Robustness study of the bio-inspired musculoskeletal arm robot based on the data-driven iterative learning algorithm

Traditional robotic systems excel in high-precision and large-load operations, but achieving tasks that require robustness, dexterity, and flexibility necessitates high-precision sensors, high-precision structures, and advanced control algorithms. In situations where the absolute precision of sensing and control in each unit is not high, the human arm can effectively utilize its inherent structural characteristics, such as the serial and parallel hybrid kinematic structure and the rigid-flexible coupling dynamic characteristics, to achieve rapid, robust, safe, dexterous, and flexible operations through information processing in neural circuits [1-3]. Through the synergy of software and hardware, developing a neuromorphic intelligent robot system that embodies human-like structural characteristics and driving mechanisms holds significant inspirational and catalytic value for advancing novel high-performance robotic systems. However, simulating the musculoskeletal structure with physical devices poses significant challenges. Michael et al. [4] created the'Anthrob' robot, which is a reduced version of the human upper limb with 13 compliant muscles and four joints, However, the complexity of muscle units makes the extension of multi-muscle actuation challenging.