Preprint · 2022 · Open access

Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots

Jagdeep Singh Bhatia, Holly Jackson, Yunsheng Tian, Jie Xu, Wojciech Matusik

arXiv (Cornell University), 34 · Published 24 January 2022 · DOI 10.48550/arxiv.2201.09863

Open PDFView at the publisherCite this paper

In brief

“Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots” is a 2022 preprint by Jagdeep Singh Bhatia and 4 co-authors, published in arXiv (Cornell University). OpenAlex counts 95 citations as of 22 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
95
Most cited in
2024 (29)
References
38
Authors
5

Abstract

Both the design and control of a robot play equally important roles in its task performance. However, while optimal control is well studied in the machine learning and robotics community, less attention is placed on finding the optimal robot design. This is mainly because co-optimizing design and control in robotics is characterized as a challenging problem, and more importantly, a comprehensive evaluation benchmark for co-optimization does not exist. In this paper, we propose Evolution Gym, the first large-scale benchmark for co-optimizing the design and control of soft robots. In our benchmark, each robot is composed of different types of voxels (e.g., soft, rigid, actuators), resulting in a modular and expressive robot design space. Our benchmark environments span a wide range of tasks, including locomotion on various types of terrains and manipulation. Furthermore, we develop several robot co-evolution algorithms by combining state-of-the-art design optimization methods and deep reinforcement learning techniques. Evaluating the algorithms on our benchmark platform, we observe robots exhibiting increasingly complex behaviors as evolution progresses, with the best evolved designs solving many of our proposed tasks. Additionally, even though robot designs are evolved autonomously from scratch without prior knowledge, they often grow to resemble existing natural creatures while outperforming hand-designed robots. Nevertheless, all tested algorithms fail to find robots that succeed in our hardest environments. This suggests that more advanced algorithms are required to explore the high-dimensional design space and evolve increasingly intelligent robots -- an area of research in which we hope Evolution Gym will accelerate progress. Our website with code, environments, documentation, and tutorials is available at http://evogym.csail.mit.edu.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Bhatia, J. S., Jackson, H., Tian, Y., Xu, J., & Matusik, W. (2022). Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2201.09863

MLA 9

Bhatia, Jagdeep Singh, et al. “Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots.” arXiv (Cornell University), vol. 34, 2022. https://doi.org/10.48550/arxiv.2201.09863.

Chicago

Bhatia, Jagdeep Singh, Holly Jackson, Yunsheng Tian, Jie Xu, and Wojciech Matusik. 2022. “Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots.” arXiv (Cornell University) 34. https://doi.org/10.48550/arxiv.2201.09863.

Harvard

Bhatia, J. S. et al. (2022) ‘Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots’, arXiv (Cornell University), 34. doi:10.48550/arxiv.2201.09863.

IEEE

J. S. Bhatia, H. Jackson, Y. Tian, J. Xu, and W. Matusik, “Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots,” arXiv (Cornell University), vol. 34, 2022, doi: 10.48550/arxiv.2201.09863.

BibTeX

@misc{bhatia2022evolution,
  title     = {{Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots}},
  author    = {Bhatia, Jagdeep Singh and Jackson, Holly and Tian, Yunsheng and Xu, Jie and Matusik, Wojciech},
  howpublished = {arXiv (Cornell University)},
  year      = {2022},
  volume    = {34},
  doi       = {10.48550/arxiv.2201.09863},
  url       = {https://doi.org/10.48550/arxiv.2201.09863}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20221414
20232222
20242929
20251717
20261313

Topic and keywords

Physical Sciences › Engineering › Biomedical Engineering › Soft Robotics and Applications

  • soft robots
  • robot design optimization
  • benchmark
  • coevolution
  • deep reinforcement learning
  • manipulation

Work with this paper

Most-cited papers in Engineering

All highly cited Engineering papers

Questions about this paper

How do I cite this paper in APA style?

Bhatia, J. S., Jackson, H., Tian, Y., Xu, J., & Matusik, W. (2022). Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots. arXiv (Cornell University), 34. https://doi.org/10.48550/arxiv.2201.09863

How many times has this paper been cited?

95 times, according to OpenAlex on 22 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Jagdeep Singh Bhatia, Holly Jackson, Yunsheng Tian, Jie Xu, Wojciech Matusik.

What is the DOI of this paper?

10.48550/arxiv.2201.09863, permanently at https://doi.org/10.48550/arxiv.2201.09863. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 22 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.