This study introduces an innovative method for gesture recognition in medical robotics, utilizing Capsule Neural Networks (CNNs) in conjunction with the Modified Spring Search Algorithm (MSSA). This approach achieves remarkable efficiency in gesture identification, facilitating precise control over medical robots. The proposed system undergoes thorough evaluation through both simulations and practical experiments, showing its capability to enhance patient outcomes in robotic surgical procedures. The primary contributions of this research include the creation of a unique CNN-MSSA architecture for gesture recognition, an extensive assessment of the system's performance, and evidence of its potential to advance patient care. The findings indicate that the system attains an accuracy rate of 95% with a processing duration of 0.5 s, surpassing existing methodologies. These results carry significant implications for the advancement of autonomous medical robots and the enhancement of patient care in robotic surgery, underscoring the technology's potential to improve the precision and efficiency of medical interventions.