# Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots

arXiv: https://arxiv.org/abs/2402.09231 · HTML: https://mlsanity.com/paper/2402.09231/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2024.

## Built on by (most cited first, 9 of 9)

- [VLMgineer: Vision Language Models as Robotic Toolsmiths](https://mlsanity.com/paper/2507.12644/) (2025)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Controller Distillation Reduces Fragile Brain-Body Co-Adaptation and Enables Migrations in MAP-Elites](https://mlsanity.com/paper/2504.06523/) (2025)
- [Towards Multi-Morphology Controllers with Diversity and Knowledge Distillation](https://mlsanity.com/paper/2404.14625/) (2024)
- [No-brainer: Morphological Computation driven Adaptive Behavior in Soft Robots](https://mlsanity.com/paper/2407.16613/) (2024)
- [Efficient and Diverse Generative Robot Designs using Evolution and Intrinsic Motivation](https://mlsanity.com/paper/2411.18423/) (2024)
- [Social Learning Strategies for Evolved Virtual Soft Robots](https://mlsanity.com/paper/2604.12482/) (2026)
- [Lamarckian Inheritance in Dynamic Environments: How Key Variables Affect Evolutionary Dynamics](https://mlsanity.com/paper/2605.15769/) (2026)
- [Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning](https://mlsanity.com/paper/2608.23100/) (2026)

## Abstract (arXiv)

Evolving virtual creatures is a field with a rich history and recently it has been getting more attention, especially in the soft robotics domain. The compliance of soft materials endows soft robots with complex behavior, but it also makes their design process unintuitive and in need of automated design. Despite the great interest, evolved virtual soft robots lack the complexity, and co-optimization of morphology and control remains a challenging problem. Prior work identifies and investigates a major issue with the co-optimization process -- fragile co-adaptation of brain and body resulting in premature convergence of morphology. In this work, we expand the investigation of this phenomenon by comparing learnable controllers with proprioceptive observations and fixed controllers without any observations, whereas in the latter case, we only have the optimization of the morphology. Our experiments in two morphology spaces and two environments that vary in complexity show, concrete examples of the existence of high-performing regions in the morphology space that are not able to be discovered during the co-optimization of the morphology and control, yet exist and are easily findable when optimizing morphologies alone. Thus this work clearly demonstrates and characterizes the challenges of optimizing morphology during co-optimization. Based on these results, we propose a new body-centric framework to think about the co-optimization problem which helps us understand the issue from a search perspective. We hope the insights we share with this work attract more attention to the problem and help us to enable efficient brain-body co-optimization.