Zulfiqar, Nimra <br/><br/>
Algorithm Development for Distributed Force Estimation During Tactile Sensing / 
Nimra Zulfiqar 
 - 72p.  Soft Copy,  30cm. 
<br/><br/> Vision-based tactile sensors provide an effective solution for robotic manipulation tasks<br/>requiring high sensitivity, such as grasping fragile objects. This research presents a tactile<br/>sensing approach based on a flat elastic skin embedded with visual markers and integrated with<br/>a depth camera on a parallel robotic gripper. A set of algorithms has been developed that process<br/>marker displacements to estimate distributed contact forces and contact areas during object<br/>interaction. These estimations are then utilized in computing distributed tactile pressure values<br/>and for detecting incipient slip through pressure variation analysis. The main contribution of<br/>this research is the development of a unified framework that integrates distributed force<br/>estimation with force-based contact detection and pressure-based slip detection for improved<br/>grasping of fragile objects. Specifically: (1) a marker tracking algorithm is proposed to detect<br/>surface deformation from the tactile skin, enabling distributed force estimation; (2) the<br/>estimated forces are used to compute pressure distribution maps and identify contact regions;<br/>and (3) a slip detection algorithm is introduced that leverages changes in the pressure field to<br/>reliably detect incipient slip during manipulation. Experimental results demonstrate that the<br/>proposed method achieves accurate slip detection with 98.9% success rate, and improves grasp<br/>reliability, achieving 99.5% success in real-time manipulation tasks. The integration of<br/>distributed force, pressure, and slip estimation significantly enhances robotic grasp stability<br/>and enables safe handling of delicate items.<br/> 
<br/><br/><label>Subjects--Topical Terms: </label><br/>MS Biomedical Engineering (BME)      
<br/><br/><label>Dewey Class. No.: </label>610