Virtual data generation for human intention prediction based on digital modeling of human-robot collaboration

Abstract

Human intention prediction is vital for the efficiency of human-robot collaboration (HRC) and is usually modeled based on data-driven methods. However, due to the complexity and diverse nature of HRC, data collection for human intention prediction suffers from low sampling efficiency which restricts the application of HRC in manufacturing. Different from traditional real world data collection, a digital modeling method for HRC is proposed in this paper to generate virtual HRC data. The dynamic musculoskeletal model of human is adopted to simulate the musculoskeletal dynamics of human. The metabolic energy consumption of human is computed and used as an indicator to evaluate the reality of the generated virtual data. The virtual data are used to train human intention prediction model and compared with experimental data. Experimental results show the reality of virtual data and its effectiveness for human intention modeling in human-robot collaborative assembly. The proposed method has potential for reducing the cost of data collection compared with purely experiments.