Package Summary

Learning from Demonstration algorithms developed by the RAIL research group at WPI.

Author: Maintained by Russell Toris
License: BSD
Source: git https://github.com/WPI-RAIL/lfd.git (branch: fuerte-devel)

About

Robot Learning from Demonstration (LfD) research focuses on algorithms that enable a robot to learn new task policies from demonstrations performed by a human teacher. The lfd ROS stack contains implementations of LfD used and developed by the RAIL research group at WPI. Currently, the classification based Confidence-Based Autonomy (CBA) algorithm is available via the cba package.

For additional details on LfD, please refer to the following publication:

Brenna Argall, Sonia Chernova, Manuela Veloso and Brett Browning. A Survey of Robot Learning from Demonstration. Robotics and Autonomous Systems. Vol. 57, No. 5, pages 469-483, 2009. PDF

Installation

To install the lfd stack, you can choose to either install from source, or from the Ubuntu package:

Source

To install from source, execute the following:

```
   1 cd /path/to/your/ros/stacks
   2 git clone https://github.com/WPI-RAIL/lfd.git
   3 roscd lfd
   4 rosdep install lfd
   5 rosmake lfd
```

Ubuntu Package

To install the Ubuntu package, execute the following:

```
sudo apt-get install ros-fuerte-lfd
```

Startup

Packages may contain test nodes which can be launched with their respective .launch files. Additional information on how to run each algorithm is discussed in their respective package wiki pages. Tutorials and example uses of these algorithms will be arriving shortly.

Support

Please send bug reports to the GitHub Issue Tracker. Feel free to contact me at any point with questions and comments.

Russell Toris
- rctoris@wpi.edu
- Academic Website