Simon Manschitz, "Learning, generating and adapting wave gestures for expressive human-robot interaction", ACM/IEEE International Conference on Human Robot Interaction, 2020.

While many humanoid robots can perform basic wave gestures, these gestures are usually hard-coded behaviors. Consequently, the gesture looks rather stiff since there is no variance in the execution of the movement. This study proposes a novel imitation learning approach for the stochastic generation of human-like rhythmic wave gestures and their modulation for effective nonverbal communication through a probabilistic formulation using joint angle data from human demonstrations. This is achieved by enabling the modulation of the overall expression characteristics of the gesture (e.g., arm posture, waving frequency and amplitude) in the frequency domain and through regulation of these qualities for few out of the total joints of the system. The method was evaluated on a robotic arm with 6 degrees of freedom in a simulation environment. The results show that the method provides efficient encoding and modulation of rhythmic movements and that generalization to previously unseen waving patterns is achievable while preserving the human-like qualities of the movement.