Ms. Prajakta V Koratkar
Biography
Ms. Prajakta V. Koratkar is currently pursuing her Ph.D. in Robotics at the Defence Institute of Advanced Technology (DIAT), Pune, India. She holds an M.Tech in Industrial Automation and Robotics from Manipal University and a B.E. in Electrical Engineering from Pune University. With over seven years of academic and research experience, she has served as an Assistant Professor at DIAT and Manipal Institute of Technology and as a Guest Faculty in various defence and engineering institutions.
Ms. Koratkar has contributed extensively to teaching postgraduate and undergraduate courses in robotics, mechatronics, AI & ML, automation, sensors, actuators, and Industry 4.0 technologies. She has guided over 39 M.Tech projects, 10+ B.Tech projects, and mentored numerous interns. Her work is supported by multiple funded research projects, including collaborations with DRDO, Saarloha Advanced Materials, and Bharat Electronics Ltd.
She has published more than ten research papers and presented at several international and national conferences in robotics and automation. Additionally, she has delivered invited lectures and training programs for defence personnel, engineers, and academic institutions on cutting-edge topics such as UAVs, robotic vision, cyber-physical systems, and sensor technologies.
Research Interest
Robotic Grippers and Adaptive Control
AI and Machine Learning in Robotics
Sensor Fusion and Tactile Perception
Mechatronics and Robot Navigation
Cybersecurity in Robotic Systems
Industrial Automation and Industry 4.0
IoT-Driven Smart Manufacturing Systems
Autonomous Vehicles and Cyber-Physical Systems
Abstract
"AI-Enabled Sensory Perception for Intelligent Robotic Grasping: Tactile Sensing, Sensor Fusion, and Adaptive Control"
The future of intelligent robotic manipulation hinges on the ability of machines to perceive, interpret, and respond to their environment with human-like precision. This talk presents a comprehensive exploration of AI-enabled sensory perception in robotic hands, with a focus on the integration and experimental evaluation of various sensors for intelligent grasp control. The study investigates how tactile force feedback can be leveraged to detect object properties such as weight, shape, and slippage in real-time, enabling robotic grippers to dynamically adjust grip strength and positioning. Machine learning-driven models for object classification and weight estimation are also explored. The findings offer valuable insights into the role of sensor fusion and perception modeling in enhancing robotic dexterity for applications in industrial automation, healthcare, and logistics. The outcomes of this work have broad relevance to space robotics, next-generation manufacturing, and automated logistics, where robotic end-effectors must perform under variable and unpredictable conditions. The presentation also highlights experimental methodologies, data-driven control strategies, and safety in robotic handling systems.
