Learning from Imperfect Demonstrations: A Human-in-the-Loop Approach for Robotic Manipulation

This paper addresses the challenge of teaching robots complex manipulation tasks using imperfect human demonstrations. We propose a novel human-in-the-loop framework that allows the robot to query a human expert for clarification or correction during policy learning, leading to faster convergence and more robust task performance in real-world unstructured environments, such as logistics and assistive robotics.