Title: LowCost Localization for Educational Robotic Platforms via an External FixedPosition Camera
1Low-Cost Localization for Educational Robotic
Platforms via an External Fixed-Position Camera
NSF Grant OCI-0636235 NSF Grant SCI-0537370
- Drew Housten (dth29_at_drexel.edu)
- Dr. William Regli (regli_at_drexel.edu)
2Pre-College Educational Robotics
- Robotics is an excellent tool to teach AI,
Engineering, Math, and Science - Currently, educational system sophistication
heavily depends on hardware cost - LEGO NXT (Fairly Cheap, Limited)
- AIBO (Expensive, More Sophisticated)
- But, cost of the solution matters in pre-college
education! - Research does not follow the same trends
- Example DARPA Urban Challenge was mostly a
software problem
3Pre-College Educational Robotics
- Hardware complexity of educational robotics is
currently sufficient - However, Software and System complexity of
educational robotics is limited - This problem can be addressed by building
software tools to bridge the gap - Software tools can be free to educators
4Why Localization?
- Chose Localization as a starting point
- Currently many AI educational projects are
limited because the robot does not know where it
is - Maze Following
- Navigation
- Searching
- Etc.
5Problem of Localization
- Current solutions in research
- Odometry
- Global Positioning Systems (GPS)
- LIDAR
- Sonar or Infrared Arrays
- Contact Sensors
- Fuducials or Landmarks
- Cameras
- Etc.
- Current solutions do not work well for education
- Expensive
- Complicated to use
- Does not work well in typical educational
environments
6CamLoc (Camera Localization)
- Goals of CamLoc
- Inexpensive solution to localization
- Simple to use
- Requires no hardware modifications
- Simplistic solution to support teaching the
principles to students - Decimeter-level accuracy in localization in an
indoor environment
7Necessary Hardware
Webcam (50-150)
Total Cost w/o Computer 400
iRobot Roomba (200)
SparkFun Electronics RooTooth (100)
Computer (500 - 2500)
8Technical Approach Fusion of Odometry Visual
Tracking
- Topological Mapping
- Record Robots start position in the image frame
- Make an action (point turn, drive)
- Record odometry distance and heading traveled
- Record Robots end position in image frame
- Add an edge to the Topological Map
- Vertices are the image frame positions
- Localization
- Search through the Topological map to find a path
between the initial position and the current
position - Calculate the current position by simulating the
actions to travel that path
9Results from 3 Runs
Square Circuit 39 Actions 12.765 Meters
Cloverleaf Circuit 50 Actions 10.885 Meters
Pseudo-Random 84 Actions 27.489 Meters
Mean Positional Error
10Future Work
- Enhancements and Improvements to Approach
- Build a more complete toolkit to assist robotic
educators - Use the solution in a classroom setting
- Make the toolkit available for download
athttp//gicl.cs.drexel.edu/wiki/LearningRoomba
11Questions?
?
12Backup
13Odometry vs. Topological Map
14Vision Tracking Interface
15Trial 1 Square Circuit
16Trial 2 Cloverleaf Circuit
17Trial 3 Pseudo-Random Path
18Approach
- Goals
- Localization to decimeter-level accuracy
- Low-cost Solution
- Easy to configure / setup / use
- Elements of Solution
- Odometry
- Topological Map
- Image Tracking