• Robotic manipulation
• task planning
• motion planning
• ROS.

The objective of this thesis is to implement two new actions, to a preceding work
"Flexibly configuring task and motion planning problems for mobile manipulators" [Saoji, Rosell], which are: Stack and Unstack. With the extension of the number of actions
that the TiaGo PAL robot can perform, it is given more robustness and versatility.
This report faces two problems, first, the symbolic level (Task planning) and second
the geometric level (Motion Planning).
The methodology uses the Fast Forward task planner for task planning. Motion
planning is done using The Kautham Project, which is equipped with the Open
Motion Planning Library suite of sampling-based motion planners. The Robotic
Operating System interfaces using services that are used to access the two levels.
These task and motion planning services are used by a client program and an XML
configuration file that defines the linkage between symbolic actions and geometric
values, to compute the sequence of feasible robot motions that allow to successfully
execute a manipulation task.
This report also includes a scenario in which the Tiago robot is employed as a helper
to an elderly person to give him his medicines.