Generating Basic Unit Movements with Conditional Generative Adversarial Networks

LUO Dingsheng; NIE Mengxi; WU Xihong

doi:10.1049/cje.2019.07.013

Volume 28 Issue 6

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2019 > 28(6): 1099-1107

LUO Dingsheng, NIE Mengxi, WU Xihong, “Generating Basic Unit Movements with Conditional Generative Adversarial Networks,” Chinese Journal of Electronics, vol. 28, no. 6, pp. 1099-1107, 2019, doi: 10.1049/cje.2019.07.013

Citation:

LUO Dingsheng, NIE Mengxi, WU Xihong, “Generating Basic Unit Movements with Conditional Generative Adversarial Networks,” Chinese Journal of Electronics, vol. 28, no. 6, pp. 1099-1107, 2019, doi: 10.1049/cje.2019.07.013

Citation:

PDF( 17760 KB)

Generating Basic Unit Movements with Conditional Generative Adversarial Networks

doi: 10.1049/cje.2019.07.013

Key Laboratory of Machine Perception(Ministry of Education), Speech and Hearing Research Center, Department of Machine Intelligence, School of EECS, Peking University, Beijing 100871, China

Funds: This work is supported by the National Natural Science Foundation of China (No.U1713217, No.11590773)

Received Date: 2018-10-11
Rev Recd Date: 2019-07-16
Publish Date: 2019-11-10

Abstract

Abstract

Arm motion control is fundamental for robot accomplishing complicated manipulation tasks. Different movements can be organized by configuring a series of motion units. Our work aims at equipping the robot with the ability to carry out Basic unit movements (BUMs), which are used to constitute various motion sequences so that the robot can drive its hand to a desired position. With the definition of BUMs, we explore a learning approach for the robot to develop such an ability by leveraging deep learning technique. In order to generate the BUM regarding to the current arm state, an internal inverse model is developed. We propose to use Conditional generative adversarial networks (CGANs) to establish the inverse model to generate the BUMs. The experimental results on a humanoid robot PKU-HR6.0II illustrate that CGANs could successfully generate multiple solutions given a BUM, and these BUMs can be used to constitute further reaching movement effectively.
- Arm motion control,
- Basic unit movements,
- Deep learning,
- CGANs,
- Inverse model,
- Humanoids

FullText(HTML)

References(27)

References

C.C. Kemp, A. Edsinger and E. Torres-Jara, "Challenges for robot manipulation in human environments", IEEE Robotics & Automation Magazine, Vol.14, No.1, pp.20-29, 2007.

Z. Li, J. Mei, S. Cao, et al., "Modeling and control of automatic precision assembly robot with multi-information fusion measuring system and control algorithm", ACTA ELECTRONICA SINICA, Vol.43, No.3, pp.636-640, 2018.

S.Y. Shin and C. Kim, "Human-like motion generation and control for humanoid's dual arm object manipulation", IEEE Transactions on Industrial Electronics, Vol.62, No.4, pp.2265-2276, 2015.

L. Jamone, L. Natale and F. Nori, "Autonomous online learning of reaching behavior in a humanoid robot", International Journal of Humanoid Robotics, Vol.9, No.03, p.1250017, 2012.

D. Bertram, J. Kuffner, R. Dillmann, et al., "An integrated approach to inverse kinematics and path planning for redundant manipulators", Proceedings of the 2006 IEEE International Conference on Robotics and Automation, ICRA 2006, Orlando, Florida, USA. pp.1874-1879, 2006.

D. Gong, R. He and J. Yu, "Motion mapping in the joint space for the control of the heterogeneous wheelchair-mounted robotic arm", ACTA ELECTRONICA SINICA, Vol.46, No.2, pp.665-672, 2018.

S. Xu, S. Song and G. She, "An improved algorithm of path planning for sweeping robot", Measurement & Control Technology, Vol.36, No.2, pp.120-127, 2017.

