Development of a Practical Tool in Pick-and-Place Tasks for Human Workers

Abstract

We introduce smart hand, a practical tool for human workers in pick-and-place tasks. It is developed to avoid picking up the wrong thing from one location or place the things in an unexpected location. Smart hand features sensors (e.g., imaging sensors, motion sensors) to sense the world and offers suggestions or aid based on the sensed results when a human worker is performing a pick-and-place task. A smart hand prototype is made in the study. In our design, the smart hand has an RGB-D sensor and an inertial measurement unit (IMU). RGB-D sensor is used to do object detection and distance/position estimation while IMU is used to track the motion of the smart hand. An experiment is conducted to compare the two working conditions that a subject performs the pick-and-place tasks with or without the smart hand. The experiment results proved that the smart hand can avoid human errors in pick-and-place tasks.