Environment-adaptive learning from demonstration for proactive assistance in human–robot collaborative tasks

Abstract

Proactive assistance in human–robot collaboration remains a challenging objective, as the spatial–temporal coordination of the human–robot motion must be considered in conjunction with the object and environmental context. In this paper, we propose an environment-adaptive probabilistic interaction primitive method using learning-from-demonstration. In particular, we propose a novel phase estimation algorithm called Single-axis Uniform Interval Interpolation, which alleviates the restriction of Gaussian or uniform distribution of phase variables. In addition, the environmental constraints in human–robot interactive skills are learned via the regression between environmental parameters and the weight vectors. The proposed method is implemented in a proactive robotic system for typical industrial-motivated human–robot collaborative scenarios, such as assistive push-button assembly and human–robot collaborative object covering. The experimental result validates the effectiveness of the proposed approach.