Concept2Robot: Learning manipulation concepts from instructions and human demonstrations
The DOI matches its Crossref record; 10 of the 10 references it cites were found in a registry or an index.
Abstract
We aim to endow a robot with the ability to learn manipulation concepts that link natural language instructions to motor skills. Our goal is to learn a single multi-task policy that takes as input a natural language instruction and an image of the initial scene and outputs a robot motion trajectory to achieve the specified task. This policy has to generalize over different instructions and environments. Our insight is that we can approach this problem through learning from demonstration by leveraging large-scale video datasets of humans performing manipulation actions. Thereby, we avoid more time-consuming processes such as teleoperation or kinesthetic teaching. We also avoid having to manually design task-specific rewards. We propose a two-stage learning process where we first learn single-task policies through reinforcement learning. The reward is provided by scoring how well the robot visually appears to perform the task. This score is given by a video-based action classifier trained on a large-scale human activity dataset. In the second stage, we train a multi-task policy through imitation learning to imitate all the single-task policies. In extensive simulation experiments, we show that the multi-task policy learns to perform a large percentage of the 78 different manipulation tasks on which it was trained. The tasks are of greater variety and complexity than previously considered robot manipulation tasks. We show that the policy generalizes over variations of the environment. We also show examples of successful generalization over novel but similar instructions.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Addressing Function Approximation Error in Actor-Critic Methods
Fujimoto, S., van Hoof, H., & Meger, D. (2018) · arXiv · doi:10.48550/arxiv.1802.09477 · Cited by 3,650 · cited 1×
“In the contextual bandit problem, the critic network is trained to directly approximate the Q value, so overestimation is not an issue when using neural networks to learn the Q value (Fujimoto et al., 2018).”
MethodA survey of robot learning from demonstration
Argall, B. D., Chernova, S., Veloso, M., & Browning, B. (2009) · Robotics and Autonomous Systems · doi:10.1016/j.robot.2008.10.024 · Cited by 3,227
Domain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · cited 1×
“We can utilize domain randomization (Tobin et al., 2017) for transferring the policy learned from simulation to the real world.”
Method(2016) · doi:10.1007/978-3-319-46475-6_5 · Cited by 1,081
Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models
Khansari-Zadeh, S. M., & Billard, A. (2011) · IEEE Transactions on Robotics · doi:10.1109/tro.2011.2159412 · Cited by 771 · cited 3×
“kind of dynamical system is analytically well understood and is widely utilized in the robotic community [21].”
BackgroundInfluentialLearning and generalization of motor skills by learning from demonstration
Pastor, P., Hoffmann, H., Asfour, T., & Schaal, S. (2009) · 2009 IEEE International Conference on Robotics and Automation · doi:10.1109/robot.2009.5152385 · Cited by 702
QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Kalashnikov, D., Irpan, A., Pastor, P., Ibarz, J., Herzog, A., Jang, E., Quillen, D., Holly, E., Kalakrishnan, M., Vanhoucke, V., et al. (2018) · arXiv · doi:10.48550/arxiv.1806.10293 · Cited by 697
Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learning
Yu, T., Quillen, D., He, Z., Julian, R., Narayan, A., Shively, H., Bellathur, A., Hausman, K., Finn, C., & Levine, S. (2019) · arXiv · doi:10.48550/arxiv.1910.10897 · Cited by 450
Rusu, A. A., Colmenarejo, S. G., Gulcehre, C., Desjardins, G., Kirkpatrick, J., Pascanu, R., Mnih, V., Kavukcuoglu, K., & Hadsell, R. (2015) · arXiv · doi:10.48550/arxiv.1511.06295 · Cited by 270
Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learning
Gupta, A., Kumar, V., Lynch, C., Levine, S., & Hausman, K. (2019) · arXiv · doi:10.48550/arxiv.1910.11956 · Cited by 153 · cited 1×
“[14] propose a method for solving long-horizon tasks which contains an imitation learning stage to produce goal-conditioned hierarchical policies, and a reinforcement learning phase to fine-tune these policies for task performance.”
Method
Cited by
Mees, O., Hermann, L., Rosete-Beas, E., & Burgard, W. B. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3180108 · Cited by 189
Embodied large language models enable robots to complete complex tasks in unpredictable environments
Mon-Williams, R., Li, G., Long, R., Du, W., & Lucas, C. G. (2025) · Nature Machine Intelligence · doi:10.1038/s42256-025-01005-x · Cited by 132
“It is important to note that the system has not been tested with fragile or deformable materi-858 als.”
Affordances from Human Videos as a Versatile Representation for Robotics
Bahl, S., Mendonca, R., Chen, L., Jain, U., & Pathak, D. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01324 · Cited by 119
“It has been common to introduce some form of prior derived from human knowledge, which could take the form of corrective interactions [22, 41, 64], structured policy spaces [2, 7, 7, 17, 48, 80, 89, 94, 102, 118], offline robotics data [24, 53, 54, 67, 92], using pretrained visual representations [79,84,100,116,117] o…”
BackgroundHuman-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
“In addition, Shao et al. [69] reported one new idea that agents are endowed to learn a single multi-task policy by leveraging large-scale vision demonstration of humans performing operation motion and natural language instructions according to the integration of DDPG and the cross entropy method…”
Learning Periodic Tasks from Human Demonstrations
Yang, J., Zhang, J., Settle, C., Rai, A., Antonova, R., & Bohg, J. (2022) · 2022 International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra46639.2022.9812402 · Cited by 21
Self-citation
Metadata
- Authors
- Shao, L., Migimatsu, T., Zhang, Q., Yang, K., & Bohg, J.
- Venue
- The International Journal of Robotics Research
- Publisher
- SAGE Publications
- Published
- 2021-10-11
- Volume
- 40
- Issue
- 12-14
- Pages
- 1419-1434
- ISSN
- 0278-3649 (ISSN-L)
- 1741-3176
- OpenAlex
- W3207832698
- Cited by
- 80
- References
- 10
- FWCI
- 5.80
- Type
- journal article
- Language
- en
- Open access
- closed
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: Concept2Robot: Learning manipulation concepts from instructions and human demonstrations. https://app.cochat.ai/papers/10.1177/02783649211046285
- The paper
- Shao, L., Migimatsu, T., Zhang, Q., Yang, K., & Bohg, J. (2021). Concept2Robot: Learning manipulation concepts from instructions and human demonstrations. The International Journal of Robotics Research. https://doi.org/10.1177/02783649211046285
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.