The co-evolution of brain and body empowers animals to exhibit complex behaviors in their environments. Motivated by this natural synergy, Embodied Co-Design (ECD) has emerged as a transformative paradigm for the development of intelligent agents, including both physical robots and virtual creatures. In contrast to conventional approaches that primarily focus on control optimization, ECD jointly optimizes an agent's morphology and control, thereby enhancing environmental interactions and improving task performance compared to control design alone.

🔑 Contributions to Embodied AI: This work provides a comprehensive survey of ECD within the broader landscape of embodied intelligence. We begin with definitions of ECD and contextualize it within related fields such as evolutionary robotics, artificial life, and computational robot design. Next, we introduce a novel hierarchical taxonomy to classify design spaces and representation methods for control, morphology, and tasks, which allows us to analyze over one hundred recent studies in ECD. We review notable benchmarks and applications in both simulated and real-world scenarios. Finally, we identify significant challenges and offer insights into promising future research directions.

We hope that this survey can serve as a reference-worthy and stimulating contribution to the advancement of embodied intelligence while also providing valuable perspectives for related fields.

2025/01/01: Happy New Year! I am updating the survey on this topic and will fully update the site when the survey is updated to Arxiv.

• Feel free to pull requests or contact us if you find any related papers that are not included here. The process to submit a pull request is as follows:

• a. Fork the project into your own repository.
• b. Add the Title, Paper link, Published in, Agent Type, Page/Code link in README.md using the following format:

  |[Title](Paper Link)|Conference/Journal/Preprint|Agent Type|[Code/Project](Code/Project Link)|

• c. Submit the pull request to this branch.

• We will update this page on a regular basis! So stay tuned~ 🎉🎉🎉. If you do find our survey or the repository helpful, please consider kindly giving a ⭐, 谢谢你, Thanks a lot, Спасибо, ありがとう, 감사합니다, Merci, Grazie, Obrigado, Danke, شكراً.

Here is a quick menu .^_^. :

• 🚀 Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges
• 📋 Update List
• 🔥 Comments
• 🎥 Overview
  • Taxonomy of Embodied Co-Design
  • Frameworks of Embodied Co-Design
• ⭐ Latest ECD Works
• 1️⃣ Bi-Level Co-Design
  • Evolutionary Reinforcement Learning
  • Surrogate-Assisted Methods
  • Other Methods
• 2️⃣ Single-Level Co-Design
  • EA-Based Methods
  • RL-Based Methods
  • Physics-Based Methods
  • Diversity-Based Methods
• 3️⃣ Generative Co-Design
  • Rule-Based Generation
  • Latent-Based Generation
  • LLM/VLM-Based Generation
• 4️⃣ Open-Ended Co-Design
  • Brain-Body-Env Co-Evolution
  • Developmental Co-Evolution
  • Other Methods
• 5️⃣ Theoretical and Experimental Analysis of Embodied Co-Design
• 💻 Simulated Benchmarks for Embodied Co-Design
• 🚪 Embodied Co-Deisgn in Real World
• 📖 Other Surveys Recommended
• ✉️ Contact Information

The creation of an embodied agent hinges on three critical components: Controlling Brain, Body Morphology, Task Environment, and the Co-Design algorithm that optimizes these components.

1. Controlling Brain: The controller (software) is responsible for perception-action coupling, enabling an agent to process sensory information and generate appropriate motor responses to control its body.

2. Body Morphology: The physical embodiment (hardware) of an agent, including its shape, material properties, sensor placement, etc. Morphological design determines the agent’s physical capabilities and constraints, thereby impacting its performance and adaptability.

3. Task Environment: This includes both task-specific conditions and broader environmental configurations. It not only defines the challenge faced by an agent but also provides the necessary feedback for learning and adaptation. Task requirements and environmental dynamics are crucial for shaping the agent’s behavior and learning objectives.

4. Co-Design Algorithms (A machine that can design other machines): An effective co-design algorithm integrates the optimization of control, morphology, and environmental interactions. Unlike traditional methods that treat these components separately, co-design algorithms aim to simultaneously refine all aspects, leading to more efficient and adaptive agents. These algorithms leverage advanced techniques to explore and exploit the co-design space, optimizing for performance across diverse tasks and environments.

📖 We provide a detailed analysis of ECD methods based on the proposed taxonomy. Please refer to our paper when it is available online.

The following picture introduces 4 general ECD frameworks, with the last sub-figure showing an example of the ECD process for creating a BipedalWalker agent.

TLDR: Methods that focus on the bi-level nature of control learning together with morphology evolution (Baldwin Effect)

TLDR: Methods that focus on using surrogate models to reduce the computational burden of the co-design process (how to efficiently evaluate a morphology without learning a specific controller?)

TLDR: Methods that focus on evolving morphology and control simultaneously (how does natural evolution inform the co-design process?).

TLDR: Methods that focus on optimizing morphology and control simultaneously using Reinforcement Learning (physics-model free).

TLDR: Methods that focus on optimizing morphology and control simultaneously using Differentiable Simulation or analytical physics model).

TLDR: Methods that focus on generating morphological diversity (how to effectively keep the morphological diversity?).

TLDR: Actuating Shape-Changed robots.

TLDR: Methods that focus on generating agent morphologies using rule-based systems (grammar, L-systems, etc.).

TLDR: Methods that focus on generating agent morphologies using latent-based systems (GAN, VAE, etc.).

TLDR: Methods that focus on generating agent morphologies using large models (Diffusion Model, LLM, etc.).

TLDR: Methods that focus on brain-body-environment co-optimization.

TLDR: Papers that investigates the synergy of Brain, Body, and Environment.

• Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot
  Guiliang Liu, et al., 2025, ArXiv Preprint
• Soft robotics: what’s next in bioinspired design and applications of soft robots?
  Cecilia Laschi, Li Wen, Fumiya Iida and others, 2025, Bioinspiration & Biomimetics
• Embodied Intelligence: A Synergy of Morphology, Action, Perception and Learning
  Huaping Liu, et al., 2025, ACM Computing Surveys
• Accessible survey of evolutionary robotics and potential future research directions
  Hari Mohan Pandey, Arxiv, 2024
• Exploring Embodied Intelligence in Soft Robotics: A Review
  Zikai Zhao, et al., 2024, Bio-Inspired and Biomimetic Intelligence in Robotics
• Collective Intelligence for Deep Learning: A Survey of Recent Developments
  David Ha and Yujin Tang, 2022, Collective Intelligence
• Bridging evolutionary algorithms and reinforcement learning: A comprehensive survey on hybrid algorithms
  Pengyi Li and Jianye Hao, et al., 2022, IEEE Transactions on Evolutionary Computation
• Design Optimization of Soft Robots: A Review of the State of the Art
  FeiFei Chen and Michael Yu Wang, 2022, IEEE Robotics & Automation Magazine
• Evolutionary robotics and open-ended design automation
  Hod Lipson, 2005, Biomimetics

This repo is developed and maintained by Yuxing Wang. For any questions, please feel free to email wyx20@tsinghua.org.cn.