Project Artemis

Visual Navigation for Flying Robots



Our MAVs    |    Technical     |    People    |    Gallery    |    Publications    |    Contact Us    

Follow me on GitHub


Technical

All of the Artemis MAVs follow the same basic, distributed  system architecture. There is a high-level onboard computer, and a low-level embedded flight controller, typically a PX4 autopilot board, or similar derivative. The middleware of choice on the high-level companion computer is ROS (Robot Operating System) and the PX4 Middleware on the deeply embedded controller.


Hardware

Computing

We have tested several onboard computing solutions, with varying levels of compute capability.

Vision


While working on our very early protoypes, we had adopted the PointGrey Firefly MV USB2.0 cameras, and continue to use them till date. Available fairly easily, these cameras are relatively inexpensive (~ $200) and very easy to integrate. They are also directly synchronizable in hardware with a precision GPIO pulse, something of utomost importance when working with visual-inertial applications.

We also evalua

Flight Control


Software

State Estimation

Visual Navigation

Mapping

Terrain Analysis

Obstacle Avoidance

Trajectory Control