Lego RobotsGMU Grand Challenge?Trinity CompetitionFlockBotsClub | ||
Changes: Recent All
History Edit Upload | ||
Pioneers
Projects
Getting Started Guide
We really need a guide to help people get started working with the Pioneers. Needed topics include:
- Installing Player/Stage
- Linux
- OS X
- Windows
- Using the Pioneer laptops
- Logging in
- Where to save projects
- Paths to commonly needed include files and libraries
- Hello World of Robots
- Point out necessary elements in main *.cc file
- How to build
- How to run in simulator
- how to run on actual robot
- How to use GMU Player library
Convert existing work to Player 2.0
There's a new API for Player. We'll need to re-write some of our code to get it working with this new API.
Monte Carlo Localization
One of the challenges in robotics is answering the question, "where am I?" With Monte Carlo localization (also known as a particle filter), a map of the environment is known ahead of time. The robot may, or may not know where it starts.
- Implement MCL, like what was developed for Trinity last year
- Add KLD sampling
- Kidnapped robot problem
Occupancy Grids
Occupancy Grids are one method of map building. Discretize the world -- carve it up into small squares, and mark each square as occupied, or unoccupied. More specifically, assign a probability to each square, to indicate the probability that it is occupied.
- Implement wall follower
- hey, we need some exploration algorithm...
- Implement occupancy grids algorithm
- Should work very well in Player/Stage
- Should fail in the real world
SLAM
The localization problem becomes much harder when you don't have a map ahead of time. In this case, the robot must perform simultaneous localization and mapping (SLAM).
- Implement Grid-based FastSLAM
- Combination of MCL and Occupancy grids