Evolving Embodied Intelligence: Graph Neural Network--Driven Co-Design of Morphology and Control in Soft Robotics

2026-03-19

AI Summary

This work addresses the challenge in co-optimizing morphology and control for soft robots, where morphological evolution often disrupts learned control policies, hindering knowledge reuse. To overcome this, the authors propose a morphology-aware graph-based policy representation that models the robot as a graph, encodes node states using a Graph Attention Network (GAT), and generates motor commands via a Multilayer Perceptron (MLP). This approach enables topology-consistent policy inheritance and transfer, effectively preserving control knowledge despite structural changes. Integrated with an evolutionary algorithm, the framework significantly outperforms conventional MLP-based methods on benchmark tasks, achieving higher final fitness and demonstrating superior adaptability to diverse morphologies. These results validate the efficacy and advantages of graph-structured policies in the co-design of embodied intelligence.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Machine Learning: Evolutionary Learning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The intelligent behavior of robots does not emerge solely from control systems, but from the tight coupling between body and brain, a principle known as embodied intelligence. Designing soft robots that leverage this interaction remains a significant challenge, particularly when morphology and control require simultaneous optimization. A significant obstacle in this co-design process is that morphological evolution can disrupt learned control strategies, making it difficult to reuse or adapt existing knowledge. We address this by develop a Graph Neural Network-based approach for the co-design of morphology and controller. Each robot is represented as a graph, with a graph attention network (GAT) encoding node features and a pooled representation passed through a multilayer perceptron (MLP) head to produce actuator commands or value estimates. During evolution, inheritance follows a topology-consistent mapping: shared GAT layers are reused, MLP hidden layers are transferred intact, matched actuator outputs are copied, and unmatched ones are randomly initialized and fine-tuned. This morphology-aware policy class lets the controller adapt when the body mutates. On the benchmark, our GAT-based approach achieves higher final fitness and stronger adaptability to morphological variations compared to traditional MLP-only co-design methods. These results indicate that graph-structured policies provide a more effective interface between evolving morphologies and control for embodied intelligence.

Problem

• embodied intelligence
• co-design
• morphology
• control
• soft robotics

Innovation

• Graph Neural Network
• Embodied Intelligence
• Morphology-Control Co-Design
• Soft Robotics
• Policy Inheritance