Project Moab

Back Download

Moab, a ball-balancing robot, leverages computer vision and various control methods to balance objects. Users can select classical control systems such as PID loops, trained AI control systems, or manual control via an integrated joystick. An undermounted camera tracks objects placed on the clear balance plate, which is then dynamically oriented by 3 servo-arm linkages. The robot's reactions and 'skill' is dependent on the control method, which users can test and evaluate against their own trained models. The hardware kit pairs with a web-based machine teaching service from Microsoft called Project Bonsai. Bonsai allows users to create and train their own AI models or 'brains' to deploy onto the robot. Once deployed, users can observe the performance of their custom ‘brain’ in physical space, interact with and test it against other control methods. Additional materials are accessible to the user including open-source code, tutorials and 3D part files via QR codes on the packaging and documentation. Moab was designed from the ground up to inspire engineers to think beyond object balancing and solve their own novel use cases via intelligent control systems. 

Red Dot Award: Design Concept | Ready to Launch | Artificial Intelligence

Red Dot: Best of the Best

By starting the video, you agree that data, e.g. your IP address, will be sent to Vimeo.

Others interested too