At IEEE/SICE International Symposium on System Integrations (SII 2019) held in Paris, France, my collaborative student presented following topic.
“Impedance Control based Assistive Mobility Aid through Online Classification of User’s State”
In this research, we are working on robot technology to support daily movement of people (especially the elderly). To do so, online classification of movement intention and appropriate support strategy based on classification results are proposed. Specifically, we employed LSTM-RNN for the online classification, achieving classification accuracy of nearly 90% for the prepared data set. In addition, we proposed a strategy to adaptively adjust the impedance parameters of the robot according to the classification results, and confirmed that unnecessary oscillation of the user can be suppressed in the demonstration.