In this paper, a novel motion learning method is introduced: Fast Marching Learning (FML). While other learning methods are focused on optimising probabilistic functions or fitting dynamical systems, the proposed method consists on the modification of the Fast Marching Square (FM2) path planning algorithm. Concretely, FM2 consists of expanding a wave through the environment with a velocity directly proportional to the distance to the closest obstacle. FML modifies these velocities in order to generalise the taught motions and reproduce them. The result is a deterministic, asymptotically globally stable learning method free of spurious attractors and unpredictable behaviours. Along the paper, detailed analysis of the method, its properties and parameters are carried out. Comparison against a state-of-the-art method and experiments with real data is also included. ; This work is supported by the Spanish Ministry of Science and Innovation under the projects DPI2010-17772 and CSD2009-00067. ; Publicado
Fast Marching-based globally stable motion learning
2017-05-01
AR/0000018878
Article (Journal)
Electronic Resource
English
DDC: | 629 |
Application of the fast marching method for outdoor motion planning in robotics
BASE | 2013
|Fast Marching Methods in path and motion planning: improvements and high-level applications
BASE | 2015
|Robust Skeletonization using the Fast Marching Method
British Library Conference Proceedings | 2005
|