W. Burger, E. Wieser, E. Dean-Leon, et al., "A scalable method for multi-stage developmental learning for reaching", Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2017), Instituto Superior Tecnico, Lisbon, Portugal, 2017.

D. Luo, F. Hu, Y. Deng, et al., "An infant-inspired model for robot developing its reaching ability", Joint IEEE International Conference on Development and Learning and on Epigenetic Robotics (ICDL-EpiRob 2016), Cergy-Pontoise, France, pp.310-317, 2016.

Z. Mahoor, B. MacLennan and A. McBride, "Neurally plausible model of robot reaching inspired by infant motor babbling", arXiv preprint, Vol.1801, No.00293, p.arXiv, 2017.

H.N. Kadmon, U. David, H.N. G, et al., "Movement decomposition in the primary motor cortex", Cerebral Cortex, 2018.

T.K. A and S. Reza, "Learning of action through adaptive combination of motor primitives", Nature, Vol.407, No.6805, p.742, 2000.

G.S. F, "Motor primitives new data and future questions", Current Opinion in Neurobiology, Vol.33, pp.156-165, 2015.

F. Tamar and H. Binyamin, "Motor primitives in vertebrates and invertebrates", Current opinion in neurobiology, Vol.15, No.6, pp.660-666, 2005.

S. Matteo, A. Sangik and L. Dongheui, "Incremental kinesthetic teaching of end-effector and null-space motion primitives", Proceedings of the 2015 IEEE International Conference on Robotics and Automation, ICRA 2015, Seattle, USA, pp.3570-3575, 2015.

P. Affan, M. Yuecheng and L. Dongheui, "Learning deep movement primitives using convolutional neural networks", IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2017), Birmingham, UK, 2017.

B. Aleksandar, N. Bojan, U. Ale, et al., "Compliant movement primitives in a bimanual setting", IEEE-RAS International Conference on Humanoid Robots (HUMANOIDS 2017), Birmingham, UK, pp.365-371, 2017.

K. Li, Y. Li, X. Hu, et al., "A robust and accurate object tracking algorithm based on convolutional neural network", ACTA ELECTRONICA SINICA, Vol.46, No.9, pp.2087-2093, 2018.

S. Piao, Q. Zhong and Y. Liu, "The research of optimal motion planning for robot in complex environment", Chinese Journal of Electronics, Vol.20, No.4, pp.637-640, 2011.

H. Fan, W. Xihong and L. Dingsheng, "Learning basic unit movements for humanoid arm motion control", 2016 IEEE 14th International Workshop on Advanced Motion Control (AMC 2016), pp.327-333, 2016.

H. Fan, L. Wentao, W. Xihong, et al., "Learning basic unit movements with gate-model auto-encoder for humanoid arm motion control", IEEE International Conference on Information and Automation (ICIA 2016), pp.246-251, 2016.

M. Mirza and S. Osindero, "Conditional generative adversarial nets", arXiv preprint, Vol.1411, No.1784, pp.1-7, 2014.

D. Nguyen-Tuong and J. Peters, "Model learning for robot control:a survey", Cognitive Processing, Vol.12, No.4, pp.319-340, 2011.

K. Mitsuo, "Internal models for motor control and trajectory planning", Current Opinion in Neurobiology, Vol.9, No.6, pp.718-727, 1999.

I.J. Goodfellow, J. Pouget-Abadie, M. Mirza, et al., "Generative adversarial nets", Advances in Neural Information Processing Systems. NIPS, 2014, Montreal, Canada, pp.2672-2680, 2014.

G. Ishaan, A. Faruk, A. Martin, et al., "Improved training of wasserstein gans", Advances in Neural Information Processing Systems, Long Beach, USA, pp.5767-5777, 2017.

T. Zhang, F. Hu, Y. Deng, et al., "A hierarchical inverse model based on proprioception and dnn for robot reaching", Conference of the IEEE Industrial Electronics Society. IECON 2017, Beijing, China, pp.6697-6702, 2017.

Relative Articles

Supplements(0)

Cited By

Proportional views