---
title: "AI2-THOR: An Interactive 3D Environment for Visual AI (2017)"
description: "The platform offers near photo-realistic indoor scenes built in the Unity engine and controlled… 45 references, cited by 142 papers here."
authors: ["Eric Kolve", "Roozbeh Mottaghi", "Winson Han", "Eli VanderBilt", "Luca Weihs", "Alvaro Herrasti", "Matt Deitke", "Kiana Ehsani", "Daniel Gordon", "Yuke Zhu", "Aniruddha Kembhavi", "Abhinav Gupta", "Ali Farhadi"]
year: 2017
venue: "arXiv:1712.05474"
source: "https://arxiv.org/abs/1712.05474"
doi: "10.48550/arxiv.1712.05474"
arxiv: "1712.05474"
licence: "arXiv — non-exclusive licence to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/kolve-2017-ai2-thor-interactive-3d-environment/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kolve-2017-ai2-thor-interactive-3d-environment/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/) / AI2-THOR: An Interactive 3D Environment for Visual AI

# AI2-THOR: An Interactive 3D Environment for Visual AI

**Authors:** [Eric Kolve](https://md.research.elamur.ai/free/en/authors/eric-kolve/), [Roozbeh Mottaghi](https://md.research.elamur.ai/free/en/authors/roozbeh-mottaghi/), Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, [Matt Deitke](https://md.research.elamur.ai/free/en/authors/matt-deitke/), Kiana Ehsani, Daniel Gordon, [Yuke Zhu](https://md.research.elamur.ai/free/en/authors/yuke-zhu/), [Aniruddha Kembhavi](https://md.research.elamur.ai/free/en/authors/aniruddha-kembhavi/), [Abhinav Gupta](https://md.research.elamur.ai/free/en/authors/abhinav-gupta/) and [Ali Farhadi](https://md.research.elamur.ai/free/en/authors/ali-farhadi/) · **Year:** 2017 · **Venue:** arXiv:1712.05474 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/1712.05474) · [PDF](https://arxiv.org/pdf/1712.05474) · [DOI 10.48550/arxiv.1712.05474](https://doi.org/10.48550/arxiv.1712.05474) · [arXiv 1712.05474](https://arxiv.org/abs/1712.05474) · [OpenAlex](https://openalex.org/W2776202271)

**Citations:** 279 citations (OpenAlex, 2026-10-14) · [142](https://md.research.elamur.ai/free/en/papers/kolve-2017-ai2-thor-interactive-3d-environment/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
AI2-THOR, developed mainly at the Allen Institute for AI, is a simulation platform for embodied and visual AI. Its motivation is that mainstream vision models learn from static images or video, while humans learn by acting in the world. Physical robots, on the other hand, are slow, costly and sometimes unsafe to train at scale. The platform offers near photo-realistic indoor scenes built in the Unity engine and controlled through a Python API. Agents with different embodiments can move around, handle objects with an arm or through high-level abstract commands, and trigger state changes and chain reactions, such as slicing bread and then toasting it. Every step returns rendered images in several modalities along with detailed metadata, which researchers typically use to build rewards, imitation experts and datasets. Scene collections range from rooms crafted by artists to procedurally generated houses. Compared with iGibson 2.0, Habitat and SAPIEN, AI2-THOR leads in scale and interactivity, although its training throughput is somewhat lower than Habitat 1.0. It has served as the testbed for more than 150 publications.

## Key points
- Scene datasets: iTHOR has 120 hand-modeled rooms (kitchens, bedrooms, bathrooms, living rooms). RoboTHOR has 89 apartment-style scenes, many rebuilt physically in Seattle for sim2real studies. ProcTHOR-10K contains 10,000 procedurally generated houses. ArchitecTHOR provides 10 large evaluation houses, split 5 for validation and 5 for testing.
- Agents: ManipulaTHOR and StretchRE1 support arm manipulation, while LoCoBot, Abstract and Drone handle navigation and abstracted interaction. Actions fall into four groups: navigation, interaction, environment queries and environment state changes.
- The object database holds 3,578 interactive objects. Rendered outputs include color (RGB) images, depth maps, segmentation masks at both the class and instance level, and surface normals.
- Pre-training only on ProcTHOR achieved state-of-the-art ObjectNav results on RoboTHOR, iTHOR and ArchitecTHOR without any extra training data.
