From Traditional AI Explanations To Human-Centred Design In XAI For Manufacturing Applications

Articles, News

STAR EU project

STAR is a joint effort of 15 European partners towards designing new technologies to enable the deployment of standard-based secure, safe, reliable and trusted human centric AI systems in manufacturing environment. STAR aims to research, develop, validate and make available to the community leading-edge AI technologies including explainable AI, active learning systems, simulated reality systems, human-centred digital twins, advanced reinforcement learning techniques and cyber-defense mechanisms, thus becoming a catalyst for the deployment of advanced AI systems in the manufacturing shop-floor.
STAR is funded under the EU Horizon 2020 programme.

Human-Centred Design In XAI For Manufacturing Applications

As the manufacturing industry continues to integrate AI and ML to improve operations, it is becoming increasingly important to design human-centred XAI for manufacturing applications. The traditional XAI approach prioritises technical aspects and transparency, but the human-centred approach focuses on what, when, and how to explain AI decisions to human end-users, by iteratively involving them in the development process.

The human-centred approach in the development process

The human-centred approach involves techniques such as interviews, hypothetical scenarios, focus groups, and questionnaires to uncover what information is understandable and useful to humans. By involving users in the development process, we can design AI systems that prioritise transparency, interpretability, and user-centredness. This approach prioritizes the user’s needs and preferences and ensures that the AI system is transparent and interpretable to them. Additionally, the use of scenarios early in the system development process to identify user needs for explanations, which can then serve as a basis for further development of explanations. By using this approach, manufacturers can ensure that AI systems are designed to meet the needs of human workers, resulting in safer, more efficient, and more effective operations.

The human-centred approach in the development process in collaborative robotics

Another area where human-centred design XAI is important in manufacturing is collaborative robotics or cobots. Cobots are designed to work alongside humans, often in close proximity. Human-centred XAI design considers not only the technical aspects of cobot design but also the social and cultural factors that influence human-robot interactions. This approach helps ensure that cobots are used in a way that is safe, efficient, and effective for humans.

Human-centred approaches to XAI and STAR ICT-38

The STAR ICT-38-2020 project aims at leveraging human-centred approaches to XAI, focusing on uncovering what, when, and how to explain AI decisions to human end-users, by involving them in the development process. By prioritising transparency, interpretability, and user-centredness, human-centred XAI can help to improve safety, reduce the risk of errors and accidents, and increase the efficiency of operations in the manufacturing industry.

This article has been extracted and freely adapted fro Star EU Project website (22 February 2023)

Authors: Georgios Makridis, Panagiotis Koulouris, Dimitris DardanisSpyros TheodoropoulosDimosthenis Kyriazis / UNIVERSITY OF PIRAEUS RESEARCH CENTER