Assessment of sensorimotor and cognitive function plays a crucial role in all facets of patient care, from diagnosing the specific disease or injury, to management and monitoring of rehabilitation strategies to ameliorate dysfunction. Most assessment scales for sensorimotor function are subjective in nature with relatively coarse rating systems, reflecting that it is difficult for even an experienced observer to discriminate small changes in performance using only the naked eye. Robotic technologies have had a profound impact in basic research to understand fundamental properties of sensorimotor control due to their ability to control the position or forces applied to the limb and their inherent ability to objectively quantify motor behavior. Our general hypothesis is that these same attributes make robotic technologies ideal for creating a new approach to neurological assessment. I will discuss a number of novel robot-based tasks weve developed to assess brain function in subjects with stroke, highlighting the complex patterns of sensory, motor and cognitive deficits that can be quantified with this technology.