- Benchmark: an ObjectNav agent was trained for 1M steps on 2 GPUs.
  - AI2-THOR averaged 167.7 training FPS (range 145.5–179.4).
  - Habitat 1.0 averaged 230.5 FPS (range 119.7–264.3).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [Stanford University](https://md.research.elamur.ai/free/en/universities/stanford-university/) — University, Stanford, United States · 506 works · 330,053 citations
- [Carnegie Mellon University](https://md.research.elamur.ai/free/en/universities/carnegie-mellon-university/) — University, Pittsburgh, United States · 598 works · 191,226 citations
- [University of Washington](https://md.research.elamur.ai/free/en/universities/university-of-washington/) — University, Seattle, United States · 402 works · 212,763 citations
- [Allen Institute for Artificial Intelligence](https://md.research.elamur.ai/free/en/labs/allen-institute-for-artificial-intelligence/) — Research institute, Seattle, United States · 304 works · 106,137 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [⚙️ Control and Systems Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/control-and-systems-engineering/) · 62 works

## Cite

Cite as: Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Matt Deitke, Kiana Ehsani, Daniel Gordon, Yuke Zhu, Aniruddha Kembhavi, Abhinav Gupta and Ali Farhadi. 2017. AI2-THOR: An Interactive 3D Environment for Visual AI. arXiv:1712.05474.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{kolve2017ai2,
  title = {{AI2-THOR: An Interactive 3D Environment for Visual AI}},
  author = {Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Matt Deitke, Kiana Ehsani, Daniel Gordon, Yuke Zhu, Aniruddha Kembhavi, Abhinav Gupta and Ali Farhadi},
  year = {2017},
  doi = {10.48550/arxiv.1712.05474},
  eprint = {1712.05474},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.1712.05474}
}
```

- [← previous Gender and Dialect Bias in YouTube's Automatic Captions](https://md.research.elamur.ai/free/en/papers/tatman-2017-gender-dialect-bias-youtube-s/)
- [next → Hindsight Experience Replay](https://md.research.elamur.ai/free/en/papers/andrychowicz-2017-hindsight-experience-replay/)
- [↑ back to papers of 2017](https://md.research.elamur.ai/free/en/papers/2017/page/2/)

## References

45 references, 2 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Matt Deitke, Winson Han, Alvaro Herrasti, Aniruddha Kembhavi, Eric Kolve, Roozbeh Mottaghi, Jordi Salvador, Dustin Schwenk, Eli VanderBilt, Matthew Wallingford, Luca Weihs, Mark Yatskar, and Ali Farhadi. Robothor: An open simulation-to-real embodied ai platform. In CVPR, 2020. 2, 3, 6, 7 [find](https://scholar.google.com/scholar?q=Matt+Deitke%2C+Winson+Han%2C+Alvaro+Herrasti%2C+Aniruddha+Kembhavi%2C+Eric+Kolve%2C+Roozbeh+Mottaghi%2C+Jordi+Salvador%2C+Dustin+Schwenk%2C+Eli+VanderBilt%2C+Matthew+Wallingford%2C+Luca+Weihs%2C+Mark+Yatskar%2C+and+Ali+Farha)
