Because of their unique adaptability, flexibility, and robustness, musculoskeletal robotic systems are regarded potentially as next-generation robots. However, motion learning and generation of such a robotic system are still challenging. This paper presents a neuromuscular control method, namely, TMS-PPO, based on time-varying muscle synergy (TMS) and proximal policy optimization (PPO). The electromyogram (EMG) activation signals of actual human motions are decomposed to obtain TMSs based on the temporal properties of the TMS. The weights of networks are trained to generate the scale and phase coefficients through the PPO. The coefficients modulate the TMSs to generate appropriate activation patterns to optimize motion learning of the musculoskeletal system. To verify the effectiveness of the proposed method, the TMSs are extracted from human upper limb muscle activation signals, and we compare TMS-PPO with PPO in the motion learning and generation process of an upper limb musculoskeletal system. The results show that TMS-PPO can complete the control tasks because the average errors of the joints are less than 0.05 rad. In the meantime, TMSs are used as motion primitives of the musculoskeletal system to simulate the process of the human CNS controlling muscles. It shows that TMS-PPO reduces the energy consumption and improves the learning rate significantly compared with the PPO. The learning episodes reduce from \(10^4\) to \(10^3\) , which indicates that TMS-PPO has a stronger learning ability and better physiological explanation. Note to Practitioners —Due to the superiorities of the musculoskeletal system, humanoid robots that imitate human driven mechanisms are vigorously carried out worldwide. Taking advantages of human-like characteristics, the musculoskeletal robot provides new opportunities to understand and validate the human mechanisms of muscle control and motion learning, to compare the performance of the robot to that of humans as well as work in real world, e.g., human interactive robots, amusement robots and medical training robots in the future. However, strong redundancy, coupling, and nonlinearity of the system also raises many challenges for the investigation of the control problem. Inspired by how the human CNS controls a musculoskeletal system and realize motion generalization, a novel muscle-synergies-based neuromuscular control that combines time-varying muscle synergy (TMS) and Proximal Policy Optimization (PPO), namely, TMS-PPO is proposed in this paper. The learning efficiency of PPO and the physiological interpretation of the control process are improved during the motion learning and generation processes of the musculoskeletal system. Preliminary simulation experiments suggest that this method is feasible in terms of control accuracy and efficiency. Moreover, the performance of the TMS-PPO is comparable to the PPO without significant improvement. To solve this problem, in future work, we will introduce the cerebellar model into the control method which plays the role of adjusting and correcting the motions of the limbs to achieve accurate and stable control in the actions process of humans.

Porous metals are found to be suitable as orthopedic scaffolds. However, only limited control over the internal architecture can be achieved using conventional design methods. The architecture with porosity variation strategy mimicking natural bone is critical to gain favorable combination of mechanical and biological properties for orthopedic implants. In this regard, a topology optimization method with customized morphology and mechanical properties derived from the trabecular bone was proposed to design three-dimensional architectures with gradient porosity resembling the porous structure of bone. In particular, the elastic constants for the trabecular bone were better predicted when the bone volume fraction was supplemented with a three-dimensional structural parameter, i.e., degree of anisotropy. These constants were set as the optimization constrains for morphology control. Then the porous titanium structures were manufactured by selective laser melting technology (SLM). The physical characteristics, mechanical properties of the scaffolds were compared systematically. The experimental results revealed that the as-built samples with the proposed method lead to a good match of morphological accuracy and mechanical properties to that of the bone. It demonstrates that the proposed topology optimization method with controlled morphology and mechanical properties provides an efficient manner for the biomimetic design of orthopedic implants.

Achieving reliable muscle synergies (MSs) is critical for optimizing motor control in neuromusculoskeletal robotics. Existing MS extraction approaches are limited by traditional electromyography (EMG) acquisition constraints, variability due to methodological differences, and difficulty in assessing the contribution of deep and small muscle groups to optimal MSs. To overcome these challenges, we developed the Determination of Optimal Functional MSs from Estimated Muscle Activations (DOMSn-EMAs), a novel computational approach elucidating the impact of high-density estimated muscle activations (EMAs) on optimal functional MSs under specific biomechanical task constraints. DOMSn-EMAs comprises three key steps: (1) computing high-density EMAs through measured human motion data and high-fidelity musculoskeletal modeling with a modified computed muscle control algorithm, constrained by limited surface EMG tracking; (2) extracting sparse MS properties using sparse non-negative matrix factorization (SNMF) to improve reconstruction accuracy and repeatability; and (3) introducing a composite reliability index for optimal MS number identification. Validation on a publicly available dataset from 10 subjects confirms DOMSn-EMAs’ reliability. The results identify five optimal MSs from 43 EMAs, with an independent MS involving deep and small muscle groups during the early swing phase. This approach corroborates the similarity between EMG-derived and EMAs-derived synergies while identifying EMAs’ potential influence on optimal functional MSs. DOMSn-EMAs provides a pioneering and practical approach for synergy analysis, ensuring more reliable and sophisticated MSs than previous modular architectures for robotics applications.

Bio-inspired musculoskeletal robots offer inherent advantages in flexibility, robustness, and compliance. However, achieving efficient and generalizable motion learning while producing natural, human-like movements remains challenging. Neuromechanical mechanisms provide a promising framework to emulate biological motor control and skill acquisition. In this study, we present a biomimetic hierarchical neuromechanical control model (HNCM) that integrates deep reinforcement learning with two distinct lower-level controllers. The model is designed to manage high-dimensional muscle control, enhance robustness to motor and sensory perturbations, generalize to previously untrained tasks, and generate human-like reaching movements. A high-level controller based on the proximal policy optimization algorithm models the supraspinal neural system and generates motor commands. The dual-path adaptive lower-level controller emulates both synergy-based and non-synergy-based motor pathways, preserving the benefits of structured exploration while allowing flexible, task-specific behavioral refinement. Comprehensive evaluations on center-out and random reaching tasks demonstrate that HNCM significantly outperforms baseline methods in control accuracy, learning efficiency, and generalization under noise perturbations, while producing more natural and biologically plausible movement trajectories. This work advances the understanding of neuromechanical control and provides a solid foundation for future applications in musculoskeletal robotics.

Muscle synergy analysis has been widely applied in neuroscience, biomechanics, rehabilitation, and robotics. However, the reliability of muscle synergy extraction remains a critical issue, as results are highly sensitive to variations in experimental design, surface electromyography preprocessing, factorization algorithms, and the determination of the number of synergies. This narrative methodological review examines the key factors that influence the robustness and reliability of muscle synergies within the framework of limb neuromechanical controllers across anatomical regions and task contexts. By analyzing the current state of research in this field, we first summarize the conceptual and methodological foundations of muscle synergy analysis and then critically examine the factors that influence its robustness and reliability. This review provides practical recommendations to enhance methodological rigor, including greater methodological harmonization and transparent reporting of experimental protocols, the use of musculoskeletal simulation to evaluate muscle selection strategies, and the refinement of synergy extraction techniques. These insights aim to improve the reliability and robustness of muscle synergy analysis and promote its application in robotics, human–machine interfacing, and computational motor control.