Conversational Agents
FAIR 1 Archive Notice
This page describes research activities and results from the FAIR 2019-2023 program period.
The content is retained for reference purposes and is no longer actively maintained. Information on this page, including research outputs, team members, contact details, collaborations and links, may be incomplete or outdated.
No direct successor use case has been defined within the FAIR 2024-2028 program. Please consult the current FAIR use cases for related research activities.
Use Case Description
Within this use case several demonstrators were built that showcase different aspects in multiple domains of conversational human-like interfaces.
Goal of the use case
With this use case we provide a conversational interface for an industry set-up, demonstrated as an implementation with a social robot. The chatbot is trained on conversational data for a specific assembly process. The assembly specific information is stored in a knowledge base, which enables easy switching between different assemblies, without the need to retrain the chatbot. The output of the system is template-based with insertable slots, combined with ChatGPT generated answers for slightly off-topic questions of the operator, thereby showcasing a mix of highly controlled output with flexible answers if needed.
Results-Artefacts
A social robot as an interface for conversational help in an industry set-up