2. Matt Deitke, Eli VanderBilt, Alvaro Herrasti, Luca Weihs, Jordi Salvador, Kiana Ehsani, Winson Han, Eric Kolve, Ali Farhadi, Aniruddha Kembhavi, and Roozbeh Mottaghi. Procthor: Large-scale embodied ai using procedural generation. arXiv, 2022. 2, 3, 6, 7, 8, 12 [find](https://scholar.google.com/scholar?q=Matt+Deitke%2C+Eli+VanderBilt%2C+Alvaro+Herrasti%2C+Luca+Weihs%2C+Jordi+Salvador%2C+Kiana+Ehsani%2C+Winson+Han%2C+Eric+Kolve%2C+Ali+Farhadi%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+Procthor%3A+Large%2Dscale+embodied+ai)
3. Heming Du, Xin Yu, and Liang Zheng. Learning object relation graph and tentative policy for visual navigation. In ECCV, 2020. 6 [find](https://scholar.google.com/scholar?q=Heming+Du%2C+Xin+Yu%2C+and+Liang+Zheng%2E+Learning+object+relation+graph+and+tentative+policy+for+visual+navigation%2E+In+ECCV%2C+2020%2E+6)
4. Kshitij Dwivedi, Gemma Roig, Aniruddha Kembhavi, and Roozbeh Mottaghi. What do navigation agents learn about their environment? In CVPR, 2022. 7, 8 [find](https://scholar.google.com/scholar?q=Kshitij+Dwivedi%2C+Gemma+Roig%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+What+do+navigation+agents+learn+about+their+environment%3F+In+CVPR%2C+2022%2E+7%2C+8)
5. Kiana Ehsani, Winson Han, Alvaro Herrasti, Eli VanderBilt, Luca Weihs, Eric Kolve, Aniruddha Kembhavi, and Roozbeh Mottaghi. Manipulathor: A framework for visual object manipulation. In CVPR, 2021. 3, 8 [find](https://scholar.google.com/scholar?q=Kiana+Ehsani%2C+Winson+Han%2C+Alvaro+Herrasti%2C+Eli+VanderBilt%2C+Luca+Weihs%2C+Eric+Kolve%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+Manipulathor%3A+A+framework+for+visual+object+manipulation%2E+In+CVPR%2C+2021%2E+3%2C)
6. Kiana Ehsani, Roozbeh Mottaghi, and Ali Farhadi. Segan: Segmenting and generating the invisible. In CVPR, 2018. 8 [find](https://scholar.google.com/scholar?q=Kiana+Ehsani%2C+Roozbeh+Mottaghi%2C+and+Ali+Farhadi%2E+Segan%3A+Segmenting+and+generating+the+invisible%2E+In+CVPR%2C+2018%2E+8)
7. Chuang Gan, Jeremy Schwartz, Seth Alter, Martin Schrimpf, James Traer, Julian De Freitas, Jonas Kubilius, Abhishek Bhandwaldar, Nick Haber, Megumi Sano, et al. Threedworld: A platform for interactive multi-modal physical simulation. In Neural Information Processing Systems Datasets and Benchmarks Tr… [find](https://scholar.google.com/scholar?q=Chuang+Gan%2C+Jeremy+Schwartz%2C+Seth+Alter%2C+Martin+Schrimpf%2C+James+Traer%2C+Julian+De+Freitas%2C+Jonas+Kubilius%2C+Abhishek+Bhandwaldar%2C+Nick+Haber%2C+Megumi+Sano%2C+et+al%2E+Threedworld%3A+A+platform+for+interactive+)
8. Chuang Gan, Yiwei Zhang, Jiajun Wu, Boqing Gong, and Joshua B Tenenbaum. Look, listen, and act: Towards audio-visual embodied navigation. In ICRA, 2020. 6, 7 [find](https://scholar.google.com/scholar?q=Chuang+Gan%2C+Yiwei+Zhang%2C+Jiajun+Wu%2C+Boqing+Gong%2C+and+Joshua+B+Tenenbaum%2E+Look%2C+listen%2C+and+act%3A+Towards+audio%2Dvisual+embodied+navigation%2E+In+ICRA%2C+2020%2E+6%2C+7)
9. Xiaofeng Gao, Qiaozi Gao, Ran Gong, Kaixiang Lin, Govind Thattai, and Gaurav S Sukhatme. Dialfred: Dialogue-enabled agents for embodied instruction following. IEEE Robotics and Automation Letters, 2022. 6 [find](https://scholar.google.com/scholar?q=Xiaofeng+Gao%2C+Qiaozi+Gao%2C+Ran+Gong%2C+Kaixiang+Lin%2C+Govind+Thattai%2C+and+Gaurav+S+Sukhatme%2E+Dialfred%3A+Dialogue%2Denabled+agents+for+embodied+instruction+following%2E+IEEE+Robotics+and+Automation+Letters%2C+202)
