Approaching the Symbol Grounding Problem with Probabilistic Graphical Models
Authors:
Open Access
- 1 December 2011
- journal article
- Published by Wiley in AI Magazine
- Vol. 32 (4) , 64-76
Abstract
In order for robots to engage in dialogue with human teammates, they must have the ability to identify correspondences between elements of language and aspects of the external world. A solution to this symbol‐grounding problem (Harnad, 1990) would enable a robot to interpret commands such as “Drive over to receiving and pick up the tire pallet.” This article describes several of our results that use probabilistic inference to address the symbol‐grounding problem. Our approach is to develop models that factor according to the linguistic structure of a command. We first describe an early result, a generative model that factors according to the sequential structure of language, and then discuss our new framework, generalized grounding graphs (G3). The G3 framework dynamically instantiates a probabilistic graphical model for a natural language input, enabling a mapping between words in language and concrete objects, places, paths, and events in the external world. We report on corpus‐based experiments in which the robot is able to learn and use word meanings in three real‐world tasks: indoor navigation, spatial language video retrieval, and mobile manipulation.Keywords
Funding Information
- Army Research Laboratory
- Office of Naval Research (MURI N00014‐07‐1‐0749)
This publication has 13 references indexed in Scilit:
- Grounding spatial language for video search2010
- Utilizing object-object and object-scene context when planning to find things2009
- Translating Structured English to Robot ControllersAdvanced Robotics, 2008
- Scalable training ofL1-regularized log-linear models2007
- The Human Speechome ProjectLecture Notes in Computer Science, 2006
- Semiotic schemas: A framework for grounding language in action and perceptionArtificial Intelligence, 2005
- A statistical semantic parser that integrates syntax and semantics2005
- Conversational robots2003
- Factor graphs and the sum-product algorithmIEEE Transactions on Information Theory, 2001
- The symbol grounding problemPhysica D: Nonlinear Phenomena, 1990