ARCOL is a project funded by the French National Agency for Research (ANR) and coordinated by Baptiste Caramiaux, CNRS research scientist at ISIR, Sorbonne Université, in Paris.

The project began in early 2020. The project started on the idea to investigate interactive machine learning techniques to assist human learning in complex motor skills such as music performance or rehabilitation. While we are acquiring and improving a wide range of motor skills throughout our lifetime, the mechanisms at play in this acquisition are complex and not yet fully understood, but there is a consensus that practice is fundamental to skill learning. For instance, a novice musician would spend hours practicing her instrument in order to play music pieces, or to play with other musicians. However, practice design is challenging as it relies mostly on heuristics, tacit knowledge and varies across learners and along the learning development. Designing good practice sessions is all the more important for beginners who do not have the expertise to select efficient practice routines and to understand what makes a good or a bad practice schedule. In the ARCOL project one objective is to design machine learning strategies able to learn novice individual-specific practice design in order to support the acquisition of motor skills.

The COVID pandemic, which hit the world between 2020 and 2022, put the project on hold and led its members to rethink some of the objectives. Some solutionist ideas to solve the problem of technology-enhanced motor learning were challenged. Other more global issues, especially those related to the link between technology and society, emerged and became increasingly important to the team. In particular, we reflected on our practice as a researcher in relation to our object of study. There are scientific intentions in the technological approach to learning assistance that are driven by a techno-centric and progressive culture. This approach can lead to fundamental scientific results, as the project tries to show, but it also seems important to us to make this technological culture explicit. This means highlighting our positionality, as a researcher, towards our object of study, such as our subjectivity, the context of investigation and the time at which this investigation is conducted. From this, we try to develop a methodology that is more inclusive from the point of view of the different actors in the project. In summary, a second objective of the project is to study technological cultures, and in particular machine learning which is heavily emphasised in the project, and to explore methods that are more explicit about the underlying cultures of the stakeholders in the research process.

The project is supported by the ANR and CNRS, and conducted at ISIR (Insititute for intellgience systems and robotics) at Sorbonne Université.