Abstract
Learning from demonstrations (LfD) provides a convenient pattern to teach robot to gain skills without mechanically programming. As an LfD approach, Gaussian mixture model/Gaussian mixture regression (GMM/GMR) has been widely used for its robustness and effectiveness. However, there still exist many problems of GMM when an obstacle, which is not presented in original demonstrations, appears in the workspace of robots. To address these problems, this paper presents a novel method based on Gaussian repulsive field-Gaussian mixture model (GRF-GMM) for obstacle avoidance by optimizing the model parameters. A Gaussian repulsive force is calculated through Gaussian functions and employed to work on Gaussian components to optimize the mixture distribution which is learnt from original demonstrations. Our approach allows the reproduced trajectory to keep a safe distance away from the obstacle. Finally, the feasibility and effectiveness of the proposed method are revealed through simulations and experiments.
This work is partially supported by the National Natural Science Foundation of China (62173352, 62006254), the Guangxi Key Laboratory of Automatic Detecting Technology and Instruments (YQ23207), and the Guangdong Basic and Applied Basic Research Foundation (2021A1515012314).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhu, Z., Hu, H.: Robot learning from demonstration in robotic assembly: a survey. Robotics 7(2), 17 (2018)
Chen, D., Li, G., Zhou, D., Ju, Z.: A novel curved gaussian mixture model and its application in motion skill encoding. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 7813–7818 (2021). https://doi.org/10.1109/IROS51168.2021.9636121
Calinon, S., Guenter, F., Billard, A.: On learning, representing, and generalizing a task in a humanoid robot. IEEE Trans. Syst., Man, Cybern. Part B (Cybernetics) 37(2), 286–298 (2007)
Calinon, S., Alizadeh, T., Caldwell, D.G.: On improving the extrapolation capability of task-parameterized movement models. In: IEEE/RSJ International Conference on Intelligent Robots and Systems, pp. 610–616 (2013)
Guenter, F., Hersch, M., Calinon, S., Billard, A.: Reinforcement learning for imitating constrained reaching movements. Adv. Robot. 21(13), 1521–1544 (2007)
Chen, J., Lau, H.Y., Xu, W., Ren, H.: Towards transferring skills to flexible surgical robots with programming by demonstration and reinforcement learning. In: Eighth International Conference on Advanced Computational Intelligence, pp. 378–384 (2016)
Zhang, H., Han, X., Fu, M., Zhou, W.: Robot obstacle avoidance learning based on mixture models. J. Robot. 2016, 1–14 (2016)
Li, W., Cheng, H., Liang, Z., Xiao, J., Zhang, X.: Adaptive obstacle avoidance optimization algorithm based on learning from demonstration. In: IEEE 11th Annual International Conference on CYBER Technology in Automation, Control, and Intelligent Systems, pp. 447–452 (2021). https://doi.org/10.1109/CYBER53097.2021.9588300
Wang, Y., Hu, Y., El Zaatari, S., Li, W., Zhou, Y.: Optimised learning from demonstrations for collaborative robots. Robot. Comput.-Integr. Manufact. 71, 102169 (2021)
Li, X., Cheng, H., Liang, X.: Adaptive motion planning framework by learning from demonstration. Ind. Robot. 46(4), 541–552 (2019)
Osa, T., Esfahani, A.M.G., Stolkin, R., Lioutikov, R., Peters, J., Neumann, G.: Guiding trajectory optimization by demonstrated distributions. IEEE Robot. Autom. Lett. 2(2), 819–826 (2017)
Chi, M., Yao, Y., Liu, Y., Zhong, M.: Learning, generalization, and obstacle avoidance with dynamic movement primitives and dynamic potential fields. Appl. Sci. 9(8), 1535 (2019)
Koert, D., Maeda, G., Lioutikov, R., Neumann, G., Peters, J.: Demonstration based trajectory optimization for generalizable robot motions. In: IEEE-RAS 16th International Conference on Humanoid Robots, pp. 515–522 (2016)
Kalakrishnan, M., Chitta, S., Theodorou, E., Pastor, P., Schaal, S.: Stomp: stochastic trajectory optimization for motion planning. In: IEEE International Conference on Robotics and Automation, pp. 4569–4574 (2011)
Duan, A., et al.: Learning to avoid obstacles with minimal intervention control. Front. Robot. AI 7, 60 (2020)
Tan, H., Erdemir, E., Kawamura, K., Du, Q.: A potential field method-based extension of the dynamic movement primitive algorithm for imitation learning with obstacle avoidance. In: IEEE International Conference on Mechatronics and Automation, pp. 525–530 (2011)
MacQueen, J.: Classification and analysis of multivariate observations. In: 5th Berkeley Symp. Math. Statist. Probability, pp. 281–297. University of California Los Angeles LA USA (1967)
Tian, Y., Zhu, X., Meng, D., Wang, X., Liang, B.: An overall configuration planning method of continuum hyper-redundant manipulators based on improved artificial potential field method. IEEE Robot. Autom. Lett. 6(3), 4867–4874 (2021)
Mok, J., Lee, Y., Ko, S., Choi, I., Choi, H.S.: Gaussian-mixture based potential field approach for uav collision avoidance. In: 56th Annual Conference of the Society of Instrument and Control Engineers of Japan, pp. 1316–1319 (2017)
Huang, Y., Rozo, L., Silvério, J., Caldwell, D.G.: Kernelized movement primitives. Int. J. Robot. Res. 38(7), 833–852 (2019)
Zucker, M., et al.: Chomp: covariant Hamiltonian optimization for motion planning. Int. J. Robot. Res. 32(9–10), 1164–1193 (2013)
Sylvain, C.: Robot programming by demonstration: a probabilistic approach (2009)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Ye, B., Yu, P., Hu, C., Qiu, B., Tan, N. (2024). GRF-GMM: A Trajectory Optimization Framework for Obstacle Avoidance in Learning from Demonstration. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Lecture Notes in Computer Science, vol 14450. Springer, Singapore. https://doi.org/10.1007/978-981-99-8070-3_2
Download citation
DOI: https://doi.org/10.1007/978-981-99-8070-3_2
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8069-7
Online ISBN: 978-981-99-8070-3
eBook Packages: Computer ScienceComputer Science (R0)