Motor Skills Learning and Generalization with Adapted Curvilinear Gaussian Mixture Model
- 124 Downloads
This paper is intended to solve the motor skills learning, representation and generalization problems in robot imitation learning. To this end, we present an Adapted Curvilinear Gaussian Mixture Model (AdC-GMM), which is a general extension of the GMM. The proposed model can encode data more compactly. More critically, it is inherently suitable for representing data with strong non-linearity. To infer the parameters of this model, a Cross Entropy Optimization (CEO) algorithm is proposed, where the cross entropy loss of the training data is minimized. Compared with the traditional Expectation Maximization (EM) algorithm, the CEO can automatically infer the optimal number of components. Finally, the generalized trajectories are retrieved by an Adapted Curvilinear Gaussian Mixture Regression (AdC-GMR) model. To encode observations from different frames, the sophisticated task parameterization (TP) technique is introduced. All above proposed algorithms are verified by comprehensive tasks. The CEO is evaluated by a hand writing task. Another goal-directed reaching task is used to evaluate the AdC-GMM and AdC-GMR algorithm. A novel hammer-over-a-nail task is designed to verify the task parameterization technique. Experimental results demonstrate the proposed CEO is superior to the EM in terms of encoding accuracy and the AdC-GMM can achieve more compact representation by reducing the number of components by up to 50%. In addition, the trajectory retrieved by the AdC-GMR is smoother and the approximation error is comparable to the Gaussian process regression (GPR) even far fewer parameters need to be estimated. Because of this, the AdC-GMR is much faster than the GPR. Finally, simulation experiments on the hammer-over-a-nail task demonstrates the proposed methods can be deployed and used in real-world applications.
KeywordsSkill learning Cross entropy Curvilinear Gaussian model Imitation learning
Unable to display preview. Download preview PDF.
Special thanks to my supervisor Prof. Weijia Zhou for his support on this work and Guangyu Zhang for his help on experimental data collection. Thanks to Nailong Liu for his technical support. We also thank the anonymous reviewers for their comments on a preliminary version of this paper.
- 2.Billard, A.G., Calinon, S., Dillmann, R.: Learning from Humans. In: Springer handbook of robotics, pp. 1995–2014. Springer (2016)Google Scholar
- 4.Calinon, S., Lee, D.: Learning Control. In: Vadakkepat, P., Goswami, A. (eds.) Humanoid robotics: a reference. Springer (2018)Google Scholar
- 5.Dillmann, R., Kaiser, M., Ude, A.: Acquisition of elementary robot skills from human demonstration. In: International Symposium on Intelligent Robotics Systems, pp. 185–192 (1995)Google Scholar
- 10.Ijspeert, A.J., Nakanishi, J., Schaal, S.: Learning attractor landscapes for learning motor primitives. In: Advances in Neural Information Processing Systems, pp. 1547–1554 (2003)Google Scholar
- 12.Kaiser, M., Dillmann, R.: Building Elementary Robot Skills from Human Demonstration. In: Proceedings of the 1996 IEEE International Conference on Robotics and Automation, 1996, vol. 3, pp. 2700–2705 (1996)Google Scholar
- 18.Lee, J.: A survey of robot learning from demonstrations for human-robot collaboration. arXiv:1710.08789 (2017)
- 19.Liu, S., Asada, H.: Teaching and Learning of Deburring Robots Using Neural Networks. In: Proceedings of the 1993 IEEE International Conference on Robotics and Automation, 1993, pp. 339–345 (1993)Google Scholar
- 20.Mayer, H., Nagy, I., Knoll, A.: Skill transfer and learning by demonstration in a realistic scenario of laparoscopic surgery. In: Proceedings of the IEEE International Conference on Humanoids CD-ROM. Munich, Germany (2003)Google Scholar
- 22.Nguyen-Tuong, D., Peters, J.R., Seeger, M.: Local Gaussian process regression for real time online model learning. In: Advances in Neural Information Processing Systems, pp. 1193–1200 (2009)Google Scholar
- 23.Paraschos, A., Daniel, C., Peters, J.R., Neumann, G.: Probabilistic movement primitives. In: Advances in Neural Information Processing Systems, pp. 2616–2624 (2013)Google Scholar
- 24.Park, D.H., Hoffmann, H., Pastor, P., Schaal, S.: Movement Reproduction and Obstacle Avoidance with Dynamic Movement Primitives and Potential Fields. In: 2008 8Th IEEE-RAS International Conference on Humanoid Robots. Humanoids 2008, pp. 91–98 (2008)Google Scholar
- 25.Rasmussen, C.E.: Gaussian processes in machine learning. In: Advanced Lectures on Machine Learning, pp. 63–71. Springer (2004)Google Scholar
- 27.Schaal, S.: Dynamic movement primitives-a framework for motor control in humans and humanoid robotics. In: Adaptive Motion of Animals and Machines, pp. 261–280. Springer (2006)Google Scholar
- 28.Sun, K., Mou, S., Qiu, J., Wang, T., Gao, H.: Adaptive fuzzy control for non-triangular structural stochastic switched nonlinear systems with full state constraints. IEEE Trans. Fuzzy Syst., pp. 1–1 (2018)Google Scholar