Upper extremity function is affected by a variety of neurological conditions. Robotic exoskeletons offer a potential solution for motor restoration. However, their systematic adoption is limited by challenges relative to human intention detection and device control. This position article offers a focused perspective on this topic. That is, on how knowledge gained from the design and implementation of human-machine interfaces (HMIs) for bionic arms can benefit the field of rehabilitation exoskeletons. Three broadly used HMIs in bionic arms are here investigated, including surface electromyography, impedance, and body-powered control. We propose that combinations of these HMIs could push forward upper extremity exoskeleton development. In this context, we provide concrete applicative examples in two selected clinical scenarios, including post-stroke and Duchenne muscular dystrophy individuals. The discussed solutions can open new avenues for the translation of robotic exoskeletons in a large set of clinical settings and enable a class of exoskeleton technologies that could support a broader range of impairment and disease types.