Learning Generalizable Robotic Reward Functions from “In-The-Wild” Human Videos
Open accessThe DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.
Abstract
We are motivated by the goal of generalist robots that can complete a wide range of tasks across many environments.Critical to this is the robot's ability to acquire some metric of task success or reward, which is necessary for reinforcement learning, planning, or knowing when to ask for help.For a general-purpose robot operating in the real world, this reward function must also be able to generalize broadly across environments, tasks, and objects, while depending only on on-board sensor observations (e.g.RGB images).While deep learning on large and diverse datasets has shown promise as a path towards such generalization in computer vision and natural language, collecting high quality datasets of robotic interaction at scale remains an open challenge.In contrast, "in-the-wild" videos of humans (e.g.YouTube) contain an extensive collection of people doing interesting tasks across a diverse range of settings.In this work, we propose a simple approach, Domain-agnostic Video Discriminator (DVD), that learns multitask reward functions by training a discriminator to classify whether two videos are performing the same task, and can generalize by virtue of learning from a small amount of robot data with a broad dataset of human videos.We find that by leveraging diverse human datasets, this reward function (a) can generalize zero shot to unseen environments, (b) generalize zero shot to unseen tasks, and (c) can be combined with visual model predictive control to solve robotic manipulation tasks on a real WidowX200 robot in an unseen environment from a single human demo.
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
ActivityNet: A large-scale video benchmark for human activity understanding
Heilbron, F. C., Escorcia, V., Ghanem, B., & Niebles, J. C. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298698 · Cited by 2,578
The “Something Something” Video Database for Learning and Evaluating Visual Common Sense
Goyal, R., Kahou, S. E., Michalski, V., Materzynska, J., Westphal, S., Kim, H., Haenel, V., Fruend, I., Yianilos, P., Mueller-Freitag, M., et al. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.622 · Cited by 1,471
Learning Latent Dynamics for Planning from Pixels
Hafner, D., Lillicrap, T., Fischer, I., Villegas, R., Ha, D., Lee, H., & Davidson, J. (2018) · arXiv · doi:10.48550/arxiv.1811.04551 · Cited by 708
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
Learning Synergies Between Pushing and Grasping with Self-Supervised Deep Reinforcement Learning
Zeng, A., Song, S., Welker, S., Lee, J., Rodriguez, A., & Funkhouser, T. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593986 · Cited by 606
Deep visual foresight for planning robot motion
Finn, C., & Levine, S. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989324 · Cited by 599
Self-citationMeta-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
Self-citation
Cited by
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Self-citationOpen X-Embodiment: Robotic Learning Datasets and RT-X Models : Open X-Embodiment Collaboration 0
O’Neill, A., Rehman, A., Maddukuri, A., Gupta, A., Padalkar, A., Lee, A., Pooley, A., Gupta, A., Mandlekar, A., Jain, A., et al. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10611477 · Cited by 210
Self-citationA Survey of Zero-shot Generalisation in Deep Reinforcement Learning
Kirk, R., Zhang, A., Grefenstette, E., & Rocktäschel, T. (2023) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14174 · Cited by 193
“A promising approach is using inverse RL (Arora & Doshi, 2020; Ng & Russell, 2000, IRL) to learn a reward function from human demonstrations (Chen et al., 2021; Schmeckpeper et al., 2020; Sermanet et al., 2018; Sestini et al., 2020), rather than hand-crafting reward functions for each task.”
MethodAffordances 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 [23, 42, 68], structured policy spaces [2, 7, 7, 17, 50, 85, 94, 99, 108, 125], offline robotics data [25, 56, 57, 71, 97], using pretrained visual representations [84,89,106,123,124] o…”
BackgroundMineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge
Fan, L., Wang, G., Jiang, Y., Mandlekar, A., Yang, Y., Zhu, H., Tang, A., Huang, D.-A., Zhu, Y., & Anandkumar, A. (2022) · arXiv · doi:10.48550/arxiv.2206.08853 · Cited by 72
AirExo: Low-Cost Exoskeletons for Learning Whole-Arm Manipulation in the Wild
Fang, H., Fang, H.-S., Wang, Y., Ren, J., Chen, J., Zhang, R., Wang, W., & Lu, C. (2024) · 2024 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra57147.2024.10610799 · Cited by 38
Scaling Up and Distilling Down: Language-Guided Robot Skill Acquisition
Ha, H., Florence, P., & Song, S. (2023) · arXiv · doi:10.48550/arxiv.2307.14535 · Cited by 24
“As another option for scalability not depending on robots, human ego-vision data [6, 26, 27] has been shown to be relevant to robot learning [5, 28], but lacks “action” (motor) labels, and requires cross-embodiment transfer.”
BackgroundLearning 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
Metadata
- Authors
- Chen, A., Nair, S., & Finn, C.
- Venue
- Robotics: Science and Systems XVII
- Published
- 2021-07-12
- OpenAlex
- W3151722529
- Cited by
- 52
- References
- 14
- FWCI
- 4.20
- Type
- conference paper
- Language
- en
- Open access
- gold
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
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.