10. Daniel Gordon, Aniruddha Kembhavi, Mohammad Rastegari, Joseph Redmon, Dieter Fox, and Ali Farhadi. Iqa: Visual question answering in interactive environments. In CVPR, 2018. 6 [find](https://scholar.google.com/scholar?q=Daniel+Gordon%2C+Aniruddha+Kembhavi%2C+Mohammad+Rastegari%2C+Joseph+Redmon%2C+Dieter+Fox%2C+and+Ali+Farhadi%2E+Iqa%3A+Visual+question+answering+in+interactive+environments%2E+In+CVPR%2C+2018%2E+6)
11. Unnat Jain, Luca Weihs, Eric Kolve, Ali Farhadi, Svetlana Lazebnik, Aniruddha Kembhavi, and Alexander G. Schwing. A cordial sync: Going beyond marginal policies for multi-agent embodied tasks. In ECCV, 2020. 6 [find](https://scholar.google.com/scholar?q=Unnat+Jain%2C+Luca+Weihs%2C+Eric+Kolve%2C+Ali+Farhadi%2C+Svetlana+Lazebnik%2C+Aniruddha+Kembhavi%2C+and+Alexander+G%2E+Schwing%2E+A+cordial+sync%3A+Going+beyond+marginal+policies+for+multi%2Dagent+embodied+tasks%2E+In+ECCV)
12. Unnat Jain, Luca Weihs, Eric Kolve, Mohammad Rastegari, Svetlana Lazebnik, Ali Farhadi, Alexander G. Schwing, and Aniruddha Kembhavi. Two body problem: Collaborative visual task completion. In CVPR, 2019. 6, 7 [find](https://scholar.google.com/scholar?q=Unnat+Jain%2C+Luca+Weihs%2C+Eric+Kolve%2C+Mohammad+Rastegari%2C+Svetlana+Lazebnik%2C+Ali+Farhadi%2C+Alexander+G%2E+Schwing%2C+and+Aniruddha+Kembhavi%2E+Two+body+problem%3A+Collaborative+visual+task+completion%2E+In+CVPR%2C+2)
13. Siddharth Karamcheti, Dorsa Sadigh, and Percy Liang. Learning adaptive language interfaces through decomposition. arXiv, 2020. 6 [find](https://scholar.google.com/scholar?q=Siddharth+Karamcheti%2C+Dorsa+Sadigh%2C+and+Percy+Liang%2E+Learning+adaptive+language+interfaces+through+decomposition%2E+arXiv%2C+2020%2E+6)
14. Charles C Kemp, Aaron Edsinger, Henry M Clever, and Blaine Matulevich. The design of stretch: A compact, lightweight mobile manipulator for indoor human environments. In ICRA, 2022. 3 [find](https://scholar.google.com/scholar?q=Charles+C+Kemp%2C+Aaron+Edsinger%2C+Henry+M+Clever%2C+and+Blaine+Matulevich%2E+The+design+of+stretch%3A+A+compact%2C+lightweight+mobile+manipulator+for+indoor+human+environments%2E+In+ICRA%2C+2022%2E+3)
15. Apoorv Khandelwal, Luca Weihs, Roozbeh Mottaghi, and Aniruddha Kembhavi. Simple but effective: Clip embeddings for embodied ai. In CVPR, 2022. 6 [find](https://scholar.google.com/scholar?q=Apoorv+Khandelwal%2C+Luca+Weihs%2C+Roozbeh+Mottaghi%2C+and+Aniruddha+Kembhavi%2E+Simple+but+effective%3A+Clip+embeddings+for+embodied+ai%2E+In+CVPR%2C+2022%2E+6)
16. Klemen Kotar, Gabriel Ilharco, Ludwig Schmidt, Kiana Ehsani, and Roozbeh Mottaghi. Contrasting contrastive self-supervised representation learning pipelines. In ICCV, 2021. 8 [find](https://scholar.google.com/scholar?q=Klemen+Kotar%2C+Gabriel+Ilharco%2C+Ludwig+Schmidt%2C+Kiana+Ehsani%2C+and+Roozbeh+Mottaghi%2E+Contrasting+contrastive+self%2Dsupervised+representation+learning+pipelines%2E+In+ICCV%2C+2021%2E+8)
