# Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning

arXiv: https://arxiv.org/abs/2608.23100 · HTML: https://mlsanity.com/paper/2608.23100/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 54 references that are in the map.
- First posted on arXiv 24 Aug 2026.

## Builds on (most cited first, 18 of 18)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Embodied Intelligence via Learning and Evolution](https://mlsanity.com/paper/2102.02202/) (2021)
- [PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics](https://mlsanity.com/paper/2104.03311/) (2021)
- [MetaMorph: Learning Universal Controllers with Transformers](https://mlsanity.com/paper/2203.11931/) (2022)
- [Evolution Gym: A Large-Scale Benchmark for Evolving Soft Robots](https://mlsanity.com/paper/2201.09863/) (2022)
- [Mirage: Cross-Embodiment Zero-Shot Policy Transfer with Cross-Painting](https://mlsanity.com/paper/2402.19249/) (2024)
- [GLSO: Grammar-guided Latent Space Optimization for Sample-efficient Robot Design Automation](https://mlsanity.com/paper/2209.11748/) (2022)
- [Scalable sim-to-real transfer of soft robot designs](https://mlsanity.com/paper/1911.10290/) (2019)
- [Sim-to-Real for Soft Robots using Differentiable FEM: Recipes for Meshing, Damping, and Actuation](https://mlsanity.com/paper/2201.12560/) (2022)
- [Investigating Premature Convergence in Co-optimization of Morphology and Control in Evolved Virtual Soft Robots](https://mlsanity.com/paper/2402.09231/) (2024)
- [Generating Freeform Endoskeletal Robots](https://mlsanity.com/paper/2412.01036/) (2024)
- [Accelerated co-design of robots through morphological pretraining](https://mlsanity.com/paper/2502.10862/) (2025)
- [RoboMoRe: LLM-based Robot Co-design via Joint Optimization of Morphology and Reward](https://mlsanity.com/paper/2506.00276/) (2025)
- [Evolutionary Brain-Body Co-Optimization Consistently Fails to Select for Morphological Potential](https://mlsanity.com/paper/2508.17464/) (2025)
- [Embodied Co-Design for Rapidly Evolving Agents: Taxonomy, Frontiers, and Challenges](https://mlsanity.com/paper/2512.04770/) (2025)
- [Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer](https://mlsanity.com/paper/2405.03534/) (2024)
- [Soft yet Effective Robots via Holistic Co-Design](https://mlsanity.com/paper/2505.03761/) (2025)
- [Evolving Embodied Intelligence: Graph Neural Network--Driven Co-Design of Morphology and Control in Soft Robotics](https://mlsanity.com/paper/2603.19582/) (2026)

## Abstract (arXiv)

Robot co-design via bi-level optimization couples within-lifetime controller learning for fitness evaluation with cross-generational morphological evolution. Prior work has established that well-adapted morphology facilitates faster control learning, a property termed morphological intelligence. Yet how control learning reciprocally shapes morphological evolution remains unexplored. This paper examines both directions for a holistic account of brain-body interplay. We first show that morphological contributions to control learning decouple into two orthogonal dimensions. We formalize the convergence speed as morphological intelligence and identify the performance ceiling as a complementary quantity termed true potential. A concise functional relation is then established to jointly characterize both quantities from individual learning curves, which, when aggregated at the population level, capture evolutionary profiles. Through extensive experiments on simulated voxel-based soft robots, we reveal that premature fitness evaluation systematically underestimates true potential and biases selection towards fast learners. This restricts design space exploration, compromising both optimization efficiency and morphological diversity. Notably, the widely recognized morphological Baldwin effect emerges as an artifact of this bias rather than a general evolutionary tendency. We therefore propose AdaControl, which monitors disproportionate selection for morphological intelligence during evolution and allocates minimally sufficient control learning for unbiased fitness evaluation. With AdaControl, a simple genetic algorithm rivals state-of-the-art generative-model-based co-design methods in discovering diverse high-performing designs while cutting computation by up to 80% versus exhaustive control.