Abstract
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 (FM\(^2\)) path planning algorithm. Concretely, FM\(^2\) 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 is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Argall BD, Chernova S, Veloso M, Browning B (2009) A survey of robot learning from demonstration. Robot Autonom Syst 57(31):469–483
Branicky M, Knepper R, Kuffner J (2008) Path and trajectory diversity: theory and algorithms. In: IEEE intl. conf. on robotics and automation, pp 1359–1364
Calinon S, Sardellitti I, Caldwell DG (2010) Learning-based control strategy for safe human-robot interaction exploiting task and robot redundancies. In: IEEE/RSJ int. conf. on intelligent robots and systems, pp 249–254
Garrido S, Moreno L, Abderrahim M, Blanco D (2009) FM2: a real-time sensor-based feedback controller for mobile robots. Int J Robot Autom 24(1):3169–3192
Garrido S, Moreno L, Blanco D, Martin F (2006) Log of the inverse of the distance transform and fast marching applied to path planning. In: IEEE/RSJ international conference on intelligent robots and systems, pp 2882–2887
Gómez JV (2012) Advanced applications of the fast marching square planning method. Master’s thesis, Carlos III University
Gómez JV, Álvarez D, Garrido S, Moreno L (2012) Kinesthetic teaching via fast marching square. In: IEEE/RSJ international conference on intelligent robots and systems, pp 1305–1310
Gómez JV, Álvarez D, Garrido S, Moreno L (2015) Fast methods for eikonal equations: an experimental survey. arXiv:1506.03771
Hersch M, Guenter F, Calinon S, Billard A (2008) Dynamical system modulation for robot learning via kinesthetic demonstrations. IEEE Trans Rob 24(6):1463–1467
Jetchev N, Toussant M (2010) Trajectory prediction in cluttered voxel environments. In: IEEE int. conf. on robotics and automation, pp 2523–2528
Jetchev N, Toussant M (2013) Fast motion planning from experience: trajectory prediction for speeding up movement generation. Auton Robots 34(1–2):111–127
Khansari-Zadeh SM, Billard A (2010) Imitation learning of globally stable non-linear point-to-point robot motions using nonlinear programming. In: IEEE/RSJ intl. conf. on intelligent robots and systems, pp 2676–2683
Khansari-Zadeh SM, Billard A (2011) Learning stable nonlinear dynamical systems with gaussian mixture models. IEEE Trans Robot 27(5):943–957
Khansari-Zadeh SM, Billard A (2012) A dynamical system approach to realtime obstacle avoidance. Auton Robots 32(4):433–454
Kober J, Bagnell JA, Peters J (2013) Reinforcement learning in robotics: a survey. Int J Rob Res 32(11):1238–1274
Lee AD, Ott C (2010) Incremental motion primitive learning by physical coaching using impedance control. In: IEEE/RSJ int. conf. on intelligent robots and systems, pp 4133–4140
Lemme A, Neumann K, Reinhart R, Steil J (2014) Neural learning of vector fields for encoding stable dynamical systems. Neurocomputing 141:3–14
Li FF, Fergus R, Perona P (2006) One-shot learning of object categories. IEEE Trans Pattern Anal Mach Intell 28(4):594–611
Martin S, Wright S, Sheppard J (2008) Offline and online evolutionary bi-directional RRT algorithms for efficient replanning in dynamic environments. In: IEEE int. conf. on automation science and engineering, pp 1131–1136
Mülling K, Kober J, Kroemer O, Peters J (2013) Learning to select and generalize striking movements in robot table tennis. Int J Rob Res 32(31):263–279
Nemec B, Zorko M, Zlajpah L (2010) Learning of a ball-in-a-cup playing robot. In: Int. workshop on robotics in Alpe-Adria-Danube region, pp 297–301
Ning K, Tamosiunaite M, Worgotter F (2012) A novel trajectory generation method for robot control. J Intell Robot Syst 68(2):165–184
Pastor P, Hoffmann H, Asfour T, Schaal S (2009) Learning and generalization of motor skills by learning from demonstration. In: IEEE intl. conf. on robotics and automation, pp 1293–1298
Petres C, Pailhas Y, Patron P, Petillot Y, Evans J, Lane D (2007) Planning for autonomous underwater vehicles. IEEE Trans Rob 32(2):331–341
Peyré G, Cohen LD (2008) Heuristically driven front propagation for fast geodesic extraction. Int J Comput Vis Biomech 1(1):55–67
Rabin J, Peyré G, Cohen LD (2010) Geodesic shape retrieval via optimal mass transport. In: European conf. on comp. vis., pp 771–784
Rasmussen C, Williams C (2006) Gaussian processes for machine learning, 3rd edn. Springer, New York
Schaal S, Atkenson C, Vijayakumar S (2002) Scalable locally weighted statistical techniques for real time robot learning. Appl Intell 17(1):49–60
Schaal S, Peters J, Nakanishi J, Ijspeert A (2004) Learning movement primitives. In: Intl. symp. rob. res
Sethian JA (1996) A fast marching levelset method for monotonically advancing fronts. Proc Natl Acad Sci 93(4):1591–1595
Slotine J, Li W (1991) Applied nonlinear control. Prentice-Hall, Englewood Cliffs
Valero-Gómez A, Gómez JV, Garrido S, Moreno L (2013) The path to efficiency: fast marching method for safer, more efficient mobile robot trajectories. IEEE Robot Autom Mag 20(4)
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Communicated by V. Loia.
This work is supported by the Spanish Ministry of Science and Innovation under the projects DPI2010-17772 and CSD2009-00067.
Rights and permissions
About this article
Cite this article
Gomez, J.V., Alvarez, D., Garrido, S. et al. Fast Marching-based globally stable motion learning. Soft Comput 21, 2785–2798 (2017). https://doi.org/10.1007/s00500-015-1981-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00500-015-1981-1