A Unified Low-Dimensional Design Embedding for Joint Optimization of Shape, Material, and Actuation in Soft Robots

2026-03-06

AI Summary

In soft robot design, shape, material distribution, and actuation are highly coupled, rendering traditional approaches inefficient for joint optimization due to the high computational cost of high-dimensional nonlinear simulations and the inapplicability of gradient-based methods. This work proposes a low-dimensional, structured design embedding based on shared basis functions that unifies these three aspects through a continuous deformation mapping and spatial material field encoding within a common latent space. The representational capacity of this approach predictably improves with the number of basis functions, remains compatible with black-box simulators, and enables end-to-end joint optimization. Experiments across multiple dynamic tasks demonstrate that the method achieves significantly better performance than neural network and voxel-based baselines using fewer parameters, and consistently outperforms sequential optimization strategies.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Mixed Discrete/Continuous Optimization

Application Category

• Graph Algorithms and Modeling for the Web: Graph embeddings and representation learning for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments

Abstract

Soft robots achieve functionality through tight coupling among geometry, material composition, and actuation. As a result, effective design optimization requires these three aspects to be considered jointly rather than in isolation. This coupling is computationally challenging: nonlinear large-deformation mechanics increase simulation cost, while contact, collision handling, and non-smooth state transitions limit the applicability of standard gradient-based approaches. We introduce a smooth, low-dimensional design embedding for soft robots that unifies shape morphing, multi-material distribution, and actuation within a single structured parameter space. Shape variation is modeled through continuous deformation maps of a reference geometry, while material properties are encoded as spatial fields. Both are constructed from shared basis functions. This representation enables expressive co-design while drastically reducing the dimensionality of the search space. In our experiments, we show that design expressiveness increases with the number of basis functions, unlike comparable neural network encodings whose representational capacity does not scale predictably with parameter count. We further show that joint co-optimization of shape, material, and actuation using our unified embedding consistently outperforms sequential strategies. All experiments are performed independently of the underlying simulator, confirming compatibility with black-box simulation pipelines. Across multiple dynamic tasks, the proposed embedding surpasses neural network and voxel-based baseline parameterizations while using significantly fewer design parameters. Together, these findings demonstrate that structuring the design space itself enables efficient co-design of soft robots.

Problem

• soft robots
• joint optimization
• shape
• material
• actuation

Innovation

• low-dimensional embedding
• co-design optimization
• soft robotics
• unified parameterization
• basis function representation