The ability to understand natural-language instructions is critical to building intelligent agents that interact with humans. In this project we look at building a system that learns to transform natural-language navigation instructions into executable formal plans. Given no prior linguistic knowledge, the system learns by only observing how humans follow navigation instructions.
More information, and an example run of the system can be found at this link:
http://www.cs.utexas.edu/users/ml/clamp/navigation/