Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain

13 years 3 months ago

Download www.ri.cmu.edu

Rough terrain autonomous navigation continues to pose a challenge to the robotics community. Robust navigation by a mobile robot depends not only on the individual performance of perception and planning systems, but on how well these systems are coupled. When traversing complex unstructured terrain, this coupling (in the form of a cost function) has a large impact on robot behavior and performance, necessitating a robust design. This paper explores the application of Learning from Demonstration to this task for the Crusher autonomous navigation platform. Using expert examples of desired navigation behavior, mappings from both online and oﬄine perceptual data to planning costs are learned. Challenges in adapting existing techniques to complex online planning systems and imperfect demonstration are addressed, along with additional practical considerations. The beneﬁts to autonomous performance of this approach are examined, as well as the decrease in necessary designer eﬀort. Expe...

David Silver, J. Andrew Bagnell, Anthony Stentz

Real-time Traffic