Human collaborative RRT for UAV mission path planning

An unmanned aerial vehicle (UAV), commonly known as a drone, is an aircraft without a human pilot on board. They are predominantly deployed for military applications, but also used in a small but growing number of civil applications, such as firefighting and nonmilitary security work, such as surveillance of pipelines. Most of the current and future Unmanned Aerial Vehicle (UAV) missions will be carried out in dynamic and complex environments, which in turn will increase the work load. In order to distribute this load Human collaboration will be required. One very interesting problem and area of research is how efficiently human can collaborate with automated systems and it would be interesting to see how single human operator can supervise multiple UAV's. Computationally, real time planning and replanning can be a very complicated and burdensome task, particularly in an environment with high density of obstacles. And the future urban application are envisioned to be very complex and will have high density obstacles environment. Recent work has proposed the use of a randomized algorithm known as the Rapidly exploring Random Tree (RRT) algorithm for path planning. This algorithm is capable of finding a feasible solutions quickly and efficiently, however it is unclear and would be interesting to see how well a human operator will be able to collaborate with such a randomized algorithm, particularly due to the unpredictable nature of the generated paths by the algorithm. This thesis presents the idea of human collaboration with Rapidly exploring Random Tree (RRT) algorithm.