Abstract

In this thesis, a novel soft sensor calibration method is proposed for minimally invasive surgery (MIS), based on a gelatin-graphite sensor with high compliance and adaptability developed in previous studies. This approach uses convolutional deep learning that accounts for a sensor’s non-linear behavior and reduces noise amplification. This technique offers a smaller minimum detectable force than other approaches and is particularly useful in sensitive surgical scenarios. The sensor’s performance is characterized by its fine resolution (≤1mN) and accurate force estimation, especially for forces below 400 mN of amplitude. The best calibration (Morse) scheme provides high performance, with a Mean Absolute Error of ≤7.9 mN. This work was validated through comparison among other representative studies and offered a path toward future directions for optimizing and implementing soft robotic sensors in minimally invasive surgeries. The application of this sensor can revolutionize surgical procedures and capitalize on the benefits of soft robotics, potentially enhancing precision and reducing trauma in surgeries. Building on the established capabilities of this calibration method, the thesis further explores its integration with the surgical applications. This integration aims to provide surgeons with a tactile sense that mimics natural touch, thereby improving the control and safety of surgeries. Future studies will aim to enhance the sensor’s performance in minimally invasive surgeries by extending the force sensing range through optimization of material properties and structural design, implementing precise micro-fabrication techniques, developing advanced real-time calibration methods, and integrating the sensor into surgical robotics to evaluate its performance in controlled, simulated MIS scenarios where sensor’s accuracy is validated using physical phantoms to mimic endoluminal procedures.