Training Robots Without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer
Open accessThe DOI matches its Crossref record; 26 of the 26 references it cites were found in a registry or an index.
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“However, this method requires designing leader hardware with a kinematic structure identical to a target robot, enabling its joint states to be directly mapped onto the robot.”
From LEGATO: Cross-Embodiment Imitation Using a Grasping Tool (2025) · cites this paper as [23]
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474 · cited 1×
“ReLU followed by nine residual blocks [21], and a max-pooling layer is inserted in every two residual blocks with the stride equal to 2.”
MethodVaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Eye movements in natural behavior
Hayhoe, M., & Ballard, D. (2005) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2005.02.009 · Cited by 1,326 · cited 2×
“object position [13], [15], this method can eliminate distractions from the human hand.”
BackgroundMethod(1994) · Aston Publications Explorer (Aston University) · Cited by 1,245
Quantifying Attention Flow in Transformers
Abnar, S., & Zuidema, W. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.385 · Cited by 995
Kuniyoshi, Y., Inaba, M., & Inoue, H. (1994) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.338535 · Cited by 676 · cited 1×
“A few researchers have studied a robot that learns from watching humans demonstrate tasks [10], [11], [12].”
BackgroundSelf-citationDeep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation
Zhang, T., McCarthy, Z., Jow, O., Lee, D., Chen, X., Goldberg, K., & Abbeel, P. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8461249 · Cited by 609
On the Variance of the Adaptive Learning Rate and Beyond
Liu, L., Jiang, H., He, P., Chen, W., Liu, X., Gao, J., & Han, J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.03265 · Cited by 595 · cited 2×
“These models were trained for 300 epochs with a learning rate of 3 e 5 using rectified Adam [22] and a weight decay of 0.01.”
MethodInfluentialDeep spatial autoencoders for visuomotor learning
Finn, C., Tan, X. Y., Duan, Y., Darrell, T., Levine, S., & Abbeel, P. (2016) · 2016 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2016.7487173 · Cited by 430 · cited 4×
“The visualized example of two-dimensional visual features extracted by SpatialSoftmax on the global vision processing network demonstrated the difference in the feature coordinates between the demonstration data collected by the master (validation set) and the robot data collected by DA-force during the test (Fig.”
MethodInfluential
Research works printed but not linked: 1
- 10.1139/y96-033 · doi:10.1139/y96-033 · Paper page
Cited by
Goal-Conditioned Dual-Action Imitation Learning for Dexterous Dual-Arm Robot Manipulation
Kim, H., Ohmura, Y., & Kuniyoshi, Y. (2024) · IEEE Transactions on Robotics · doi:10.1109/tro.2024.3372778 · Cited by 60
“Hence, this research uses a general-purpose manipulator with a single degree-of-freedom end-effector, which can also be applied to other various tasks [3], [4], [5], [52], to learn dexterous manipulation skills such as banana-peeling by imitating human manipulation skills.”
Self-citationLiu, W., Wang, J., Wang, Y., Wang, W., & Lu, C. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128061 · Cited by 139
“…to collect robot manipulation demonstrations is teleoperation [4], where a human operator remotely controls the robot to execute the manipulation task, by various user interfaces, including haptic devices [7], exoskeleton [8–10], virtual reality [11–14] and leader-follower paradigm [15–19].”
Adaptive Compliance Policy: Learning Approximate Compliance for Diffusion Guided Control
Hou, Y., Liu, Z., Chi, C., Cousineau, E. A., Kuppuswamy, N. S., Feng, S., Burchfiel, B., & Song, S. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128452 · Cited by 141
“To effectively encode the temporal relations in the force/torque data, Prior work has explored many different encoding meth-ods such as causal convolution [26], TCN [2], LSTM [9], VAE [1], and self-attention [22, 23].”
Human-in-the-Loop Robot Learning for Smart Manufacturing: A Human-Centric Perspective
Chen, H., Li, S., Fan, J., Duan, A., Yang, C., Navarro-Alarcon, D., & Zheng, P. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3528051 · Cited by 67
“Kim et al. [147] proposed a transfer learning policy based master-to-robot (M2R) system.”
Goal-conditioned dual-action imitation learning for dexterous dual-arm robot manipulation
Kim, H., Ohmura, Y., & Kuniyoshi, Y. (2022) · arXiv · doi:10.48550/arxiv.2203.09749 · Cited by 64
Self-citation
Metadata
- Authors
- Kim, H., Ohmura, Y., Nagakubo, A., & Kuniyoshi, Y.
- Affiliations
- The University of Tokyo (JP)
- National Institute of Advanced Industrial Science and Technology (JP)
- Venue
- IEEE Robotics and Automation Letters
- Published
- 2023-05
- Volume
- 8
- Issue
- 5
- Pages
- 2906-2913
- ISSN
- 2377-3766 (ISSN-L)
- 2377-3774
- OpenAlex
- W4361029864
- Cited by
- 28
- References
- 25
- Citations by year
- 2026: 2 · 2025: 13 · 2024: 9 · 2023: 1
- FWCI
- 2.68
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Robotics and Automation Letters (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by-nc-nd)
- arXiv (Cornell University)
- Funders
- Grant-in-Aid for Scientific Research (JP22H00528)
- Department of Social Cooperation Program Intelligent Mobility Society Design
- Toyota Central R&D Labs., Inc.
- Next Generation AI Research Center
- University of Tokyo
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Mechanical Engineering › Teleoperation and Haptic Systems
- Keywords
- deep imitation learning, force feedback, robotic manipulation, human demonstrations, force/torque sensor, domain gap, calibration, teleoperation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Training Robots Without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer. https://app.cochat.ai/papers/10.1109/lra.2023.3262423
- The paper
- Kim, H., Ohmura, Y., Nagakubo, A., & Kuniyoshi, Y. (2023). Training Robots Without Robots: Deep Imitation Learning for Master-to-Robot Policy Transfer. IEEE Robotics and Automation Letters. https://doi.org/10.1109/lra.2023.3262423
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.