Many of the applications that have been proposed for future small unmanned aerial vehicles (UAVs) are at low altitude in areas with many obstacles. A vital component for successful navigation in such environments is a path planner that can find collision free paths for the UAV.
Two popular path planning algorithms are the probabilistic roadmap algorithm (PRM) and the rapidly-exploring random tree algorithm (RRT).
Adaptations of these algorithms to an unmanned autonomous helicopter are presented in this thesis, together with a number of extensions for handling constraints at different stages of the planning process.
The result of this work is twofold:
First, the described planners and extensions have been implemented and integrated into the software architecture of a UAV. A number of flight tests with these algorithms have been performed on a physical helicopter and the results from some of them are presented in this thesis.
Second, an empirical study has been conducted, comparing the performance of the different algorithms and extensions in this planning domain. It is shown that with the environment known in advance, the PRM algorithm generally performs better than the RRT algorithm due to its precompiled roadmaps, but that the latter is also usable as long as the environment is not too complex. The study also shows that simple geometric constraints can be added in the runtime phase of the PRM algorithm, without a big impact on performance. It is also shown that postponing the motion constraints to the runtime phase can improve the performance of the planner in some cases.
The emerging area of intelligent unmanned aerial vehicle (UAV) research has shown rapid development in recent years and offers a great number of research challenges for artificial intelligence. For both military and civil applications, there is a desire to develop more sophisticated UAV platforms where the emphasis is placed on development of intelligent capabilities. Imagine a mission scenario where a UAV is supplied with a 3D model of a region containing buildings and road structures and is instructed to fly to an arbitrary number of building structures and collect video streams of each of the building's respective facades. In this article, we describe a fully operational UAV platform which can achieve such missions autonomously. We focus on the path planner integrated with the platform which can generate collision free paths autonomously during such missions. Both probabilistic roadmap-based (PRM) and rapidly exploring random trees-based (RRT) algorithms have been used with the platform. The PRM-based path planner has been tested together with the UAV platform in an urban environment used for UAV experimentation.
The emerging area of intelligent unmanned aerialvehicle (UAV) research has shown rapid development in recentyears and offers a great number of research challenges for artificialintelligence. For both military and civil applications, thereis a desire to develop more sophisticated UAV platforms wherethe emphasis is placed on development of intelligent capabilities.Imagine a mission scenario where a UAV is supplied with a 3Dmodel of a region containing buildings and road structures andis instructed to fly to an arbitrary number of building structuresand collect video streams of each of the building’s respectivefacades. In this article, we describe a fully operational UAVplatform which can achieve such missions autonomously. Wefocus on the path planner integrated with the platform which cangenerate collision free paths autonomously during such missions.It is based on the use of probabilistic roadmaps. The path plannerhas been tested together with the UAV platform in an urbanenvironment used for UAV experimentation.