# Neural Graph Evolution: Towards Efficient Automatic Robot Design

arXiv: https://arxiv.org/abs/1906.05370 · HTML: https://mlsanity.com/paper/1906.05370/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jun 2019.

## Built on by (most cited first, 30 of 36)

- [An End-to-End Differentiable Framework for Contact-Aware Robot Design](https://mlsanity.com/paper/2107.07501/) (2021)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://mlsanity.com/paper/2201.09863/) (2022)
- [Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design](https://mlsanity.com/paper/2110.03659/) (2021)
- [Task-Agnostic Morphology Evolution](https://mlsanity.com/paper/2102.13100/) (2021)
- [GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation](https://mlsanity.com/paper/2209.11748/) (2022)
- [REvolveR: Continuous Evolutionary Models for Robot-to-robot Policy Transfer](https://mlsanity.com/paper/2202.05244/) (2022)
- [Symmetry-Aware Robot Design with Structured Subgroups](https://mlsanity.com/paper/2306.00036/) (2023)
- [From Universal Humanoid Control to Automatic Physically Valid Character Creation](https://mlsanity.com/paper/2206.09286/) (2022)
- [The Effects of Learning in Morphologically Evolving Robot Systems](https://mlsanity.com/paper/2111.09851/) (2021)
- [DiffAqua: A Differentiable Computational Design Pipeline for Soft Underwater Swimmers with Shape Interpolation](https://mlsanity.com/paper/2104.00837/) (2021)
- [BodyGen: Advancing Towards Efficient Embodiment Co-Design](https://mlsanity.com/paper/2503.00533/) (2025)
- [HERD: Continuous Human-to-Robot Evolution for Learning from Human Demonstration](https://mlsanity.com/paper/2212.04359/) (2022)
- [Text2Robot: Evolutionary Robot Design from Text Descriptions](https://mlsanity.com/paper/2406.19963/) (2024)
- [RoboMorph: Evolving Robot Morphology using Large Language Models](https://mlsanity.com/paper/2407.08626/) (2024)
- [Curriculum Reinforcement Learning via Morphology-Environment Co-Evolution](https://mlsanity.com/paper/2309.12529/) (2023)
- [Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design](https://mlsanity.com/paper/2311.00462/) (2023)
- [Evolution and learning in differentiable robots](https://mlsanity.com/paper/2405.14712/) (2024)
- [RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward](https://mlsanity.com/paper/2506.00276/) (2025)
- [Task2Morph: Differentiable Task-inspired Framework for Contact-Aware Robot Design](https://mlsanity.com/paper/2403.19093/) (2024)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Efficient Morphology-Control Co-Design via Stackelberg Proximal Policy Optimization](https://mlsanity.com/paper/2603.15388/) (2026)
- [What Robot do I Need? Fast Co-Adaptation of Morphology and Control using Graph Neural Networks](https://mlsanity.com/paper/2111.02371/) (2021)
- [C^2:Co-design of Robots via Concurrent Networks Coupling Online and Offline Reinforcement Learning](https://mlsanity.com/paper/2209.06579/) (2022)
- [CompetEvo: Towards Morphological Evolution from Competition](https://mlsanity.com/paper/2405.18300/) (2024)
- [Shape Your Body: Value Gradients for Multi-Embodiment Robot Design](https://mlsanity.com/paper/2606.00702/) (2026)
- [A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration](https://mlsanity.com/paper/2111.14767/) (2021)
- [Co-design of Embodied Neural Intelligence via Constrained Evolution](https://mlsanity.com/paper/2205.10688/) (2022)
- [Latent Diffeomorphic Co-Design of End-Effectors for Deformable and Fragile Object Manipulation](https://mlsanity.com/paper/2602.17921/) (2026)
- [Evolving Embodied Intelligence: Graph Neural Network--Driven Co-Design of Morphology and Control in Soft Robotics](https://mlsanity.com/paper/2603.19582/) (2026)
- [BRIDGE: An Open-Source Humanoid Platform via Morphology-Control Co-Design for Physical AI](https://mlsanity.com/paper/2609.03497/) (2026)

## Abstract (arXiv)

Despite the recent successes in robotic locomotion control, the design of robot relies heavily on human engineering. Automatic robot design has been a long studied subject, but the recent progress has been slowed due to the large combinatorial search space and the difficulty in evaluating the found candidates. To address the two challenges, we formulate automatic robot design as a graph search problem and perform evolution search in graph space. We propose Neural Graph Evolution (NGE), which performs selection on current candidates and evolves new ones iteratively. Different from previous approaches, NGE uses graph neural networks to parameterize the control policies, which reduces evaluation cost on new candidates with the help of skill transfer from previously evaluated designs. In addition, NGE applies Graph Mutation with Uncertainty (GM-UC) by incorporating model uncertainty, which reduces the search space by balancing exploration and exploitation. We show that NGE significantly outperforms previous methods by an order of magnitude. As shown in experiments, NGE is the first algorithm that can automatically discover kinematically preferred robotic graph structures, such as a fish with two symmetrical flat side-fins and a tail, or a cheetah with athletic front and back legs. Instead of using thousands of cores for weeks, NGE efficiently solves searching problem within a day on a single 64 CPU-core Amazon EC2 machine.