2000 character limit reached
Training Robots without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer (2202.09574v2)
Published 19 Feb 2022 in cs.RO and cs.AI
Abstract: Deep imitation learning is promising for robot manipulation because it only requires demonstration samples. In this study, deep imitation learning is applied to tasks that require force feedback. However, existing demonstration methods have deficiencies; bilateral teleoperation requires a complex control scheme and is expensive, and kinesthetic teaching suffers from visual distractions from human intervention. This research proposes a new master-to-robot (M2R) policy transfer system that does not require robots for teaching force feedback-based manipulation tasks. The human directly demonstrates a task using a controller. This controller resembles the kinematic parameters of the robot arm and uses the same end-effector with force/torque (F/T) sensors to measure the force feedback. Using this controller, the operator can feel force feedback without a bilateral system. The proposed method can overcome domain gaps between the master and robot using gaze-based imitation learning and a simple calibration method. Furthermore, a Transformer is applied to infer policy from F/T sensory input. The proposed system was evaluated on a bottle-cap-opening task that requires force feedback.
- H. Kim, Y. Ohmura, and Y. Kuniyoshi, “Gaze-based dual resolution deep imitation learning for high-precision dexterous robot manipulation,” Robotics and Automation Letters, pp. 1–1, 2021.
- H. Kim, Y. Ohmura, and Y. Kuniyoshi, “Transformer-based deep imitation learning for dual-arm robot manipulation,” in International Conference on Intelligent Robots and Systems, 2021.
- T. Zhang, Z. McCarthy, O. Jow, D. Lee, X. Chen, K. Goldberg, and P. Abbeel, “Deep imitation learning for complex manipulation tasks from virtual reality teleoperation,” in International Conference on Robotics and Automation, 2018, pp. 1–8.
- H. Kim, Y. Ohmura, and Y. Kuniyoshi, “Using human gaze to improve robustness against irrelevant objects in robot manipulation tasks,” Robotics and Automation Letters, vol. 5, no. 3, pp. 4415–4422, 2020.
- T. Hulin, K. Hertkorn, P. Kremer, S. Schätzle, J. Artigas, M. Sagardia, F. Zacharias, and C. Preusche, “The dlr bimanual haptic device with optimized workspace,” in International Conference on Robotics and Automation, 2011, pp. 3441–3442.
- J. Guo, C. Liu, and P. Poignet, “A scaled bilateral teleoperation system for robotic-assisted surgery with time delay,” Journal of Intelligent & Robotic Systems, vol. 95, no. 1, pp. 165–192, 2019.
- T. Adachi, K. Fujimoto, S. Sakaino, and T. Tsuji, “Imitation learning for object manipulation based on position/force information using bilateral control,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2018, pp. 3648–3653.
- C. Schou, J. S. Damgaard, S. Bøgh, and O. Madsen, “Human-robot interface for instructing industrial tasks using kinesthetic teaching,” in IEEE ISR 2013. IEEE, 2013, pp. 1–6.
- B. Akgun, M. Cakmak, J. W. Yoo, and A. L. Thomaz, “Trajectories and keyframes for kinesthetic teaching: A human-robot interaction perspective,” in International Conference on Human-Robot Interaction, 2012, pp. 391–398.
- Y. Kuniyoshi, M. Inaba, and H. Inoue, “Learning by Watching: Extracting reusable task knowledge from visual observation of human performance,” Transactions on Robotics and Automation, vol. 10, no. 6, pp. 799–822, 1994.
- T. Yu, C. Finn, A. Xie, S. Dasari, T. Zhang, P. Abbeel, and S. Levine, “One-shot imitation from observing humans via domain-adaptive meta-learning,” arXiv preprint arXiv:1802.01557, 2018.
- Y. Liu, A. Gupta, P. Abbeel, and S. Levine, “Imitation from observation: Learning to imitate behaviors from raw video via context translation,” in International Conference on Robotics and Automation, 2018, pp. 1118–1125.
- M. Hayhoe and D. Ballard, “Eye movements in natural behavior,” Trends in Cognitive Sciences, vol. 9, pp. 188–94, 2005.
- A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A. N. Gomez, Ł. Kaiser, and I. Polosukhin, “Attention is all you need,” in Neural Information Processing Systems, 2017, pp. 5998–6008.
- J. Pelz, M. Hayhoe, and R. Loeber, “The coordination of eye, head, and hand movements in a natural task,” Experimental Brain Research, vol. 139, pp. 266–77, 2001.
- C. M. Bishop, “Mixture density networks,” Neural Computing Research Group, Aston University, Tech. Rep., 1994.
- L. Bazzani, H. Larochelle, and L. Torresani, “Recurrent mixture density network for spatiotemporal visual attention,” in International Conference on Learning Representations, 2016.
- C. Finn, X. Y. Tan, Y. Duan, T. Darrell, S. Levine, and P. Abbeel, “Deep spatial autoencoders for visuomotor learning,” in International Conference on Robotics and Automation, 2016, pp. 512–519.
- J. Paillard, “Fast and slow feedback loops for the visual correction of spatial errors in a pointing task: a reappraisal,” Canadian Journal of Physiology and Pharmacology, vol. 74, no. 4, pp. 401–417, 1996.
- H. Kim, Y. Ohmura, and Y. Kuniyoshi, “Robot peels banana with goal-conditioned dual-action deep imitation learning,” arXiv preprint arXiv:2203.09749, 2022.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Conference on Computer Vision and Pattern Recognition, 2016, pp. 770–778.
- L. Liu, H. Jiang, P. He, W. Chen, X. Liu, J. Gao, and J. Han, “On the variance of the adaptive learning rate and beyond,” in International Conference on Learning Representations, 2020, pp. 1–14.
- S. Abnar and W. Zuidema, “Quantifying attention flow in transformers,” in Annual Meeting of the Association for Computational Linguistics, 2020, pp. 4190–4197.
- T. Kanai, Y. Ohmura, A. Nagakubo, and Y. Kuniyoshi, “Third-party evaluation of robotic hand designs using a mechanical glove,” arXiv preprint arXiv:2109.10501, 2021.
- Heecheol Kim (8 papers)
- Yoshiyuki Ohmura (17 papers)
- Akihiko Nagakubo (2 papers)
- Yasuo Kuniyoshi (35 papers)