This study presents a unified collaborative decision-making framework that integrates adaptive control and visual navigation to enhance the performance of aerospace electromechanical systems operating in dynamic and uncertain environments. The proposed methodology builds upon a rigorous mathematical foundation and introduces two core components that enable robust system intelligence: the Adaptive Collaborative Control Model (ACCM) and the Adaptive Collaborative Strategy (ACS). The ACCM establishes a multimodal decision-making structure capable of fusing heterogeneous signals from system states, actions, and visual observations. Through a multimodal encoder, graphical propagation layer, and a unified integration of adaptive control with perception, the model generates coordinated policies across multiple agents. These policies dynamically evolve based on shared information and collaborative reward structures, allowing the system to maintain stability, optimize performance, and adapt to rapidly changing conditions. The ACS further operationalizes collaboration by incorporating real-time information sharing, dynamic weighting mechanisms, and a consensus-based conflict resolution process. By embedding visual feature extraction, shared latent representations, and feedback-driven updates, the strategy strengthens multi-agent coordination and enhances reliability under communication uncertainties or environmental perturbations. Extensive experiments conducted on visual navigation datasets, adaptive control logs, and electromechanical collaboration records validate the effectiveness of the framework. Results show consistent improvements in efficiency, accuracy, robustness, and scalability compared with state-of-the-art baselines. Overall, this research demonstrates that jointly optimizing adaptive control and visual navigation through ACCM and ACS provides a powerful pathway for advancing autonomous aerospace electromechanical systems.
QiaoYing et al. (Wed,) studied this question.