View source for Robot learning by demonstration

=== Principle ===
The main principle of robot LfD-PbD is that end-users can teach robots new tasks without programming. Consider, for example, a domestic service robot that an owner wishes to have prepare orange juice for breakfast, see <figref>Orange-Task-Teaching.gif</figref>. The task itself may involve multiple subtasks, such as juicing the orange, throwing the rest of the orange in the trash and pouring the liquid in a cup. Furthermore, each time this task is performed, the robot will need to contend with changes such as displacement of the items' locations.

In a traditional programming scenario, a human programmer would have to reason in advance and code a robot controller that is capable of responding to any situation the robot may face, no matter how unlikely. This process may involve breaking down the task into 100s of different steps, and thoroughly testing each step. If errors or new circumstances arise after the robot is deployed, the entire costly process may need to be repeated, and the robot recalled or taken out of service while it is fixed.

In contrast, LfD - PbD allows the end-user to 'program' the robot simply by showing it how to perform the task - no coding required. Then, when failures occur, the end-user needs only to provide more demonstrations, rather than calling for professional help.
LfD - PbD hence seeks to endow robots with the ability to learn what it means to perform a task by '''generalizing''' from observing several demonstrations, see <figref>Orange-Task-Teaching.gif</figref>. LfD - PbD is NOT a ''record and replay'' technique. Learning and generalizing is core to  LfD - PbD.
{|
|[[Image:Orange-Task-Teaching.gif|thumb|600px|left|The teacher performs several demonstrations of the same task, changing the location of each item in between to allow the robot to generalize correctly. From observing these changes the robot can infer that the relative positions of the objects matter, but that their absolute positions do not.]]  [[Image:Orange-Task-Reproduction.gif|thumb|600px|right|After learning, the robot successfully reproduces the task even when all objects are in novel positions.]]
|}