Hybrid Human Motion Prediction for Action Selection Within Human-Robot Collaboration

An initial prediction and fine-tuning model based on improving GCN for 3D human motion prediction

“…Motion prediction technology helps robots understand human behavior. This technology is of great value in areas such as intelligent security, autonomous driving (Ge et al, 2019 ; Djuric et al, 2020 ; Gao et al, 2020 ), object tracking, and human-robot collaboration (Liu and Wang, 2017 ; Oguz et al, 2017 ; Liu et al, 2019a , 2021 ; Li et al, 2020b ; Liu and Liu, 2020 ; Ding et al, 2021 ; Mao et al, 2021 ).…”

Task allocation and planning for product disassembly with human–robot collaboration

“…One such example is the integration of a minimum-jerk model-based algorithm for human motion prediction in [146], specifically designed to facilitate local obstacle avoidance in close HRC scenarios. Another approach, presented in [147], suggested a two-stage prediction method that combines the classical minimum-jerk model with Dynamic Movement Primitives (DMPs) to forecast human motion while taking into account obstacles present in the environment.…”

Data Driven Models for Human Motion Prediction in Human-Robot Collaboration

“…Maeda et al also used imitation learning to construct a mixture model of human-robot interaction primitive, which allows for both action recognition and human-robot movement coordination [39]. In [40], a hybrid motion prediction method that combines a minimum-jerk model and a dynamic movement primitives system is used to predict human motion. Oguz et al proposed a supervised learning framework to imitate close proximity dyadic interaction movement behavior and used recurrent neural networks (RNNs) to learn generalized policies [41].…”