Towards the interaction in Natural Language with Industrial Production Machines

Description

The EKIN project aims to advance in the development and implementation of the concept of “conversational interfaces” as an interaction mechanism between operators and machines in the production plants of the Basque Country to facilitate and improve the productivity of certain processes.

Objectives

For this, three main objectives have been established that will be undertaken using the most advanced Artificial Intelligence technologies:

• To facilitate the development of natural language interaction interfaces between operators and industrial production machines based on the information contained in technical documentation such as manuals, manufacturing / assembly dossiers and maintenance notes
• To optimize the neural models of speech recognition and synthesis so that they can be embedded in electronic devices in the machines themselves and automatisms to avoid the problems of privacy, security and latency of their deployments in the cloud
• To formalize a terminology and a corpus of expressions of interaction with machines and automatisms in Basque that will serve as a reference to be able to develop conversational interfaces in the sector, also in Basque.

When developing this type of solution, it is necessary to have a corpus that comes from documents from the domain of use, in this case, the industrial environment. Therefore, manuals, dossiers and maintenance notes are required as well as a base of terminology and expressions of human-machine interaction in the reference languages.

Three environments have been defined to be used as use cases for technology development:

• The programming of numerical controls
• The manufacturing and assembly processes
• Industrial maintenance

Once the project is finished, one of them will be chosen to carry out the real implementation and proceed to validate the results before transferring and applying the technology in other industrial plants.

Consortium

Vicomtech, UPV / EHU, Tekniker, Ikor, IMH and UZEI

This project has been funded by SPRI within the framework of the Elkartek Program that supports collaborative research carried out by RVCTI agents in the RIS3 Euskadi strategic areas.