17. Klemen Kotar and Roozbeh Mottaghi. Interactron: Embodied adaptive object detection. In CVPR, 2022. 7, 8 [find](https://scholar.google.com/scholar?q=Klemen+Kotar+and+Roozbeh+Mottaghi%2E+Interactron%3A+Embodied+adaptive+object+detection%2E+In+CVPR%2C+2022%2E+7%2C+8)
18. Chengshu Li, Fei Xia, Roberto Martín-Martín, Michael Lingelbach, Sanjana Srivastava, Bokui Shen, Kent Elliott Vainio, Cem Gokmen, Gokul Dharan, Tanish Jain, Andrey Kurenkov, Karen Liu, Hyowon Gweon, Jiajun Wu, Li Fei-Fei, and Silvio Savarese. igibson 2.0: Object-centric simulation for robot learning… [find](https://scholar.google.com/scholar?q=Chengshu+Li%2C+Fei+Xia%2C+Roberto+Mart%C3%ADn%2DMart%C3%ADn%2C+Michael+Lingelbach%2C+Sanjana+Srivastava%2C+Bokui+Shen%2C+Kent+Elliott+Vainio%2C+Cem+Gokmen%2C+Gokul+Dharan%2C+Tanish+Jain%2C+Andrey+Kurenkov%2C+Karen+Liu%2C+Hyowon+Gweon%2C+J)
19. Qi Li, Kaichun Mo, Yanchao Yang, Hang Zhao, and Leonidas Guibas. Ifr-explore: Learning inter-object functional relationships in 3d indoor scenes. In ICLR, 2022. 7 [find](https://scholar.google.com/scholar?q=Qi+Li%2C+Kaichun+Mo%2C+Yanchao+Yang%2C+Hang+Zhao%2C+and+Leonidas+Guibas%2E+Ifr%2Dexplore%3A+Learning+inter%2Dobject+functional+relationships+in+3d+indoor+scenes%2E+In+ICLR%2C+2022%2E+7)
20. Xinzhu Liu, Di Guo, Huaping Liu, and Fuchun Sun. Multi-agent embodied visual semantic navigation with scene prior knowledge. IEEE Robotics and Automation Letters, 2022. 6 [find](https://scholar.google.com/scholar?q=Xinzhu+Liu%2C+Di+Guo%2C+Huaping+Liu%2C+and+Fuchun+Sun%2E+Multi%2Dagent+embodied+visual+semantic+navigation+with+scene+prior+knowledge%2E+IEEE+Robotics+and+Automation+Letters%2C+2022%2E+6)
21. Martin Lohmann, Jordi Salvador, Aniruddha Kembhavi, and Roozbeh Mottaghi. Learning about objects by learning to interact with them. In NeurIPS, 2020. 8 [find](https://scholar.google.com/scholar?q=Martin+Lohmann%2C+Jordi+Salvador%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+Learning+about+objects+by+learning+to+interact+with+them%2E+In+NeurIPS%2C+2020%2E+8)
22. Yi Lu, Yaran Chen, Dongbin Zhao, and Dong Li. Mgrl: Graph neural network based inference in a markov network with reinforcement learning for visual navigation. Neurocomputing, 2021. 6 [find](https://scholar.google.com/scholar?q=Yi+Lu%2C+Yaran+Chen%2C+Dongbin+Zhao%2C+and+Dong+Li%2E+Mgrl%3A+Graph+neural+network+based+inference+in+a+markov+network+with+reinforcement+learning+for+visual+navigation%2E+Neurocomputing%2C+2021%2E+6)
23. So Yeon Min, Devendra Singh Chaplot, Pradeep Ravikumar, Yonatan Bisk, and Ruslan Salakhutdinov. Film: Following instructions in language with modular methods. In ICLR, 2022. 6 [find](https://scholar.google.com/scholar?q=So+Yeon+Min%2C+Devendra+Singh+Chaplot%2C+Pradeep+Ravikumar%2C+Yonatan+Bisk%2C+and+Ruslan+Salakhutdinov%2E+Film%3A+Following+instructions+in+language+with+modular+methods%2E+In+ICLR%2C+2022%2E+6)
