A survey of robot learning from demonstration

Wepresent a comprehensive survey of robot Learning fromDemonstration (LfD), a technique that develops policies from example state to action mappings. We introduce the LfD design choices in terms of demonstrator, problem space, policy derivation and performance, and contribute the foundations for a structure in which to categorize LfD research. Specifically, we analyze and categorize the multiple ways inwhich examples are gathered, ranging from teleoperation to imitation, aswell as the various techniques for policy derivation, including matching functions, dynamics models and plans. To conclude we discuss LfD limitations and related promising areas for future research. © 2008 Elsevier B.V. All rights reserved.