Every year, one out of three adults over the age of 65 falls, and about 30% of the falls result in moderate to severe injuries. The high rate of fall-related hospitalizations and the fact that falls are a major source of morbidity and mortality in older adults have motivated extensive interdisciplinary clinical and engineering research with a focus on fall prevention. This research is aimed at developing a medical Cyber Physical System (CPS) composed of a human supervised mobile robot and ambient intelligence sensors to provide continuous evaluation of environmental risks in the home. As a preventive measure to avoid falls, we propose use of mobile robots to detect possible fall risks inside a house. As a step-up to that, we also define a control framework for intelligent, networked mobile robots to semi-autonomously perform assistive and preventive tasks. This framework is integrated in a smart home that provides monitoring and control capabilities of environmental conditions such as objects blocking pathways or uneven surfaces. The main outcome of this work is the realization of this system at Worcester Polytechnic Institute's (WPI) @Home testbed.