Toward understanding natural language directions
Authors:
Open Access
- 1 March 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21672121,p. 259-266
Abstract
Speaking using unconstrained natural language is an intuitive and flexible way for humans to interact with robots. Understanding this kind of linguistic input is challenging because diverse words and phrases must be mapped into structures that the robot can understand, and elements in those structures must be grounded in an uncertain environment. We present a system that follows natural language directions by extracting a sequence of spatial description clauses from the linguistic input and then infers the most probable path through the environment given only information about the environmental geometry and detected visible objects. We use a probabilistic graphical model that factors into three key components. The first component grounds landmark phrases such as ¿the computers¿ in the perceptual frame of the robot by exploiting co-occurrence statistics from a database of tagged images such as Flickr. Second, a spatial reasoning component judges how well spatial relations such as ¿past the computers¿ describe a path. Finally, verb phrases such as ¿turn right¿ are modeled according to the amount of change in orientation in the path. Our system follows 60% of the directions in our corpus to within 15 meters of the true destination, significantly outperforming other approaches.Keywords
This publication has 13 references indexed in Scilit:
- Grounding spatial prepositions for video search2009
- Applying Computational Models of Spatial Prepositions to Visually Situated DialogComputational Linguistics, 2009
- What to do and how to do it: Translating natural language directives into temporal and dynamic logic representation for goal management and action execution2009
- Utilizing object-object and object-scene context when planning to find things2009
- Topological mapping using spectral clustering and classification2007
- Improved Techniques for Grid Mapping With Rao-Blackwellized Particle FiltersIEEE Transactions on Robotics, 2007
- A location representation for generating descriptive walking directions2005
- Spatial Language for Human–Robot DialogsIEEE Transactions on Systems, Man and Cybernetics, Part C (Applications and Reviews), 2004
- “What” and “where” in spatial language and spatial cognitionBehavioral and Brain Sciences, 1993
- Error bounds for convolutional codes and an asymptotically optimum decoding algorithmIEEE Transactions on Information Theory, 1967