Augmenting Knowledge through Statistical, Goal-oriented Human-Robot Dialog
This work addresses the challenge of enabling robots to learn and enhance their knowledge base through human-robot dialog, which is incremental as it builds on existing dialog systems.
The paper tackles the problem of robots improving their language capabilities from dialog experiences by developing a dialog agent that uses a semantic parser and probabilistic dialog manager to interpret commands and ask clarification questions, resulting in better efficiency and accuracy compared to baseline learning agents.
Some robots can interact with humans using natural language, and identify service requests through human-robot dialog. However, few robots are able to improve their language capabilities from this experience. In this paper, we develop a dialog agent for robots that is able to interpret user commands using a semantic parser, while asking clarification questions using a probabilistic dialog manager. This dialog agent is able to augment its knowledge base and improve its language capabilities by learning from dialog experiences, e.g., adding new entities and learning new ways of referring to existing entities. We have extensively evaluated our dialog system in simulation as well as with human participants through MTurk and real-robot platforms. We demonstrate that our dialog agent performs better in efficiency and accuracy in comparison to baseline learning agents. Demo video can be found at https://youtu.be/DFB3jbHBqYE