Improving Grounded Natural Language Understanding through Human-Robot Dialog
This work addresses the challenge of enabling robots to adapt dynamically to new language and perceptual concepts in human environments, though it appears incremental as it builds on existing methods for dialog-based learning.
The paper tackles the problem of domain-specific engineering in natural language understanding for robotics by developing an end-to-end pipeline that translates commands to robot actions and uses clarification dialogs to improve language parsing and concept grounding, with evaluation in a virtual setting and real-world transfer to a physical robot.
Natural language understanding for robotics can require substantial domain- and platform-specific engineering. For example, for mobile robots to pick-and-place objects in an environment to satisfy human commands, we can specify the language humans use to issue such commands, and connect concept words like red can to physical object properties. One way to alleviate this engineering for a new domain is to enable robots in human environments to adapt dynamically---continually learning new language constructions and perceptual concepts. In this work, we present an end-to-end pipeline for translating natural language commands to discrete robot actions, and use clarification dialogs to jointly improve language parsing and concept grounding. We train and evaluate this agent in a virtual setting on Amazon Mechanical Turk, and we transfer the learned agent to a physical robot platform to demonstrate it in the real world.