Related Concepts
Definition
Learning-from-Observation is the framework to generate robot’s (or other agent’s) movement to achieve a target task with less user’s programming effort. In this framework, a user just demonstrates the target task and a robot learns the method to reproduce the target task from the observation.
Background
One goal in robotics and artificial intelligence (AI) fields is to achieve any target tasks by a robot with less user’s programming efforts. To achieve this purpose, Learning-from-Observation (LFO) framework attracts an attention. In this framework, a user just demonstrates the target task and a robot learns the method to reproduce the target task from the observation. The user is not required to have special skills on robotics. Note that an agent that the user teaches is not limited to a robot.
In a scientific point of view, it is...
References
Oztop E, Kawato M, Arbib M (2006) Mirror neurons and imitation: a computationally guided review. Neural Netw 19(3):254–271
Bates T, Ramirez-Amaro K, Inamura T, Cheng G (2017) On-line simultaneous learning and recognition of everyday activities from virtual reality performances. In: Proceedings of the International Conference on Intelligent Robots and Systems, pp 3510–3515
Kato H, Billinghurst M (1999) Marker tracking and HMD calibration for a video-based augmented reality conferencing system. In: Proceedings of the 2nd IEEE and ACM International Workshop on Augmented Reality (IWAR 99), pp 85–94
Kuniyoshi Y (2015) Learning from examples: imitation learning and emerging cognition. In: Cheng G (ed) Humanoid robotics and neuroscience: science, engineering and society, chapter 8. CRC Press/Taylor & Francis. https://pubmed.ncbi.nlm.nih.gov/26065071/
Ramirez-Amaro K, Beetz M, Cheng G (2017) Transferring skills to humanoid robots by extracting semantic representations from observations of human activities. Artif Intell 247:95–118
Elbanhawi M, Simic M (2014) Sampling-based robot motion planning: a review. IEEE Access 2:56–77
Ikeuchi K, Suehiro T (1994) Toward an assembly plan from observation. I. Task recognition with polyhedral objects. IEEE Trans Robot Autom 10(3):368–385
Kang SB, Ikeuchi K (Feb. 1997) Toward automatic robot instruction from perception – mapping human grasps to manipulator grasps. IEEE Trans Robot Autom 13(1):81–95
Takamatsu J, Morita T, Ogawara K, Kimura H, Ikeuchi K (2006) Representation for knot-tying tasks. IEEE Trans Robot 22(1):65–78
Ikeuchi K, Ma Z, Yan Z, Kudoh S, Nakamura M (2018) Describing upper-body motions based on labanotation for learning-from-observation robots. Int J Comput Vis 126(12):1415–1429
Hussein A, Gaber MM, Elyan E, Jayne C (2017) Imitation learning: a survey of learning methods. ACM Comput Surv 50(2):1995–2014
Billard A, Calinon S, Dillmann R, Schaal S (2008) Survey: robot programming by demonstration. In: Handbook of robotics, vol 59(BOOK_CHAP). https://dl.acm.org/doi/10.1016/j.robot.2008.10.024
Argall BD, Chernova S, Veloso M, Browning B (2009) A survey of robot learning from demonstration. Robot Auton Syst 57(5):469–483
Ijspeert AJ, Nakanishi J, Hoffmann H, Pastor P, Schaal S (2013) Dynamical movement primitives: learning attractor models for motor behaviors. Neural Comput 25(2):328–373
Calinon S, D’halluin F, Caldwell DG, Billard AG (2009) Handling of multiple constraints and motion alternatives in a robot programming by demonstration framework. In: 2009 9th IEEE-RAS International Conference on Humanoid Robots, pp 582–588
Schulman J, Ho J, Lee C, Abbeel P (2016) Learning from demonstrations through the use of non-rigid registration. Springer International Publishing, Cham, pp 339–354
Ye G, Alterovitz R (2017) Demonstration-guided motion planning. Springer International Publishing, pp 291–307
Kramberger A, Piltaver R, Nemec B, Gams M, Ude A (2016) Learning of assembly constraints by demonstration and active exploration. Ind Robot 43(5): 524–534
Author information
Authors and Affiliations
Corresponding author
Section Editor information
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this entry
Cite this entry
Takamatsu, J. (2021). Learning-from-Observation. In: Computer Vision. Springer, Cham. https://doi.org/10.1007/978-3-030-03243-2_869-1
Download citation
DOI: https://doi.org/10.1007/978-3-030-03243-2_869-1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-03243-2
Online ISBN: 978-3-030-03243-2
eBook Packages: Springer Reference Computer SciencesReference Module Computer Science and Engineering