Innovative Sensing and Data Processing for Deformation and Texture Classification in Robot-Assisted Minimally Invasive Surgery

Tactile feedback is crucial in robot-assisted minimally invasive surgery (RAMIS), especially for surgeons palpating subsurface tumors and other organ structures. This research introduces a novel approach to tactile perception in RAMIS, focusing on deformation and texture detection. The proposed solution involves the design of a sensory system and two main data processing phases: feature extraction and recognition. During feature extraction, data is gathered from two micro-electromechanical (MEMS) sensors and a force-sensitive resistor (FSR) sensor attached to an EndoWrist thoracic grasper instrument compatible with the da Vinci Surgical System. Digital signal processing techniques are then applied to process the acquired data. In the recognition phase, the extracted features serve as inputs for training and testing two advanced machine learning algorithms: Reflex Fuzzy Min-Max Neural Network (RFMN) and Time Series Classification - Learning Shapelets (TSC-LS). These algorithms aim to accurately classify objects with varying softness and roughness into corresponding deformation or texture labels. The research presents preliminary experiments and results analyzing the performance metrics of the two machine learning algorithms.