Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation

This paper describes a new model for understanding natural language commands given to autonomous systems that perform navigation and mobile manipulation in semi-structured environments. Previous approaches have used models with fixed structure to infer the likelihood of a sequence of actions given the environment and the command. In contrast, our framework, called Generalized Grounding Graphs, dynamically instantiates a probabilistic graphical model for a particular natural language command according to the command's hierarchical and compositional semantic structure. Our system performs inference in the model to successfully find and execute plans corresponding to natural language commands such as "Put the…

• MU
  Multidisciplinary University Research Initiative
• OO
  Office of Naval Research

  Awards: MURI N00014-07-1-0749, N00014
• AR
  Army Research Laboratory

  Awards: W911NF, W911NF-10-2-0016