MYWAI ports VILMA to Arduino AI boards
Developed under the European ARISE I-GENIUS research initiative alongside Centro Ricerche FIAT and the University of Genoa, MYWAI's VILMA (Visual Imitation Learning for Manipulation Activities) toolkit enables robotic manipulators to acquire kitting and pick-and-place tasks by watching a single human demonstration. The end-to-end pipeline extracts 3D hand landmarks via MediaPipe, tracks objects with YOLOv8, and models motion trajectories using Dynamic Movement Primitives (DMPs) that adapt dynamically to new object coordinates. The toolkit has now been ported to edge hardware, running vision inference and motion adaptation directly on Qualcomm-powered Arduino UNO Q and VENTUNO Q boards interfaced with ROS 2 and robotic arms like the Fairino FR10.
Bringing one-shot imitation learning to low-power microcontroller-class developer boards democratizes advanced robotics programming, though dynamic occlusion and edge-case handling will remain challenging in real-world production environments.
- –Edge-native efficiency: Running quantized YOLOv8 models and DMP adaptation on Arduino boards eliminates the need for expensive dedicated compute workstations on industrial assembly lines.
- –Drastic setup reduction: Extracting kinematics directly from RGB-D video bypasses tedious manual waypoint programming and extensive reinforcement learning cycles.
- –Practical modularity: Splitting high-level edge perception from low-latency ROS 2 robotic command nodes allows flexible integration with diverse robotic manipulators.
DISCOVERED
1h ago
2026-09-15
PUBLISHED
1h ago
2026-09-15
RELEVANCE
AUTHOR
velitesgear