Extracting common sense knowledge from text for robot planning
Authors:
- 1 May 2014
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10504729,p. 3749-3756
Abstract
Autonomous robots often require domain knowledge to act intelligently in their environment. This is particularly true for robots that use automated planning techniques, which require symbolic representations of the operating environment and the robot's capabilities. However, the task of specifying domain knowledge by hand is tedious and prone to error. As a result, we aim to automate the process of acquiring general common sense knowledge of objects, relations, and actions, by extracting such information from large amounts of natural language text, written by humans for human readers. We present two methods for knowledge acquisition, requiring only limited human input, which focus on the inference of spatial relations from text. Although our approach is applicable to a range of domains and information, we only consider one type of knowledge here, namely object locations in a kitchen environment. As a proof of concept, we test our approach using an automated planner and show how the addition of common sense knowledge can improve the quality of the generated plans.Keywords
This publication has 15 references indexed in Scilit:
- Grounded spatial symbols for task planning based on experience2013
- Web mining driven object locality knowledge acquisition for efficient robot behavior2012
- Towards a Watson that sees: Language-guided action recognition for robots2012
- Generalizing objects by analyzing language2011
- Toward humanoid manipulation in human-centred environmentsRobotics and Autonomous Systems, 2008
- Developing and analyzing intuitive modes for interactive object modeling2007
- ARMAR-III: An Integrated Humanoid Platform for Sensory-Motor Control2006
- Accurate unlexicalized parsing2003
- Open Mind Common Sense: Knowledge Acquisition from the General Public2002
- WordNetCommunications of the ACM, 1995