As the aging population continues to grow, service robots are emerging as valuable tools to promote active and healthy aging. Previous work at the WE-COBOT Lab developed a motor-cognitive game for the TIAGo robot (PAL Robotics), combining physical and memory training through embodied interaction [Pozzi, Gandolla, Braghin, Robot-Mediated Gesture-Based Memory Game for Older Adult Psychophysical Stimulation. IEEE IROS 2025]. In the game, the robot mimes letters with its arm, and the user must recognize and imitate them, promoting motor and mental engagement. Pilot tests with older adults confirmed the potential of this approach but also revealed practical limitations in gesture tracking and difficulty in maintaining engagement due to the fixed level of challenge.
The student will extend and improve this system by:
- Redesigning the gesture tracking module to replace ArUCo marker-based recognition with a markerless vision system, based on RGB or RGB-D data and neural network–based pose estimation.
- Implementing an adaptive hinting mechanism using a local Large Language Model (LLM) to provide intelligent, context-aware suggestions during gameplay.
- Exploring adaptive difficulty adjustment, allowing the robot to autonomously tailor the task (e.g., recognition-only or memory-only modes) based on user performance and engagement.
The developed solution will be tested with participants from different age groups to evaluate usability, engagement, and system robustness.
Contacts Luca Pozzi | Marta Gandolla