24. Adithyavairavan Murali, Tao Chen, Kalyan Vasudev Alwala, Dhiraj Gandhi, Lerrel Pinto, Saurabh Gupta, and Abhinav Gupta. Pyrobot: An open-source robotics framework for research and benchmarking. arXiv, 2019. 3 [find](https://scholar.google.com/scholar?q=Adithyavairavan+Murali%2C+Tao+Chen%2C+Kalyan+Vasudev+Alwala%2C+Dhiraj+Gandhi%2C+Lerrel+Pinto%2C+Saurabh+Gupta%2C+and+Abhinav+Gupta%2E+Pyrobot%3A+An+open%2Dsource+robotics+framework+for+research+and+benchmarking%2E+arXiv%2C)
25. Tushar Nagarajan and Kristen Grauman. Learning affordance landscapes for interaction exploration in 3d environments. In NeurIPS, 2020. 7 [find](https://scholar.google.com/scholar?q=Tushar+Nagarajan+and+Kristen+Grauman%2E+Learning+affordance+landscapes+for+interaction+exploration+in+3d+environments%2E+In+NeurIPS%2C+2020%2E+7)
26. Tushar Nagarajan and Kristen Grauman. Shaping embodied agent behavior with activity-context priors from egocentric video. In NeurIPS, 2021. 7 [find](https://scholar.google.com/scholar?q=Tushar+Nagarajan+and+Kristen+Grauman%2E+Shaping+embodied+agent+behavior+with+activity%2Dcontext+priors+from+egocentric+video%2E+In+NeurIPS%2C+2021%2E+7)
27. Aishwarya Padmakumar, Jesse Thomason, Ayush Shrivastava, Patrick Lange, Anjali Narayan-Chen, Spandana Gella, Robinson Piramuthu, Gokhan Tur, and Dilek Hakkani-Tur. Teach: Task-driven embodied agents that chat. In AAAI, 2022. 6, 7 [find](https://scholar.google.com/scholar?q=Aishwarya+Padmakumar%2C+Jesse+Thomason%2C+Ayush+Shrivastava%2C+Patrick+Lange%2C+Anjali+Narayan%2DChen%2C+Spandana+Gella%2C+Robinson+Piramuthu%2C+Gokhan+Tur%2C+and+Dilek+Hakkani%2DTur%2E+Teach%3A+Task%2Ddriven+embodied+agents+t)
28. Alexander Pashevich, Cordelia Schmid, and Chen Sun. Episodic transformer for vision-and-language navigation. In ICCV, 2021. 6 [find](https://scholar.google.com/scholar?q=Alexander+Pashevich%2C+Cordelia+Schmid%2C+and+Chen+Sun%2E+Episodic+transformer+for+vision%2Dand%2Dlanguage+navigation%2E+In+ICCV%2C+2021%2E+6)
29. Santhosh Kumar Ramakrishnan, Aaron Gokaslan, Erik Wijmans, Oleksandr Maksymets, Alexander Clegg, John M Turner, Eric Undersander, Wojciech Galuba, Andrew Westbury, Angel X Chang, Manolis Savva, Yili Zhao, and Dhruv Batra. Habitat-matterport 3d dataset (HM3d): 1000 large-scale 3d environments for emb… [find](https://scholar.google.com/scholar?q=Santhosh+Kumar+Ramakrishnan%2C+Aaron+Gokaslan%2C+Erik+Wijmans%2C+Oleksandr+Maksymets%2C+Alexander+Clegg%2C+John+M+Turner%2C+Eric+Undersander%2C+Wojciech+Galuba%2C+Andrew+Westbury%2C+Angel+X+Chang%2C+Manolis+Savva%2C+Yili+Z)
30. Manolis Savva, Abhishek Kadian, Oleksandr Maksymets, Yili Zhao, Erik Wijmans, Bhavana Jain, Julian Straub, Jia Liu, Vladlen Koltun, Jitendra Malik, Devi Parikh, and Dhruv Batra. [Habitat: A platform for embodied ai research](https://md.research.elamur.ai/free/en/papers/savva-2019-habitat-platform-embodied-ai-research/). In ICCV, 2019. 8
31. Mohit Shridhar, Jesse Thomason, Daniel Gordon, Yonatan Bisk, Winson Han, Roozbeh Mottaghi, Luke Zettlemoyer, and Dieter Fox. [Alfred: A benchmark for interpreting grounded instructions for everyday tasks](https://md.research.elamur.ai/free/en/papers/shridhar-2019-alfred-benchmark-interpreting-grounded-instructions/). In CVPR, 2020. 6, 7
