Abstract
Dynamical Movement Primitives (DMPs) can equip the robot with humanoid characteristics and make it efficiently complete the task. However, research on obstacle avoidance strategies combined with DMPs is still being explored nowadays. In this paper, we proposed new obstacle avoidance methods based on geometric information under the DMPs framework, in order that the robot can still complete the task in an unstructured environment. We first generalized new trajectories by DMPs after demonstration. Then according to the interference area of a static or a moving obstacle after extracting the geometric information of the obstacle, we quantitatively adjusted the generalized trajectories by adding proper offset at a certain direction. Finally we used proportional-derivative (PD) control to ensure that the modified trajectories converge to the original one and the goal. The methods make the robot successfully avoid the interference of a static or a moving obstacle, and besides, they maintain all the advantages of the DMPs framework, such as fast goal convergence, simple mathematical principles and high imitation similarity. We verified the effectiveness of the methods in two dimensional and three dimensional simulation, and set up the real experiments using a static or a moving obstacle respectively, and finally proved the feasibility and validity of the avoidance methods.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Zhang, T., Zhu, Y., Song, J.: Real-time motion planning for mobile robots by means of artificial potential field method in unknown environment. Ind. Robot. 37, 19 (2010)
Xu, J., Duindam, V., Alterovitz, R., Goldberg, K.: Motion planning for steerable needles in 3D environments with obstacles using rapidly-exploring random trees and backchaining, p. 6
Hussein, A., Gaber, M.M., Elyan, E., Jayne, C.: Imitation learning: a survey of learning methods. ACM Comput. Surv. 50, 35 (2017)
Khansari-Zadeh, S.M., Billard, A.: Learning stable nonlinear dynamical systems with Gaussian mixture models. IEEE Trans. Robot. 27, 15 (2011)
Ti, B.: Human intention understanding from multiple demonstrations and behavior generalization in dynamic movement primitives framework. IEEE Access 4, 9 (2016)
Ijspeert, A.J., Nakanishi, J., Schaal, S.: Learning attractor landscapes for learning motor primitives, p. 8
Schaal, S.: Dynamic 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, pp. 261–280. Springer, Tokyo (2006). https://doi.org/10.1007/4-431-31381-8_23
Park, D.-H., Hoffmann, H., Pastor, P., Schaal, S.: Movement reproduction and obstacle avoidance with dynamic movement primitives and potential fields, p. 8
Hoffmann, H.: Biologically-inspired dynamical systems for movement generation: automatic real-time goal adaptation and obstacle avoidance, p. 6
Rai, A., Sutanto, G., Schaal, S., Meier, F.: Learning feedback terms for reactive planning and control, p. 8
Pairet, È., Ardón, P., Mistry, M., Petillot, Y.: Learning generalizable coupling terms for obstacle avoidance via low-dimensional geometric descriptors. IEEE Robot. Autom. Lett. 4, 8 (2019)
Ginesi, M., Meli, D., Calanca, A., Dall’Alba, D., Sansonetto, N., Fiorini, P.: Dynamic movement primitives: volumetric obstacle avoidance, 6
pbdlib-matlab. https://gitlab.idiap.ch/rli/pbdlib-matlab/
Har-Peled, S., Raichel, B.: The Fréchet distance revisited and extended. ACM Trans. Algorithms 10, 22 (2014)
Garrido-Jurado, S.: Automatic generation and detection of highly reliable fiducial markers under occlusion. Pattern Recognit. 13 (2014)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Shi, M., Gao, Y., Ti, B., Zhao, J. (2021). Obstacle Avoidance Methods Based on Geometric Information Under the DMPs Framework. In: Liu, XJ., Nie, Z., Yu, J., Xie, F., Song, R. (eds) Intelligent Robotics and Applications. ICIRA 2021. Lecture Notes in Computer Science(), vol 13014. Springer, Cham. https://doi.org/10.1007/978-3-030-89098-8_6
Download citation
DOI: https://doi.org/10.1007/978-3-030-89098-8_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-89097-1
Online ISBN: 978-3-030-89098-8
eBook Packages: Computer ScienceComputer Science (R0)