Evolving virtual creatures
Abstract
This paper describes a novel system for creating virtual creatures that move and behave in simulated three-dimensional physical worlds. The morphologies of creatures and the neural systems for controlling their muscle forces are both generated automatically using genetic algorithms. Different fitness evaluation functions are used to direct simulated evolutions towards specific behaviors such as swimming, walking, jumping, and following. A genetic language is presented that uses nodes and connections as its primitive elements to represent directed graphs, which are used to describe both the morphology and the neural circuitry of these creatures. This genetic language defines a hyperspace containing an indefinite number of possible creatures with behaviors, and when it is searched using optimization techniques, a variety of successful and interesting locomotion strategies emerge, some of which would be difficult to invent or build by design. 1
Integrity signals
Registry
Cites
Statistics
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?
The classic 'Evolved Synthetic Creatures' co-evolved agent morphology and neural controllers in a simulated 3D world, leading to the discovery of a wide variety of novel and effective locomotion strategies.
“For example, the classic”
From A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence (2025) · cites this paper as Sims, 1994
Cites
Artificial evolution for computer graphics
Sims, K. (1991) · Proceedings of the 18th annual conference on Computer graphics and interactive techniques · doi:10.1145/122718.122752 · Cited by 741 · see citing works
Self-citation
Flagged first, then by citations
Cited by
Sorted by citations
Deep learning in neural networks: an overview
Schmidhuber, J. (2015) · Neural Networks · doi:10.1016/j.neunet.2014.09.003 · Cited by 18,570 · see citing works
MuJoCo: A physics engine for model-based control
Todorov, E., Erez, T., & Tassa, Y. (2012) · 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems · doi:10.1109/iros.2012.6386109 · Cited by 4,767 · see citing works
Emergent Tool Use From Multi-Agent Autocurricula
Baker, B., Kanitscheider, I., Markov, T., Wu, Y., Powell, G., McGrew, B., & Mordatch, I. (2019) · arXiv · doi:10.48550/arxiv.1909.07528 · Cited by 424 · see citing works
“Our work sees itself in the tradition of previous studies that showcase emergent complexity in simple physically grounded environments [11, 12, 13, 14]; the success in these settings inspires confidence that inducing autocurricula in physically grounded and open-ended environments could eventually enable agents to acq…”
BackgroundLehman, J., Clune, J., Misevic, D., Adami, C., Altenberg, L., Beaulieu, J., Bentley, P. J., Bernard, S., Beslon, G., Bryson, D. M., et al. (2020) · Artificial Life · doi:10.1162/artl_a_00319 · Cited by 181 · see citing works
Self-citationOptimizing walking controllers
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2009) · ACM Transactions on Graphics · doi:10.1145/1618452.1618514 · Cited by 181 · see citing works
Optimizing walking controllers for uncertain inputs and environments
Wang, J. M., Fleet, D. J., & Hertzmann, A. (2010) · ACM Transactions on Graphics · doi:10.1145/1778765.1778810 · Cited by 113 · see citing works
Meta Learning Backpropagation And Improving It
Kirsch, L., & Schmidhuber, J. (2020) · arXiv · doi:10.48550/arxiv.2012.14905 · Cited by 19 · see citing works
FARMS: Framework for Animal and Robot Modeling and Simulation
Arreguit, J., Tata Ramalingasetty, S., Danner, S. M., & Ijspeert, A. (2023) · doi:10.1101/2023.09.25.559130 · Cited by 12 · see citing works
Gao, H.-A., Geng, J., Hua, W., Hu, M., Juan, X., Liu, H., Liu, S., Qiu, J., Qi, X., Wu, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2507.21046 · Cited by 3 · see citing works
- Authors
- Sims, K.
- Corresponding author
- Sims, Karl
- Venue
- Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94
- Publisher
- ACM Press
- Published
- 1994
- Pages
- 15-22
- OpenAlex
- W2117085697
- Cited by
- 1,005
- References
- 1
- Citations by year
- 2026: 6 · 2025: 15 · 2024: 28 · 2023: 33 · 2022: 30 · 2021: 26 · 2020: 36 · 2019: 34 · 2018: 40 · 2017: 37 · 2016: 24 · 2015: 35 · 2014: 43 · 2013: 33 · 2012: 56
- FWCI
- 19.80
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM SIGGRAPH Conference (SIGGRAPH) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- Physical Sciences › Engineering › Mechanical Engineering › Modular Robots and Swarm Intelligence
- Physical Sciences › Engineering › Biomedical Engineering › Robotic Locomotion and Control
- Keywords
- virtual creatures, genetic algorithm, morphological evolution, neural network evolution, locomotion, artificial evolution, fitness function, directed graphs, three-dimensional simulation, swimming, walking, jumping, following behavior
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
