Emotion sensitive robots- A NEW PARADIGM FOR HUMAN-ROBOT INTERACTION

1. EMOTION-SENSITIVE
ROBOTS
A NEW PARADIGM FOR
HUMAN-ROBOT
INTERACTION

2. 2
INDEX
• Introduction
• Physical Responses for Emotion Recognition
• Emotion Detection and Recognition
• Control Architecture
• Communication
• Experiment
• Applications
• Conclusion
• References

3. 3
INTRODUCTION
• A robot which responds to the emotions of
human- emotion sensitive robot.
• Physiologica1 responses of a human are
measured through wearable biofeedback
sensors to detect level of anxiety.
• The robot detects both implicit and explicit
communication from the human to determine
its own behavior.

4. 4
PHYSIOLOGICAL RESPONSES
• Emotions– physiological changes, expressive
behaviors and states of feeling.
• Emotion recognition through Rule based
system and Fuzzy logic, Neural networks .
• Neuro-fuzzy, an adaptive technique used in the
development of emotion recognition.
• Response through EMG, EEG, ANS and
Cardiac activity.

5. 5
PHYSIOLOGICAL RESPONSES
• EMG(electromyography)
• EEG(elctroencephalography)

6. 6
PHYSIOLOGICAL RESPONSES
• ANS(autonomic nervous system) receptor
• Cardiac activity monitor

7. 7
PHYSIOLOGICAL RESPONSES
• Electrodermal activity receptor

8. 8
Emotion Detection and Recognition
• Efforts to identify the generic signatures-
person-stereotype and situation-stereotype.
• Detecting and identifying the emotion of
anxiety.
• Sensory-motor coordination was designed to
elicit emotional responses from subjects.
• Features of physiological response for emotion
recognition.

9. 9
Emotion Detection and Recognition
Table represents features of physiological response for emotion recognition

10. 10
Control Architecture

11. 11
Communication
• IMPLICIT-
When the internal emotions are being used to
communicate.
• EXPLICIT-
When the visible expressions are being used to
communicate

12. 12
Communication
• Class1-
high urgency level situation.
• Class2-
Medium urgency level situation.
• Class3-
low urgency level situation.

13. 13
Communication
Fig. Generating triggers from implicit and explicit communications

14. 14
Communication
Fig. Behavior model in the robot when task is assigned

15. 15
EXPERIMENT
• APPARATUS
 Emotion sensitive robot named ORACLE
 Operator
 Bio-feedback sensor
 Workspace
 Physiological state monitor

16. 16
PROCEDURE

17. 17
• Oracle’s tasks included:
(i) Exploring the workspace
(ii) Avoiding obstacles in the workspace
(iii) Wall following
(iv) Providing environment related information to the human.
(v) Responding to the urgency of the situation in the following manner
a) Class 1 Trigger - Raise an alarm, reach the human in shortest
possible time.
b) Class 2 Trigger - Move to the vicinity of the operator
c) Class 3 Trigger- Initiate speech to query the operator or give
suggestions
PROCEDURE

18. 18
RESULT
Where actual = actual level of anxiety, predicted = predicted level of anxiety, n = total number

19. 19
RESULT

20. 20
RESULT
Figure. Path taken by Oracle through implicit communication

21. 21
APPLICATIONS
 To help a human during –
Search and rescue operations
Fire fighting
Space
Remote planet
Underwater exploration
Warfare
Medical unit

22. 22
CONCLUSION
• Proposed an innovative human-robot interaction
structure wherein the robot was sensitive to the
emotions of the human.
• Achieved computing, psychology, and robotics to
develop a robotic system capable of combining
implicit and explicit channels of
communication from the human.
• Future work would consist of expanding the range of
tasks and contexts to which this framework
can be applied.

23. 23
REFERENCES
• http://en.wikipedia.org/wiki/Electromyography
• http://www.paranormality.com/eda.shtml
• V. Riley, A General Model of Mixed-Initiative
Human-Machine Systems
• Nursebot Project, http://iwww-2.cs.cmu.edui-
nursebot
• http://www.inel.gov%2Fadaptiverobotics
%2Fhumanoidrobotics
%2F&ei=PNZDUJCVFoesrAeX6YGICA&usg=AF
QjCNFFx6BCb4orDfI2kQF1byZyg2erfg&sig2=y3
bk4ugz0em0izszD7UdhA
• www.ai.mit.edu/projects/humanoid-robotics-group/

24. 24
QUIRIES???