Project description
Keeping humans in the loop when interacting with robots
Advances in computer science and mechanical and electronics engineering and science have resulted in robotics and automation forever changing the workplace. Growing interaction with artificial intelligence can also place humans in the out-of-the-loop (OOTL) phenomenon that makes it difficult to predict and prevent failures. The EU-funded TeAMH-Robot project will address this issue. It will develop efficient human-robot interaction in order to guard against the OOTL phenomenon when interacting with robots. It will explore how humans can ‘stay in the loop’ when mistakes occur and how to ensure real-time coordination. The findings will promote the exploitation of robots in everyday life.
Objective
In the near future, the advent of robots will change the role that artificial agents play in our life, as the interaction with them will not be limited to specialized and well-structured work environments. When interacting with artificial agents, humans often occur into the Out of The Loop phenomenon (OOTL), that is a difficulty to predict and prevent failures, probably due to a lack of transparency in artificial agents actions. The overarching aim of TeAMH-Robot is to develop a model of Human-Robot Interaction (HRI) that will prevent the OOTL phenomenon when interacting with robots. To this end, TeAMH-Robot will use a novel approach to develop efficient HRI that combines cognitive neuroscience methods with real-time interactive tasks with a humanoid robot. Firstly, TeAMH-Robot will aim to understand how temporal adaptation and anticipation mechanisms allow humans to “stay in the loop” when mistakes occur. Then, TeAMH-Robot will use this knowledge to develop a human-inspired module for humanoid robots that ensure real-time coordination. Finally, TeAMH-Robot will test the efficiency of human-inspired behaviour in reducing the impact of the OOTL phenomenon. The outgoing phase will be hosted by the Western Sydney University (Australia), where the ER will (i) identify and (ii) model temporal adaptation and anticipation mechanisms that allow humans to predict, prevent and recover mistakes. The return phase will be hosted by the Italian Institute of Technology (Italy), where the ER will (iii) develop a module for humanoid robots that ensure real-time coordination and (iv) test its efficiency in reducing the OOTL by means of the acquired neurocognitive methods. TeAMH-Robot will increase ER’s expertise on social cognitive mechanisms and allow her to start her independency. Moreover, the fellowship will enable the ER to build an international and interdisciplinary network. The results of TeAMH-Robot have the potential to promote the exploitation of robots in everyday life.
Fields of science
Not validated
Not validated
Programme(s)
Funding Scheme
MSCA-IF - Marie Skłodowska-Curie Individual Fellowships (IF)Coordinator
16163 Genova
Italy