Pioneer P3-AT mobile robot (rightmost photos: config-1 at ISR/IST)
MSc dissertation proposal 2007/2008
Visual
Control of a Unicycle Type Robot
Introduction:
"Although a few of the robots of tomorrow may resemble the anthropomorphic
devices seen in Star Wars, most will look nothing like the humanoid C-3PO. In
fact, as mobile peripheral devices become more and more common, it may be
increasingly difficult to say exactly what a robot is. Because the new machines
will be so specialized and ubiquitous--and look so little like the two-legged
automatons of science fiction--we probably will not even call them robots. But
as these devices become affordable to consumers, they could have just as
profound an impact on the way we work, communicate, learn and entertain
ourselves as the PC has had over the past 30 years."
Excerpt of A Robot in Every Home, Bill Gates,
ScientificAmerican.com, January 2007.
Future robots will be more than mere tools: they will be quasi-team
members whose tasks have to be integrated with those of humans (or other
robots). In order for this to happen, the robots should be coordinating their
behaviours with the requirements and expectations of human team members
[HRI2007]. In this work we consider behaviours where mobile-robots follow
humans or other robots (therefore making chained systems). Particular
attention is given to the sensorial, control and navigation aspects.
Objectives:
The objectives of this work are twofold: (i)
Visual tracking of a pattern by its colour or shape; (ii) Control of a
unicycle-type robot in order to follow the visually tracked pattern. At the end
is expected to demonstrate chaining capabilities by a mobile robot equipped
with a vision sensor.
Detailed description:
Controlling the motion of a mobile robot is still a very active
research-and-development topic mainly because the large variety of applications
and the available locomotion methods and sensors. In this work-proposal the
robots are of the very common unicycle-type, i.e. carts or cars moving in a
two-dimensional world having two parallel driven wheels, one mounted on each
side of their centre, and one or two offset castors to maintain balance. These
vehicles allow simultaneous arbitrary rotation and translation being only
constrained in the sideways motion (the sideways motion cannot be
instantaneous). The main sensors used are computer vision and odometry.
More specifically, the work-proposal consists of controlling one
unicycle robot to follow a visually-tracked person or other robot. The visual-tracking
is simplified to tracking colours, shapes or distinctive features - some of these
tools are already available e.g. in vision toolboxes as [OpenCV].
The control can be of two types: maintaining a distance or maintaining a
pose relative to the target. These two purposes depend on the output of the
visual tracking, which provides in some cases distances and in other ones
poses.
The work is therefore organized in the following main steps:
1) visual tracking of patterns based on colours
and/or shapes
2) controller design for a unicycle type robot,
in order to follow a target at a constant distance, and imitate the target's
pose (if available from the visual tracking)
3) develop a cable-less joystick combining the
visual tracking done onboard a unicycle type robot and the controller;
demonstration of the cable-less joystick on a mobile-robots simulation
environment and/or on a real robot
References:
[HRI2007] - 2nd ACM/IEEE International Conference on Human-Robot
Interaction, http://hri2007.org/
[ISR-galery] Some images of unicycle type
robots at ISR: see labmate, scouts, pioneers, ... in "Mini galeria
de fotografias de projectos
@ IST/ISR", http://users.isr.ist.utl.pt/~jag/infoforum/isr_galeria/
[VISP] Visual servoing videos, http://www.irisa.fr/lagadic/visp/video.html
[OpenCV] Open Computer Vision Library, http://sourceforge.net/projects/opencv/
[Aguiar] "Position Tracking for a
Nonlinear Underactuated Hovercraft: Controller Design
and Experimental Results", A. Pedro Aguiar, L. Cremean, and João P. Hespanha, in Proc. of CDC’03 – 42nd IEEE Conference on
Decision and Control, Maui, Hawaii, Dec. 2003
[GWSV00] Vision-based Navigation and Environmental Representations with
an Omnidirectional Camera, José Gaspar, Niall Winters, José Santos-Victor, IEEE Transaction on Robotics and Automation, Vol 16, number 6, December 2000
Expected results:
At the end of the work the students will have enriched their knowledge
in:
* Computer vision
* Control of unicycle type vehicles
Examples of expected demonstrations in simulated and/or real
environments:
* remotely controlling the unicycle-type robot
by moving one 3D object which is tracked visually by the robot
* making a robotic trailer by mounting the 3D tracked object on another
mobile robot, i.e. chaining two robots using a visual link
Observations:
--
More MSc dissertation
proposals on Computer and Robot Vision in:
http://omni.isr.ist.utl.pt/~jag