Abstract
Trajectory planning of manipulator is a popular research area. To allow the manipulator to have the knowledge of demonstrated skills and the intelligence to infer trajectories for new tasks, a new kind of imitation learning framework is proposed in this paper. Our framework builds up a Functional Primitives Library which is composed by three different types of elements: Event Primitive, Object Primitive and Relation Primitive. Event Primitive consists of action features extracted by Dynamic Movement Primitive and the functions of the actions which describe the state changes of operated objects monitoring by visual sensor. Object Primitive describes the objects involved in tasks. Relation Primitive is used to represent the relationship between objects. Besides, a state-movement reasoning algorithm based on dichotomy is raised to realize the inference of the complete movement sequence for a new task.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Argall, B.D., Sonia, C., Manuela, V., Brett, B.: A survey of robot learning from demonstration. Robot. Auton. Syst. 57(5), 469–483 (2008)
Bandera, J.P., Molina-Tanco, L., Rodriguez, J.A., et al.: Architecture for a robot learning by imitation system. In: IEEE Mediterranean Electrotechnical Conference (2010)
Daumé, H., Langford, J., Marcu, D.: Search-based structured prediction. Mach. Learn. 75(3), 297–325 (2009)
Ross, S., Bagnell, D.: Efficient reductions for imitation learning. In: Proceedings of the Thirtieth International Conference on Artificial Intelligence and Statistics, pp. 661–668 (2010)
Chella, A., Dindo, H., Infantino, I.: A cognitive framework for imitation learning. Robot. Auton. Syst. 54(5), 403–408 (2006)
Forte, D., Gams, A., Morimoto, J., et al.: On-line motion synthesis and adaptation using a trajectory database. Robot. Auton. Syst. 60(10), 1327–1339 (2012)
Park, G., Konno, A.: Imitation learning framework based on principal component analysis. Adv. Robot. 29(9), 639–656 (2015)
Ahmadzadeh, S.R., Paikan, A., Mastrogiovanni, F., et al.: Learning symbolic representations of actions from human demonstrations. In: IEEE International Conference on Robotics and Automation ICRA, pp. 3801–3808 (2015)
Niekum, S., Osentoski, S., Konidaris, G., et al.: Learning grounded finite-state representations from unstructured demonstrations. Int. J. Robot. Res. 34(2), 131–157 (2015)
Cho, N.J., Sang, H.L., Kim, J.B., et al.: Learning, improving, and generalizing motor skills for the peg-in-hole tasks based on imitation learning and self-learning. Appl. Sci. 10(8), 2719 (2020)
Lioutikov, R., Maeda, G., Veiga, F., et al.: Learning attribute grammars for movement primitive sequencing. Int. J. Robot. Res. 39(1), 21–38 (2020)
Rozo, L., Guo, M., Kupcsik, A.G., et al.: Learning and sequencing of object-centric manipulation skills for industrial tasks. In: IEEE International Conference on Intelligent Robots and Systems (IROS) (2020)
Schaal, S.: Dynamical movement primitives - a framework for motor control in humans and humanoid robotics. In: Kimura, H., Tsuchiya, K., Ishiguro, A., Witte, H. (eds.) Adaptive Motion of Animals and Machines. Springer, Tokyo (2006). https://doi.org/10.1007/4-431-31381-8_23
Redmon, J., Farhadi, A.: YOLOv3: an incremental improvement. ArXiv e-prints (2018)
Acknowledgment
The work was jointly supported by the National Natural Science Foundation of China under Grant 61873006 and Grant 61673053, and in part by National Key Research and Development Project (2018YFC1602704, 2018YFB1702704), Beijing Natural Science Foundation (4212933) and Scientific Research Project of Beijing Educational Committee (KM202110005023).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Xue, A., Li, X., Liu, C. (2022). Functional Primitive Library and Movement Sequence Reasoning Algorithm. In: Sun, F., Hu, D., Wermter, S., Yang, L., Liu, H., Fang, B. (eds) Cognitive Systems and Information Processing. ICCSIP 2021. Communications in Computer and Information Science, vol 1515. Springer, Singapore. https://doi.org/10.1007/978-981-16-9247-5_11
Download citation
DOI: https://doi.org/10.1007/978-981-16-9247-5_11
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-16-9246-8
Online ISBN: 978-981-16-9247-5
eBook Packages: Computer ScienceComputer Science (R0)