Abstract The development of an advanced human–machine interface has always been an interesting research topic in the field of rehabilitation, in which biomedical signals, such as myoelectric signals, have a key role to play. Myoelectric control is an advanced technique concerned with the detection, processing, classification, and application of myoelectric signals to control human-assisting robots or rehabilitation devices. This paper reviews recent research and development in pattern recognition- and non-pattern recognition-based myoelectric control, and presents state-of-the-art achievements in terms of their type, structure, and potential application. Directions for future research are also briefly outlined.