Physical Analytics (previous) - UAV Technology


 Development of a Real-Time Drone Competition and Learning System

We are developing a drone-competition system based on the game of ping pong. The goal of the research is to integrate various hardware and software technologies such as computer vision, energy-efficient computation, object tracking, motion dynamics, game intelligence etc. In this early version prototype we have utilized the IRIS drone system, Raspberry Pis for on-board computation, Microsoft Kinect for positioning system (synthetic GPS) and ping pong tracking algorithms.  One of the goal of this research is for the drone to carry out its applications regardless of the connectivity. This requirement poses significant constraints on the system design, which includes trading off between computational efficiency in order to be low-power (hardware and software design), payload, agility of the drone etc.

Please refer to our technical publication here and a demo video here.

Development team:  Wang Zhou (currently at Northwestern University), Dhruv Nair (currently at Columbia University), Theodore van Kessel, Oki Gunawan, Dhruv Nair, Hendrik F. Hamann, Pradip Bose, Sharathchandra Pankanti (all IBM) and others.

 

  




News and Events

Deployment of IBM LMT at the Metropolitan Museum of Art in NYC