◼︎Paper information:
Yuxi Lu, Zhongchao Zhou*, Yanmin Zhou, Zhipeng Wang, Shuo Jiang, Wenwei Yu, Bin He. “Offline-Trained GAN-Augmented Highly Adaptive Control with Multi-DoF Fusion for Pneumatic Soft Surgical Robots”.
* Corresponding author
◼︎Abstract:
Pneumatic soft robots are well-suited for minimally invasive surgery owing to their compliance and tissue-safe interaction. However, achieving highly adaptive control is difficult owing to modeling inaccuracies, inter-chamber coupling, and disturbances from surgical instruments. Non-learning adaptive methods depend on simplified models and perform poorly in unstructured settings. Conversely, learning-based methods often impose high computational costs, especially in multi-degree-of freedom (multi-DoF) pneumatic systems. A previous study proposed a generative adversarial network (GAN)-based proportional–integral–derivative (G-PID) controller that combined PID stability with learning-based adaptability by aligning system behavior with a reference model. However, its performance in highly coupled multi-DoF pneumatic soft robots was unverified, and its online adversarial training was computationally intensive. This study addressed these limitations by developing an offline-trained G-PID controller, shifting adversarial training offline to cut computational overhead, achieving 23-fold faster convergence, and enabling real-time, model-free control with balanced adaptability and efficiency. We evaluated three multi-DoF data fusion strategies, showing effective coordination of DoF coupling while maintaining individual control fidelity. Validation on a multi-DoF soft robotic mechatronic system for single-port transvesical prostatectomy showed tip errors below 0.16 mm across surgical instruments. The proposed controller enhances scalability and adaptability and is expected to generalize to other mechatronic systems with nonlinear, coupled dynamics