Scheduling Robotic Collaboration Based on Human Motion Analysis

In human–robot collaboration (HRC), having a clear understanding between the human and robot is essential for maintaining safety and productivity throughout the task. A robot not only needs to be aware of the task sequences required to finish a task but also needs to be able to predict the future actions of the human. Predicting the human motions can help the robot preplan its trajectory to prevent collisions with the human throughout the task. While previous methods could predict human motions for HRC, their predictions were not applied to fine motions throughout a task. In a realistic industrial setting, human workers will likely have distinct motions unique to a particular body section and subtask. This chapter focuses on simultaneously predicting and segmenting the human’s motion and using the segmentation results for scheduling a robot’s involvement in a collaborative task. A real-world example is presented to demonstrate the utility of the proposed method.