The virtual model control (VMC) method establishes a direct correlation model between the end-effector and the main body by selecting appropriate virtual mechanical components. This approach facilitates direct force control while circumventing the necessity for complex dynamic modeling. However, the simplification inherent in this modeling can result in inaccuracies in the calculation of joint driving torques, ultimately diminishing control precision. Moreover, VMC typically depends on predefined models for control, which constrains its adaptability in dynamically complex environments and under varying movement conditions. To address these limitations, this paper proposes the BP-VMC method, which is based on a backpropagation neural network (BPNN). Initially, a quadruped robot model was established through kinematic analysis. Subsequently, a decomposed VMC model was developed, and BPNN was introduced to facilitate the adaptive tuning of virtual parameters. This approach resulted in the creation of a virtual mechanical component model with adaptive capabilities, compensating for errors arising from simplified modeling. Finally, a simulation control system was constructed based on the BP-VMC control framework to validate the optimization of control performance. Simulation experiments demonstrated that, in comparison to traditional VMC methods, the BP-VMC method exhibits enhanced control accuracy and stability, achieving a 30% reduction in trajectory tracking error, a 40% reduction in velocity tracking error, and a 20–30% improvement in instability indices across various working conditions. This evidence underscores the BP-VMC method’s robust adaptability in dynamic environments.
1 January 2026 in IEEE Transactions on Automation Science and Engineering
Modular reconfigurable robots exhibit significant potential in adapting to complex terrains through cooperative multi-robot formations. However, current control systems often struggle to maintain consistent performance when the number of modules varies due to a lack of unified and adaptive control frameworks. Existing Virtual Model Control (VMC) methods, while effective for fixed-configuration legged robots, are limited in their ability to dynamically adjust control parameters in reconfigurable multi-legged systems. To address this gap, this study proposes a parallel multi-legged control system that integrates a Backpropagation Neural Network (BPNN) with a decoupled VMC framework. The BPNN enables adaptive tuning of motion parameters under varying modular configurations, while the decoupled VMC ensures stable gait control under force feedback. Simulation and physical experiments demonstrate that the proposed system achieves a unified control architecture across quadrupedal and multi-legged configurations, with improved tracking accuracy, stability, and adaptability compared to traditional VMC methods.