2012 12th IEEE-RAS International Conference on Humanoid Robots (Humanoids 2012) 2012
DOI: 10.1109/humanoids.2012.6651508
|View full text |Cite
|
Sign up to set email alerts
|

Face classification using touch with a humanoid robot hand

Abstract: Abstract-This paper presents an experiment in which the iCub humanoid robot learns to recognize faces through proprioceptive information. We take inspiration in the way blind people recognize people's faces, i.e. through tactile exploration of the person's face. The iCub robot's tactile sensors are used to provide compliance in the hand motion so as to smoothly scan the facial features. The displacement of the fingers, as the robot explores the face, is used to build a model of the face using Hidden Markov Mod… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2014
2014
2021
2021

Publication Types

Select...
3
2

Relationship

2
3

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 16 publications
0
3
0
Order By: Relevance
“…However, the robustness and applicability of these strategies have only been evaluated on simple shaped objects (a cylinder and a sphere) in simulation. Other related works, such as our previous work [7], show that tactile exploration using an anthropomorphic robot hand can successfully recognize several human-like faces. In [8], a probabilistic approach is proposed to represent datapoints, which are collected from predefined grasps using a Schunk hand with tactile sensors at high frame rates.…”
Section: Introductionmentioning
confidence: 87%
“…However, the robustness and applicability of these strategies have only been evaluated on simple shaped objects (a cylinder and a sphere) in simulation. Other related works, such as our previous work [7], show that tactile exploration using an anthropomorphic robot hand can successfully recognize several human-like faces. In [8], a probabilistic approach is proposed to represent datapoints, which are collected from predefined grasps using a Schunk hand with tactile sensors at high frame rates.…”
Section: Introductionmentioning
confidence: 87%
“…This added capability can also be beneficial in other applications, such as for use in robotic arms and humanoid robots. Tactile sensors play an important role in accomplishing various functions of humanoid robots, such as object manipulation (Yussof et al, 2007), robotic hands (Romano et al, 2011;Ataollahi et al, 2010;Schmitz et al, 2011), decoding and transferring tactile data collected in the fingerprint area of humanoid robots (Dahiya et al, 2009(Dahiya et al, , 2010 and classification of human facial features (Sommer and Billard, 2012). Also, communication between a robot and a human can be performed for different purposes, such as in the nursing context (Chen et al, 2014), socializing (Yohanan and MacLean, 2008) and affective touching (Yohanan and MacLean, 2008).…”
Section: Introductionmentioning
confidence: 99%
“…In our previous work [12], we tackled tactile exploration of human-like faces for classification, using fingertip tactile sensors and statistical encoding of the face models for robustness to proprioceptive noise. We also developed an algorithm for bi-manual haptic exploration of objects [13], using multiple phalanxes per finger, covered with tactile sensors, for the 3-d reconstruction of the objects' shapes.…”
Section: Tactile Explorationmentioning
confidence: 99%