A decentralized probabilistic framework for the path planning of autonomous vehicles
| Authors: | Gu Da-Wei, University of Leicester, United Kingdom
Kamal Waseem, University of Leicester, United Kingdom
Postlethwaite Ian, University of Leicester, United Kingdom |
|---|
| Topic: | 7.5 Intelligent Autonomous Vehicles |
|---|
| Session: | Vehicle Motion Planning |
|---|
| Keywords: | UAV, Autonomy, Path Planning, Local Minimisation, ProbabilisticApproach |
|---|
Abstract
A three dimensional probabilistic approach for the path planningof uninhabited air vehicles (UAVs) is presented. The algorithm canbe used in real time because of a low computational load in spiteof the fact that it finds a path in three dimensions. The pathsare locally optimal and are feasible for the UAV to follow bykeeping the turn angle within a certain maximum limit. For thispurpose, a relation has been derived that transforms the maximumturn angle into a maximum search angle. The UAVs are preventedfrom flying at very low altitudes to avoid crashing into theground. Because of limited fuel, a compromise is made between riskand fuel consumption by limiting the height and search angle.
