Pontificia Universidad Católica de Chile Pontificia Universidad Católica de Chile
Rojas M., Sáez C., Baier J., Nussbaum M., Guerrero O., Rodríguez M. F. (2022)

Using Automated Planning to Provide Feedback during Collaborative Problem-Solving

Revista : International Journal of Artificial Intelligence in Education
Tipo de publicación : ISI Ir a publicación


Collaborative Problem-Solving Skills (CPS) have become increasingly important. Research into the development of CPS is still scarce, but there are several approaches that may be useful for its development. Specifically, providing feedback in collaborative contexts is key. In this paper, we study and develop a feedback system that uses Automated Planning techniques to promote communication among students. Our system is designed to be used in a real-world educational setting, considering the underpinning theory of when and how to give feedback. The system’s frontend is a video game, which presents tasks that can only be solved when students collaborate. In the backend, the system computes the solution to the task in a partial-order plan using an automated planning engine. While it monitors the plan and provides feedback to students. We describe an experimental study involving 42 students aged between 10 and 13, in which we explore the effectiveness of the feedback that was given. We show that the feedback allowed the students to perform better in the game, improve their communication, and develop their collaborative problem-solving skills. We also describe a novel approach to monitoring multi-agent partial-order plans, specifically designed for plans with so-called independent chains, that is more efficient than previous approaches and therefore requires fewer computational resources in the classroom. This paper contributes to the literature in two ways. First, we propose a novel monitoring algorithm for partial-order plans that is better suited to educational settings. Second, we show that feedback extracted from a plan can promote reflection about collaborative problem-solving during a multi-agent activity.