32. Andrew Szot, Alexander Clegg, Eric Undersander, Erik Wijmans, Yili Zhao, John Turner, Noah Maestre, Mustafa Mukadam, Devendra Singh Chaplot, Oleksandr Maksymets, Aaron Gokaslan, Vladimir Vondrus, Sameer Dharur, Franziska Meier, Wojciech Galuba, Angel X. Chang, Zsolt Kira, Vladlen Koltun, Jitendra Ma… [find](https://scholar.google.com/scholar?q=Andrew+Szot%2C+Alexander+Clegg%2C+Eric+Undersander%2C+Erik+Wijmans%2C+Yili+Zhao%2C+John+Turner%2C+Noah+Maestre%2C+Mustafa+Mukadam%2C+Devendra+Singh+Chaplot%2C+Oleksandr+Maksymets%2C+Aaron+Gokaslan%2C+Vladimir+Vondrus%2C+Same)
33. Sinan Tan, Weilai Xiang, Huaping Liu, Di Guo, and Fuchun Sun. Multi-agent embodied question answering in interactive environments. In ECCV, 2020. 6 [find](https://scholar.google.com/scholar?q=Sinan+Tan%2C+Weilai+Xiang%2C+Huaping+Liu%2C+Di+Guo%2C+and+Fuchun+Sun%2E+Multi%2Dagent+embodied+question+answering+in+interactive+environments%2E+In+ECCV%2C+2020%2E+6)
34. Luca Weihs, Matt Deitke, Aniruddha Kembhavi, and Roozbeh Mottaghi. Visual room rearrangement. In CVPR, 2021. 7, 8 [find](https://scholar.google.com/scholar?q=Luca+Weihs%2C+Matt+Deitke%2C+Aniruddha+Kembhavi%2C+and+Roozbeh+Mottaghi%2E+Visual+room+rearrangement%2E+In+CVPR%2C+2021%2E+7%2C+8)
35. Luca Weihs, Aniruddha Kembhavi, Kiana Ehsani, Sarah M Pratt, Winson Han, Alvaro Herrasti, Eric Kolve, Dustin Schwenk, Roozbeh Mottaghi, and Ali Farhadi. Learning generalizable visual representations via interactive gameplay. In ICLR, 2021. 6, 8 [find](https://scholar.google.com/scholar?q=Luca+Weihs%2C+Aniruddha+Kembhavi%2C+Kiana+Ehsani%2C+Sarah+M+Pratt%2C+Winson+Han%2C+Alvaro+Herrasti%2C+Eric+Kolve%2C+Dustin+Schwenk%2C+Roozbeh+Mottaghi%2C+and+Ali+Farhadi%2E+Learning+generalizable+visual+representations+v)
36. Luca Weihs, Jordi Salvador, Klemen Kotar, Unnat Jain, Kuo-Hao Zeng, Roozbeh Mottaghi, and Aniruddha Kembhavi. Allenact: A framework for embodied AI research. arXiv, 2020. 11 [find](https://scholar.google.com/scholar?q=Luca+Weihs%2C+Jordi+Salvador%2C+Klemen+Kotar%2C+Unnat+Jain%2C+Kuo%2DHao+Zeng%2C+Roozbeh+Mottaghi%2C+and+Aniruddha+Kembhavi%2E+Allenact%3A+A+framework+for+embodied+AI+research%2E+arXiv%2C+2020%2E+11)
37. Mitchell Wortsman, Kiana Ehsani, Mohammad Rastegari, Ali Farhadi, and Roozbeh Mottaghi. Learning to learn how to learn: Self-adaptive visual navigation using meta-learning. In CVPR, 2019. 6 [find](https://scholar.google.com/scholar?q=Mitchell+Wortsman%2C+Kiana+Ehsani%2C+Mohammad+Rastegari%2C+Ali+Farhadi%2C+and+Roozbeh+Mottaghi%2E+Learning+to+learn+how+to+learn%3A+Self%2Dadaptive+visual+navigation+using+meta%2Dlearning%2E+In+CVPR%2C+2019%2E+6)
38. Qi Wu, Cheng-Ju Wu, Yixin Zhu, and Jungseock Joo. Communicative learning with natural gestures for embodied navigation agents with human-in-the-scene. In IROS, 2021. 6, 7 [find](https://scholar.google.com/scholar?q=Qi+Wu%2C+Cheng%2DJu+Wu%2C+Yixin+Zhu%2C+and+Jungseock+Joo%2E+Communicative+learning+with+natural+gestures+for+embodied+navigation+agents+with+human%2Din%2Dthe%2Dscene%2E+In+IROS%2C+2021%2E+6%2C+7)
