Towards Multi-User Activity Recognition through Facilitated Training Data and Deep Learning for Human-Robot Collaboration Applications

Human-robot interaction (HRI) research is progressively addressing multi-party scenarios, where a robot interacts with more than one human user at the same time. Conversely, research is still at an early stage for human-robot collaboration (HRC). The use of machine learning techniques to handle such type of collaboration requires data that are less feasible to produce than in a typical HRC setup. This work outlines concepts of design of concurrent tasks for non-dyadic HRC applications. Based upon these concepts, this study also proposes an alternative way of gathering data regarding multiuser activity, by collecting data related to single subjects and merging them in post-processing, to reduce the effort involved in producing recordings of pair settings. To validate this statement, 3D skeleton poses of activity of single subjects were collected and merged in pairs. After this, the datapoints were used to separately train a long short-term memory (LSTM) network and a variational autoencoder (VAE) composed of spatio-temporal graph convolutional networks (STGCN) to recognise the joint activities of the pairs of people. The results showed that it is possible to make use of data collected in this way for pair HRC settings and get similar performances compared to using data regarding groups of users recorded under the same settings, relieving from the technical difficulties involved in producing these data.