Abstract
Advances in reinforcement learning algorithms allow robots to learn complex tasks such as object manipulation. However, most of these tasks have been implemented only in simulations. In addition, it is difficult to apply reinforcement learning in the real world because of the difficulty in obtaining the state details for the learning process, such as the position of an object, and collecting large amount of data. Moreover, existing reinforcement learning algorithms are designed to learn a single task, so there is a limit to learning multiple tasks. To address these problems, a novel system is proposed in this study for applications to the real world after learning multiple tasks in the simulation. First, a generative model that converts real-world images into simulation images is proposed, so that simulation-to-real-world transfer wherein the learning results from simulation can be applied directly to the real-world scenarios is possible. Additionally, to learn multiple tasks using images, a reinforcement learning algorithm combining variational auto-encoder and asymmetric actor-critic is developed. To verify this system, experiments are conducted in which the algorithms learned in the simulation are applied to the real world to achieve a success rate of 83.8%; this shows that the proposed system can perform multiple manipulation tasks successfully.
Similar content being viewed by others
References
Tobin J, Fong R, Ray A, Schneider J, Zaremba W, Abbeel P (2017) Domain randomization for transferring deep neural networks from simulation to the real world. In: Proceedings of IEEE/RSJ international conference on intelligent robots and systems, pp 23–30
Kar A et al (2019) Meta-sim: learning to generate synthetic datasets. In: Proceedings of the IEEE international conference on computer vision, pp 4551–4560
James S et al (2019) Sim-to-real via sim-to-sim: data-efficient robotic grasping via randomized-to-canonical adaptation networks. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, pp 12627–12637
Lee AX, Nagabandi A, Abbeel P, Levine S (2019) Stochastic latent actor-critic: deep reinforcement learning with a latent variable model. https://arxiv.org/abs/1907.00953
Laskin M, Lee K, Stooke A, Pinto L, Abbeel P, Srinivas A (2020) Reinforcement learning with augmented data. https://arxiv.org/abs/2004.14990
Pinto L, Andrychowicz M, Welinder P, Zaremba W, Abbeel P (2018) Asymmetric actor critic for image-based robot learning. In: Proceedings of robotics science and systems
Haarnoja T, Zhou A, Abbeel P, Levine S (2018) Soft actor-critic: off policy maximum entropy deep reinforcement learning with a stochastic actor. Proceedings of international conference on machine learning 80:1861–1870
Kingma DP, Welling M (2014) Auto-encoding variational Bayes. In: Proceedings of international conference on learning representations
Isola P, Zhu J-Y, Zhou T, Efros AA (2016) Image-to-image translation with conditional adversarial networks. In: Proceedings of IEEE computer society conference on computer vision and pattern recognition, pp 1125–1134
Mao X, Li Q, Xie H, Lau RY, Wang Z, Smolley SP (2017) Least squares generative adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2794–2802
Higgins I, Matthey L, Pal A, Burgess C, Glorot X, Botvinick M, Mohamed S, Lerchner A (2017) beta-vae: Learning basic visual concepts with a constrained variational framework. In: Proceedings of international conference on learning representations
Yarats D, Zhang A, Kostrikov I, Amos B, Pineau J, Fergus R (2019) Improving sample efficiency in model-free reinforcement learning from images. arXiv preprint. https://arxiv.org/abs/1910.01741
Funding
This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (No. 2018-0-00622)
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Kim, S., Jo, H. & Song, JB. Object manipulation system based on image-based reinforcement learning. Intel Serv Robotics 15, 171–177 (2022). https://doi.org/10.1007/s11370-021-00402-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11370-021-00402-6