39. Fanbo Xiang, Yuzhe Qin, Kaichun Mo, Yikuan Xia, Hao Zhu, Fangchen Liu, Minghua Liu, Hanxiao Jiang, Yifu Yuan, He Wang, Li Yi, Angel X. Chang, Leonidas J. Guibas, and Hao Su. Sapien: A simulated part-based interactive environment. In CVPR, 2020. 8 [find](https://scholar.google.com/scholar?q=Fanbo+Xiang%2C+Yuzhe+Qin%2C+Kaichun+Mo%2C+Yikuan+Xia%2C+Hao+Zhu%2C+Fangchen+Liu%2C+Minghua+Liu%2C+Hanxiao+Jiang%2C+Yifu+Yuan%2C+He+Wang%2C+Li+Yi%2C+Angel+X%2E+Chang%2C+Leonidas+J%2E+Guibas%2C+and+Hao+Su%2E+Sapien%3A+A+simulated+part%2Db)
40. Wei Yang, Xiaolong Wang, Ali Farhadi, Abhinav Gupta, and Roozbeh Mottaghi. Visual semantic navigation using scene priors. In ICLR, 2019. 6 [find](https://scholar.google.com/scholar?q=Wei+Yang%2C+Xiaolong+Wang%2C+Ali+Farhadi%2C+Abhinav+Gupta%2C+and+Roozbeh+Mottaghi%2E+Visual+semantic+navigation+using+scene+priors%2E+In+ICLR%2C+2019%2E+6)
41. Rowan Zellers, Ari Holtzman, Matthew E. Peters, Roozbeh Mottaghi, Aniruddha Kembhavi, Ali Farhadi, and Yejin Choi. Piglet: Language grounding through neuro-symbolic interaction in a 3d world. In ACL, 2021. 6 [find](https://scholar.google.com/scholar?q=Rowan+Zellers%2C+Ari+Holtzman%2C+Matthew+E%2E+Peters%2C+Roozbeh+Mottaghi%2C+Aniruddha+Kembhavi%2C+Ali+Farhadi%2C+and+Yejin+Choi%2E+Piglet%3A+Language+grounding+through+neuro%2Dsymbolic+interaction+in+a+3d+world%2E+In+ACL%2C+)
42. Kuo-Hao Zeng, Roozbeh Mottaghi, Luca Weihs, and Ali Farhadi. Visual reaction: Learning to play catch with your drone. In CVPR, 2020. 3 [find](https://scholar.google.com/scholar?q=Kuo%2DHao+Zeng%2C+Roozbeh+Mottaghi%2C+Luca+Weihs%2C+and+Ali+Farhadi%2E+Visual+reaction%3A+Learning+to+play+catch+with+your+drone%2E+In+CVPR%2C+2020%2E+3)
43. Yizhou Zhao, Kaixiang Lin, Zhiwei Jia, Qiaozi Gao, Govind Thattai, Jesse Thomason, and Gaurav S Sukhatme. Luminous: Indoor scene generation for embodied ai challenges. arXiv, 2021. 8 [find](https://scholar.google.com/scholar?q=Yizhou+Zhao%2C+Kaixiang+Lin%2C+Zhiwei+Jia%2C+Qiaozi+Gao%2C+Govind+Thattai%2C+Jesse+Thomason%2C+and+Gaurav+S+Sukhatme%2E+Luminous%3A+Indoor+scene+generation+for+embodied+ai+challenges%2E+arXiv%2C+2021%2E+8)
44. Kaiyu Zheng, Rohan Chitnis, Yoonchang Sung, George Konidaris, and Stefanie Tellex. Towards optimal correlational object search. In ICRA, 2022. 6 [find](https://scholar.google.com/scholar?q=Kaiyu+Zheng%2C+Rohan+Chitnis%2C+Yoonchang+Sung%2C+George+Konidaris%2C+and+Stefanie+Tellex%2E+Towards+optimal+correlational+object+search%2E+In+ICRA%2C+2022%2E+6)
45. Yuke Zhu, Roozbeh Mottaghi, Eric Kolve, Joseph J Lim, Abhinav Gupta, Li Fei-Fei, and Ali Farhadi. Target-driven visual navigation in indoor scenes using deep reinforcement learning. In ICRA, 2017. 6, 7, 11 [find](https://scholar.google.com/scholar?q=Yuke+Zhu%2C+Roozbeh+Mottaghi%2C+Eric+Kolve%2C+Joseph+J+Lim%2C+Abhinav+Gupta%2C+Li+Fei%2DFei%2C+and+Ali+Farhadi%2E+Target%2Ddriven+visual+navigation+in+indoor+scenes+using+deep+reinforcement+learning%2E+In+ICRA%2C+2017%2E+6%2C+)

*Updated 2 November 2026*