Evolving the Complete Muscle: Efficient Morphology-Control Co-design for Musculoskeletal Locomotion

Lidong Sun; Wentao Zhao; Ye Wang; Huaping Liu; Fuchun Sun

cs.ROApr 14, 2026

Evolving the Complete Muscle: Efficient Morphology-Control Co-design for Musculoskeletal Locomotion

Authors: Lidong Sun, Wentao Zhao, Ye Wang, Huaping Liu, Fuchun Sun

Organizations: Naval University of Engineering, Wuhan 430033, China · Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China · Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China

Abstract

Musculoskeletal robots offer intrinsic compliance and flexibility, providing a promising paradigm for versatile locomotion. However, existing research typically relies on models with fixed muscle physiological parameters. This static physical setting fails to accommodate the diverse dynamic demands of complex tasks, inherently limiting the robot's performance upper bound. In this work, we focus on the morphology and control co-design of musculoskeletal systems. Unlike previous studies that optimize single physiological attributes such as stiffness, we introduce a Complete Musculoskeletal Morphological Evolution Space that simultaneously evolves muscle strength, velocity, and stiffness. To overcome the exponential expansion of the exploration space caused by this comprehensive evolution, we propose Spectral Design Evolution (SDE), a high-efficiency co-optimization framework. By integrating a bilateral symmetry prior with Principal Component Analysis (PCA), SDE projects complex muscle parameters onto a low-dimensional spectral manifold, enabling efficient morphological exploration. Evaluated on the MyoSuite framework across four tasks (Walk, Stair, Hilly, and Rough terrains), our method demonstrates superior learning efficiency and locomotion stability compared to fixed-morphology and standard evolutionary baselines.

Figures & tables

Fig. 1: Conceptual overview of Spectral Design Evolution (SDE). (Left) Fixed-morphology agent fails on challenging terrains due to physical limits. (Right) SDE optimizes muscle triad parameters ( $\sigma,\nu,\kappa$ ) on a low-dimensional spectral manifold, enabling the robot to adapt its physical capacity for superior locomotion stability.

Fig. 2: The SDE framework architecture. The process consists of an offline dynamics-aware manifold construction phase and an online two-stage co-optimization phase where the design policy $\pi_{\theta}$ and control policy $\pi_{\phi}$ are optimized via shared reward signals.

Fig. 3: Experimental setup and task environments in MyoSuite: (a) The MyoLeg model used for spectral analysis and co-optimization; (b) Walk terrain; (c) Rough terrain with stochastic debris; (d) Hilly terrain with undulating slopes; (e) Stair terrain with vertical obstacles.

Panel of Figure 4 — Fig. 4: Learning curves across four terrains. SDE demonstrates superior adaptability, particularly in high-impedance tasks like Stair , Hilly and Rough .

Fig. 5: Learning curves comparing full triad co-optimization against single-parameter evolution. The synergy between parameters contributes to adaptation across diverse terrains.

Fig. 6: Qualitative comparison of evolved gaits: (Left) The full SDE framework emerges a stable, alternating bipedal gait with natural leg-swing phases. (Right) The SDE- $\sigma$ (Strength-only) variant falls into a sub-optimal “scissor-gait”, where the limbs remain in a crossed configuration and the agent moves via hopping.

Panel of Figure 7 — Fig. 7: Radar charts showing the distributions of evolved muscle parameters across different muscle groups. (a-c) depict the evolution of individual parameters: strength ( $\sigma$ ), velocity ( $\nu$ ), and stiffness ( $\kappa$ ), which exhibit fragmented and inconsistent adaptation across muscles. (d) shows the SDE-evolved full triad, highlighting a coordinated synergy where muscle parameters co-adapt in a physiologically plausible manner, enabling efficient and stable locomotion.

Panel of Figure 8 — Fig. 8: Ablation study on bilateral symmetry. While SDE-Asym has higher degrees of freedom, the symmetry prior in SDE ensures more stable and physically plausible gait patterns.

Fig. 9: Cumulative explained variance of musculoskeletal dynamical response across different $k$ . A distinct “elbow” is observed at $k=5$ , capturing over $98\%$ of the morphological variance.

Fig. 10: Learning curves on the Rough task for different latent dimensions $k$ . Although $k=7$ and $k=9$ offer higher theoretical expressivity, $k=5$ achieves the most efficient balance between convergence speed and final reward.

Robot Morphology-Control Co-Design

Robot morphology-control co-design studies how to jointly shape a robot’s body and controller to improve task performance.

See all 60 papers

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning
Aug 24, 2026Junru Song, Yang Yang, Yaqing Xu +5Robot Morphology-Control Co-Design Evolutionary Robotics
Shanghai Jiao Tong University, Shanghai 200240, China · Intelligent Game and Decision Laboratory, Beijing 100048, China · Renmin University of China, Beijing 100872, China +1
Identifying and Exploiting Structure in Robot Co-Design
Apr 13, 2026Apoorv Vaish, Oliver BrockRobot Morphology-Control Co-Design Robotic Manipulation
Robotics and Biology Laboratory, Technische Universität Berlin · Science of Intelligence (SCIoI), Cluster of Excellence, Berlin · Robotics Institute Germany (RIG)
EvoGymCM: Harnessing Continuous Material Stiffness for Soft Robot Co-Design
Apr 9, 2026Le Shen, Kangyao Huang, Wentao Zhao +1Soft Robotics Robot Morphology-Control Co-Design
College of Control Science and Engineering, Zhejiang University. · Department of Computer Science and Technology, Tsinghua University.

Aug 24, 2026J/K move · Enter open · S save

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning

Junru Song, Yang Yang, Yaqing Xu, Ying Wen+4

Shanghai Jiao Tong University, Shanghai 200240, China · Intelligent Game and Decision Laboratory, Beijing 100048, China · Renmin University of China, Beijing 100872, China+1

Robot Morphology-Control Co-Design Evolutionary Robotics Embodied Cognition

Open paper AskPDF 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.

Abstract

Robot Morphology-Control Co-Design

Explore similar work

Shaping the Evolutionary Dynamics of Robot Morphology via Adaptive Control Learning

Identifying and Exploiting Structure in Robot Co-Design

EvoGymCM: Harnessing Continuous Material Stiffness for Soft Robot Co-Design