Generation of Diverse and Functional Robot Designs using Superquadrics Parametrisation and Quality-Diversity

2026-06-09

AI Summary

This work addresses key limitations in robot generative design—namely, the vast search space, premature convergence of evolutionary algorithms, and insufficient morphological diversity. To overcome these challenges, the authors propose a method that integrates superquadrics-based parametric representation with the quality-diversity optimization algorithm MAP-Elites. This approach leverages a compact and interpretable geometric encoding to explicitly preserve morphological diversity while enabling co-optimization of functional performance and structural form. Evaluated in two distinct test environments, the method significantly improves QD scores, demonstrating enhanced exploration of the design space by simultaneously achieving high functionality and greater morphological variety in the generated robots.

Abstract

Generative design of robots requires navigating a vast search-space, encompassing physical configurations and behavioural parameters. Evolutionary Algorithms (EAs) have shown promising results, but often converge prematurely to a small set of sub-optimal designs. Most EAs fail to maintain sufficient diversity in the population that would allow the discovery of distinct functional robots. To counter premature convergence, we introduce a superquadrics-based representation (SQs) for robot bodies. SQs are interpretable, compact and computationally efficient mathematical representations of 3D geometrical shapes that can be tuned to specific design-spaces. To encourage morphological diversity, we combine this representation with a quality-diversity (QD) algorithm (MAP-Elites). We compare SQs and Compositional Pattern Producing Networks representations as generators of morphologies, combining them with standard EAs and MAP-Elites. In two test environments, we find that using SQs to generate morphology in conjunction with the MAP-Elites algorithm reaches the highest QD-score across both environments, maximising diversity of design and functionality of generated robots. The findings highlight the benefits of using a compact and interpretable geometric representation for exploring a complex design-space and suggest that combining SQs with an explicit diversity mechanism increases the quality and number of designs generated.

Problem

• robot design
• morphological diversity
• premature convergence
• quality-diversity
• search space

Innovation

• Superquadrics
• Quality-Diversity
• MAP-Elites
• Generative Design
• Evolutionary Robotics