A Human-Robot Collaboration Framework Based on Human Motion Prediction and Task Model in Virtual Environment

Human-robot collaboration is one of the hot topics in the field of robotics, which has attracted much recent interests. This paper proposes a human-robot collaboration framework that combines a human motion prediction model with a finite state machine-based task model. A virtual human-robot collaboration environment is created, including a robot model, an interactive object model, and a human body model that can be controlled by a skeleton point tracking algorithm. The experimental results show that the precision and recall based on our model are much higher than those based on the traditional Gaussian mixture model. The task model based on finite state machine can effectively model human-robot collaboration tasks.