Here are some ideas and readings for class projects. Your best bet is
to pick a topic which explores in greater detail some topics covered in class (hence involes additional reading) and implement the chosen algorithm and demostrate it in action in simulation.
It is preferable if you use one of the existing simulators or Matlab depending
on the project. If you choose to implement one of the algorithms for
processing sensory data (sonar or vision), then you should acquire the
data using the mobile robot platforms in the lab.
If you are Java savy Teambots simulator (multi-agent simulator) is
also fine. http://www.teambots.org/. It would not be sufficient to merely run one of their demos. You should implement something with a clear contribution of your own.
Up to one page project description is due Friday November 6th (via
e-mail or in person).You can also schedule a meeting with me to
discuss the project, if you are not sure what to do, you can also
choose one of the suggested projects. The requirement of the project
is that you will have to study, read some advanced material (either
papers or advanced chapters from the books) not covered in the
class. I will provide additional links of such materials shortly.
Recognition, Localization and Mapping (to be covered in the class)
Vision Based Localization using scale invariant features (rea datal) reading
Recognizing groceries using visual reading
Particle Filter for Localization using Range data (simulation) reading1 , reading2
Implementation of scan matching using real and testing on real robot (real data) reading
Inverse Kinematics
Inverse Kinematics Survey paper
Path planning, Sensor Based Planning, Sampling based planning
Pick two different path planning algorithms on a grid. (Best first
search, A*), try them on different environments, generalize to higher dimension or
multiple robots. Path planning algorithms have to be demonstrated on some nontrivial
environments.
Sensor Based Motion Planning: The
Hierarchical Generalized Voronoi Graph , WAFR 96., Incremental
Construction of Generalized Voronoi Graph, ICRA 95
Sensor based path planning in the dynamically changing or partially
unknown environments. A. Stentz D*
- Dynamic A* algorithm (.pdf) and its extensions. Experiment with different versions
of the cost function (time traveled, danger), multiple robots
Steven LaValle; Read Chap 7., Chap 8. of the book. Look at the extensions of RRT's to moving objects and/or feedback motion strategies.
Multi-robot problems, Coverage problems, tasks, architectures
Combine reactive and path planning strategies to achieve the
best possible coverage of a particular area.
Design decentralized conrol strategies for formation flight
Design reactive behaviors based on potential field strategies to acomplish
set cooperative behaviors for mutiple mobile robot agents. Experiment with different
sensing and communication strategies. Experiment with different arbitration strategies.
(see paper by Craig Reynolds on
Steering Behaviors for Autonomous characters.)