Search

Some psychomotor tasks require students to perform a specific sequence of poses and motions. A natural teaching scheme for such tasks is to contrast a student’s execution to a teacher demonstration. However, this requires strategies to match the teacher demonstration of each motion to the student’s attempts and to identify differences between demonstration and attempt. In this paper, we investigate methods to automatically detect student attempts for poses with only a single correct teacher demonstration. We investigate relevance learning, prototype networks, and attention mechanisms to achieve a robust few-shot approach which generalizes across students. In an experiment with one teacher and 27 students performing a sequence of motion elements from the field of fitness and dance, we show that prototype networks combined with an attention mechanism perform best.

Acquisition and internalisation of many fundamental skills rely on repeated authentic practice and teachers providing support during practice. Despite this well accepted norms in skills acquisition, much of our assumptions about learning skills, mostly from a cognitive perspective, remain nebulous. Besides splitting hairs to classify skills acquisition into a paradigm, much of findings of related research from educational science and psychology have struggled to transfer into the domain of skills acquisition. Instead, in this paper, we propose to shift our view of skills acquisition from a cognitive approach to an embodied one with the help of multimodal technologies and provide a use-case which combines deliberate practice framework, embodied cognition principles, and multimodal learning.

Learning psychomotor skills is challenging because motion is fast, relies strongly on subconscious mechanisms, and instruction typically disrupts the activity. As such, learners would profit from mechanisms that can react swiftly, raise subtle mistakes to the conscious level, and do not disrupt the activity. In this paper, we sketch a machine learning-supported approach to provide feedback in two example scenarios: running, and interacting with a robot. For the running case, we provide an evaluation how motions can be compared to highlight deviations between student and expert motion.