Unsupervised Cross-Subject Adaptation for Predicting Human Locomotion Intent

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 28; no. 3; pp. 646 - 657
• Main Authors: Zhang, Kuangen, Wang, Jing, de Silva, Clarence W., Fu, Chenglong
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.03.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Adaptation; Classification; Classifiers; Cross-subject adaptation; Disabilities; Electromyography; Evaluation; Feature extraction; Generators; human intent classification; Labelling; Locomotion; Neural networks; Researchers; Robot control; Robot sensing systems; Robots; Training; unsupervised learning; Wearable robots; Wearable technology

Accurately predicting human locomotion intent is beneficial in controlling wearable robots and in assisting humans to walk smoothly on different terrains. Traditional methods for predicting human locomotion intent require collecting and labeling the human signals, and training specific classifiers f...