Assessing student individual performance within PBL teams: findings from the implementation of a new mechanism

This paper reports on the experience of the implementation of a new mechanism to assess individual student contribution within project work, where students work in teams to solve a large-scale open-ended interdisciplinary project. The study takes place at the University of Minho, with first year engineering students, enrolled in the Industrial Management and Engineering (Integrated Masters) degree. The aim of this paper is to describe the main principles and procedures underlying the assessment mechanism created and also provide some feedback from its first implementation, based on the students, lecturers and tutors perceptions. For data collection, a survey was sent to all course lecturers and tutors involved in the assessment process. Students also contributed with suggestions, both on a workshop held at the end of the project and also by answering a survey on the overall satisfaction with PBL experience. Findings show a positive level of acceptance of the new mechanism by the students and also by the lecturers and tutors. The study identified the need to clarify the criteria used by the lecturers and the exact role of the tutor, as well as the need for further improvement of its features and procedures. Some recommendations are also issued regarding technical aspects related to some of the steps of the procedures, as well as the need for greater support on the adjustment and final setting of the individual grades.

Off-line simulation inspires insight: a neurodynamics approach to efficient robot task learning

There is currently an increasing demand for robots able to acquire the sequential organization of tasks from social learning interactions with ordinary people. Interactive learning-by-demonstration and communication is a promising research topic in current robotics research. However, the efficient acquisition of generalized task representations that allow the robot to adapt to different users and contexts is a major challenge. In this paper, we present a dynamic neural field (DNF) model that is inspired by the hypothesis that the nervous system uses the off-line re-activation of initial memory traces to incrementally incorporate new information into structured knowledge. To achieve this, the model combines fast activation-based learning to robustly represent sequential information from single task demonstrations with slower, weight-based learning during internal simulations to establish longer-term associations between neural populations representing individual subtasks. The efficiency of the learning process is tested in an assembly paradigm in which the humanoid robot ARoS learns to construct a toy vehicle from its parts. User demonstrations with different serial orders together with the correction of initial prediction errors allow the robot to acquire generalized task knowledge about possible serial orders and the longer term dependencies between subgoals in very few social learning interactions. This success is shown in a joint action scenario in which ARoS uses the newly acquired assembly plan to construct the toy together with a human partner.