn, N. Lepora. Exploiting sensor symmetry for...
ECRAN TACTILE ROBOT S6 et ROTOPLAT SERIE 8 de ROBOPAC
Vidéo de démonstration de l'écran tactile tournant sur le ROBOT S6 ( mais aussi sur la banderoleuse à plateau tournant ROTOPLAT) . Réglage de tous les paramètres sur l'écran couleur,...
A Touch Sensor Based on Light Transport
We demonstrate a low-cost, easy to manufacture tactile sensor based on light transport through a polymer.
object handling using slip sensor.
we propose a method for controlling grasping force to resist tangential force applied to the grasped object using a feedback control system with the Center of Pressure (CoP) tactile sensor's...