Author: Klaas Dijkstra

Smart Sailing with Twirre

The Smart Sailing Twirre project aims to add automatic navigation to boats.

Twirre is a new architecture for mini-UAV platforms designed for autonomous flight in both GPS-enabled and GPS-deprived applications. The architecture consists of low-cost hardware and software components. High-level control software enables autonomous operation. Exchanging or upgrading hardware components is straightforward and the architecture is an excellent starting point for building low-cost autonomous systems for a variety of applications. Experiments with an implementation of the architecture are in development, and preliminary results demonstrate accurate navigation.

For Smart Sailing, the Twirre architecture will be utilized and adapted for automatic navigation of boats.

Students: Mechanical Engineering, Electrical Engineering, Information Science.

Deep Learning

Deep Learning is one of the most important machine learning paradigms currently in use. This is currently the most researched field within artificial intelligence.

Big companies like Google, Facebook and Microsoft use this technique for data mining, classification and prediction. We currently research the application areas of this exiting new technology. In previous efforts with student we found great potential in using these technologies on practical machine vision applications.

You’ll be working on a project with deep learning on our special “deep learning machine” with multiple GPUs. For more information on the used software you can take a look at the caffe.berkeleyvision.org and NVIDIA DIGITS.

Students: 1 or 2