- Head of project : Éric Anquetil
- ACTIF project partners :
- Project initiator: GIP-FAR (Groupement d’Intérêt Public de Formation de l’Académie de Rennes)
- IRISA laboratory(IntuiDoc team),
- LP3C laboratory (Laboratoire de Psychologie: Cognition, Comportement et Communication)
- LOUSTIC platform
- Rennes academy
- Duration: 48 months
The ACTIF project (Apprentissage et collaboration sur Tablettes, Interactions et Feedback) is funded by the French ministry of education (PIA, BPI), in context of the call for projects e-fran. The goal of ACTIF is to experiment pedagogical methods and tools to foster active and collaborative learning with stylus and touch tablets.
In this context, we focus on geometry learning support on tablet for middle-school children. The goal is to propose an e-learning system to help the autonomy of the child with a personalized course. We have designed IntuiGeo , an Intelligent Tutoring System which allows the child to draw freely geometric figures by simulating the traditional pen and paper approach. IntuiGeo interprets, on the fly, the child’s sketches, allowing for a real-time user interaction, and visual, corrective or guidance feedback interventions, in order to enhance the child’s learning performance.
The interaction mode is stylus-fingers. The child draws therefore with the pen and is able to manipulate with his/her hands virtual tools, that simulate the traditional tools used on the paper support such as the ruler, the compass, the protractor, or the set square.
Our e-learning system is based on the combination of Pattern Recognition techniques and tutoring expertise. IntuiGeo is therefore composed of two Artificial Intelligence engines:
- A 2D recognition engine, which interprets, on the fly, the pupil drawings and transforms them into geometrical objects, rendering a visual feedback. The real-time interpretation is based on a bi-dimensional grammar called CD-CMG (Context Driven Constraints Multiset Grammar;
- A supervision engine, based on three main principles:
- The automatic generation of a construction exercise, based on the teacher solution example;
- Strategy synthesis and planning for exercise resolution: the tutor has to have the necessary knowledge in order to help the pupil;
- Real-time supervision of the pupil resolution strategies: semantic interpretation of the pupil’s actions in order to provide corrective and guidance feedback.
Here is a demonstration video illustrating these concepts in details:
We followed a user-centred design process, in partnership with our colleagues from LP3C and LOUSTIC. Volunteers professors from middle-schools in the region of Brittany allowed us to carry user experiments with their pupils in their classrooms. The experiments compared the pupils performance when using IntuiGeo with a control group using pen and paper. The results showed the positive impact of our tutor as well as the learning transferability between the supports since the pupils who used our tutor were also able to succeed better than the control group when they switched to the pen and paper support for the post-test experiment.
Éric Anquetil (firstname.lastname@example.org)
Full professor at INSA Rennes, IRISA laboratory
Head of IntuiDoc team
Researchers and engineers in the IntuiDoc team, involved in the ACTIF project
- Éric Anquetil (Professor)
- Nathalie Girard (Associate Professor)
- Omar Krichen (PhD student)
- Simon Corbillé (Research Engineer)
- Mickaël Renault (Research Engineer)
- Morgane Carry (Research Engineer)
- O. Krichen, N. Girard, E. Anquetil, M. Renault, “Real-time interpretation of geometric shapes for digital learning”, in Proc. ICPRAI (Int. Conf. on PR & AI), May 2018, Montreal, Canada. pp.31-36.
- Omar Krichen, Nathalie Girard, Eric Anquetil, Simon Corbillé, Mickaël Renault. Real-time interpretation of hand-drawn sketches with extended hierarchical bi-dimensional grammar. The 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), Aug 2018, NIAGARA FALLS, United States. pp.273-278. ⟨hal-01917888⟩
- Omar Krichen, Eric Anquetil, Nathalie Girard, Mickaël Renault. Online analysis of hand-drawn strokes for Geometry learning. Marleah Blom; Nicola Nobile; Ching Y Suen. Frontiers in Pattern Recognition and Artificial Intelligence, 5, World Scientific, pp.129-149, 2019, Language Processing, Pattern Recognition, and Intelligent Systems, 9789811203527. ⟨10.1142/9789811203527_0008⟩. ⟨hal-02162405⟩
- Omar Krichen, Eric Anquetil, Nathalie Girard. IntuiGeo: Interactive tutor for online geometry problems resolution on pen-based tablets. European Conference on Artificial Intelligence (ECAI) 2020, In Press, Aug 2020, Santiago de compostela, Spain, pp. 1842 – 1849. ⟨hal-02544384⟩
- Omar Krichen, Nathalie Girard, Eric Anquetil. Extension of a bi-dimensional grammar for online interpretation of structured documents: application on architecture plans and geometry domains, ICFHR 2020, September 2020, Dortmund, Germany, pp.325 – 330.
Website of global project efran ACTIF
Operation support by French government under the e-FRAN component of the investment program for the future, managed by Caisse des Dépôts