Unmanned aircraft systems use a variety of techniques to plan collision-free flight paths given a map of obstacles and no-fly zones. However, maps are not perfect and obstacles may change over time or be detected during flight, which may invalidate paths that the aircraft is already following. Thus, dynamic in-flight replanning is required. Numerous strategies can be used for replanning, where the time requirements and the plan quality associated with each strategy depend on the environment around the original flight path. This paper investigates the use of machine learning techniques, in particular support vector machines, to choose the best possible replanning strategy depending on the amount of time available. The system has been implemented, integrated and tested in hardware-in-the-loop simulation with a Yamaha RMAX helicopter platform. When an unmanned aircraft detects an obstacle ahead, there is generally little time available for replanning. Reactive behaviors for collision avoidance suffer from problems with local minima. Additionally, they solve the problem locally without a global overview of the environment, which may lead to highly suboptimal paths. Instead, the authors can identify a number of replanning strategies that vary in time requirements as well as in the resulting plan quality. Much can then be gained by choosing the highest quality strategy that does not exceed the given time window. The authors have applied machine learning techniques to this problem, with promising results in empirical testing: In each test environment, flight times could be improved up to 25% compared to the use of a fixed replanning strategy, resulting in times close to the best achievable with the available planning algorithms.
Choosing path replanning strategies for unmanned aircraft systems
Die Auswahl von Streckenneuplanungsstrategien für unbemannte Flugzeugsysteme
2010
8 Seiten, 10 Bilder, 1 Tabelle, 23 Quellen
Conference paper
English
Trajectory Planning and Replanning Strategies Applied to a Quadrotor Unmanned Aerial Vehicle
Online Contents | 2012
|