Brigham Young University

bouncerarcheryΤεχνίτη Νοημοσύνη και Ρομποτική

14 Νοε 2013 (πριν από 3 χρόνια και 10 μήνες)

95 εμφανίσεις

J. Alan Atherton

Michael Goodrich

Brigham Young University

Department of Computer Science

April 9, 2009


Funded in part by Idaho National Laboratory

And Army Research Laboratory

1


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


2


What is a remote manipulator?


Applications


USAR


EOD


Planetary Exploration


3


Remotely operating a robot is difficult


“Soda straw”


Maintaining situation awareness


Time delay


Mental workload


Why is this a

problem?


Collisions


Slow


Stressful

Foster
-
Miller Talon

4

All images adopted from

Yanco
, H. A.; Drury, J. L. &
Scholtz
, J.

“Beyond usability evaluation: analysis of human
-
robot interaction at a major robotics competition”

Hum.
-
Comput
. Interact., L. Erlbaum Associates Inc.,
2004
, 19
, 117
-
149

5


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


6

Idaho National Laboratory

UMass Lowell

Bruemmer
, D. J. et al.

“Shared understanding for collaborative
control.”

IEEE Transactions on Systems, Man and
Cybernetics, Part A,
2005
, 35
, 494
-
504

Yanco
, H. A. et al.

“Analysis of Human
-
Robot Interaction for
Urban Search and Rescue.”

Proceedings of the IEEE International Workshop
on Safety, Security and Rescue Robotics,
2006


7

INL / BYU AV Interface

Ferland

et al.
-

Sherbrooke

C. W. Nielsen, M. A. Goodrich, and B. Ricks.


“Ecological
Interfaces for Improving Mobile Robot
Teleoperation
.”


IEEE Transactions on Robotics and
Automation
.


Vol

23, No 5, pp. 927
-
941, October 2007.



Ferland
, F.;
Pomerleau
, F.;
Dinh
, C. T. L. & Michaud, F.

“Egocentric and exocentric
teleoperation

interface
using real
-
time, 3D video projection.”

Proceedings of the 4th ACM/IEEE international
conference on Human robot interaction, ACM,
2009
,
37
-
44

8

NASA
Viz

Nguyen, L. A.;
Bualat
, M.; Edwards, L. J.;
Flueckiger
, L.;
Neveu
, C.;
Schwehr
, K. ..; Wagner, M. D. &
Zbinden
, E.

“Virtual Reality Interfaces for visualization and control of
remote vehicles”

Autonomous Robots,
2001
, 11
, 59
-
68

9

Kelly, A.; Anderson, D.;
Capstick
, E.; Herman, H. &
Rander
, P.


Photogeometric

Sensing for Mobile Robot
Control and
Visualisation

Tasks”

Proceedings of the AISB Symposium on New
Frontiers in Human
-
Robot Interaction,
2009


CMU Robotics Institute


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


10


Requirements


Ecological


Increase situation awareness


Manage workload


Existing Interfaces


Lack depth information


No manipulation support


Not designed for real
-
time operation


11



12


Real
-
time

remote
manipulation

13


Robot


Build from kit, modify


Player driver


Motion planning for arm


Swiss Ranger driver


Communication


Integrate with INL’s system


Network data transfer


User Interface


OpenGL display


Experiment automation



14

Robot
Controller

User
Interface


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


15

Variant

1

Variant

2

Variant 3

Variant 4

Variant 5

Variant 6

3D +
Video

End
Effector

Video

3D

Joint

Robot
Control

Visualization


Task: collect yellow blocks


30 participants


Between
-
subject
comparison

16


Reduce memorization
effects


Minimize damage to arm


Quick change

17

18


19


Joint control


View
-
dependent end
effector

control

20

21


Robot reaches
for point


User moves
point with
joystick


Point
movement
depends on
view
orientation

3D +
Vid
.

End eff.

3D +
Vid
.

Joint

3D

End eff.

3D

Joint

Video

End eff.

Video

Joint

22

3D +
Vid
.

End eff.

3D +
Vid
.

Joint

3D

End eff.

3D

Joint

Video

End eff.

Video

Joint

3D +
Vid
.

End eff.

3D +
Vid
.

Joint

3D

End eff.

3D

Joint

Video

End eff.

Video

Joint

23

Collisions with
posts, box, table

Collisions with
block in final
adjustments



Interface

Measure

3D

+
Vid
.
End eff.

3D +
Vid
.

Joint

3D

End

eff.

3D

Joint

Video

End eff.

Video

Joint

Time to completion

6th

1st

World collisions

3rd

6th

1st

3rd

6th

Block collisions

1st

6th

6th

Preference

1st

1st

6th

1st

Subjective

mental workload

1st

6th

2nd

3rd

24


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


25


Problems


Alignment


Time lag


Cluttered 3D scan model


Changes


Stereo camera exterior orientation


Interactive robot arm calibration


Simple Quickening


Scan Pruning



26


Interactive stereo
camera
calibration




Live robot arm
calibration



27

28


29


30


Background


Related Work


Ecological Interface


User Study


Interface Changes from Study


Conclusions and Future Work


31


3D visualization supports SA


Video is faster


3D + video is a good tradeoff


3D + video might reduce workload

32

33


Head tracking


Ecological
camera video


Haptics