Whether evolutionary robotics (ER) controllers evolve in simulation or on real robots, realworld performance is the true test of an evolved controller. Controllers must overcome the noise inherent in real environments to operate robots efficiently and safely. To prevent a poorly performing controller from damaging a vehicle—susceptible vehicles include statically unstable walking robots, flying...

Swarm control is an open problem. We are taking steps for systematic flight control of large numbers of UAVs. In this paper, we present our design and implementation of UAV group control in a fully implemented simulated UAV environment. We explore issues of limited user intervention, novel agent personality, and multi-theater load balancing.

Unmanned Aerial Vehicles (UAVs) equipped with multiple sensors publish data in unpredictable manner using considerable bandwidth and missing spatial reference. Additionally, the available approaches only provide proprietary access to the data. Integrating sensors from UAVs into a synchronized data stream is required for publishing the transmitted data on the Web. This article describes a softwa...

iii

This paper details the application of an adaptive neural network based limit detection and avoidance algorithm for envelope protection on the autonomous Yamaha R-Max unmanned helicopter test bed. Software-in-the-loop and flight test results are presented. The envelope protection system is implemented as a mid-level controller component into the unmanned helicopter software infrastructure, calle...

Unmanned aerial vehicles (UAVs) are a critical component of many military operations. Over the last few decades, the evolution of UAVs has given rise to increasingly smaller aircraft. Along with the development of smaller UAVs, termed mini UAVs, has come issues involving the endurance of the aircraft. Endurance in mini UAVs is problematic because of the limited size of the fuel systems that can...

The least squares method has been applied to estimate parameters in an aerodynamic model of a simulated aircraft, using data that can be expected to available from sensors on an Unmanned Aerial Vehicle. A combination of two non-linear state observers have been implemented to estimate wind data such as angle of attack, sideslip and dynamic pressure. Simulations have confirmed that the observers ...

Visual tracking of small unmanned aerial vehicles (UAVs) on a smart phone can be quite a daunting task. In this paper an image processing algorithm is outlined in order to be able to assist a user in visually tracking small UAVs. Due to the small nature of the target, simple template matching or optical flow provided to be too process intensive and unreliable for real time tracking. To improve ...

In many military and civilian applications, Unmanned Aerial Vehicles (UAVs) provide an indispensable platform for gathering information about the situation on the ground. In particular, they have the potential to revolutionize the way in which information is collected, fused and disseminated. These advantages are greatly enhanced if swarms of multiple UAVs are used, since this enables the colle...

The rise of Unmanned Aerial Vehicles and their increasing use in the cinema industry calls for the creation of dedicated tools. Though there is a range of techniques to automatically control drones for a variety of applications, none have considered the problem of producing cinematographic camera motion in real-time for shooting purposes. In this paper we present our approach to UAV navigation ...