Expanding our research into intelligent automation, HDL develops vision-based robotic manipulation systems that enable robots to dynamically perceive and interact with their environments. By integrating computer vision with deep learning-based object detection and pose estimation, we compute optimal grasp configurations and implement robust visual feedback control strategies. Building upon our core expertise in human motion analysis, we are exploring human-to-robot motion transfer and intuitive teleoperation. From deciphering human dynamics to deploying adaptive, vision-driven robots, HDL effectively bridges the fields of biomechanics, perception, and control.