The EU funded project RADIO brings forward a new health care paradigm according to which a mobile robot platform can act as assistant to an elderly person in his/her domestic environment. Under this context, unobtrusiveness is of paramount importance since the robot should be a natural participant of patients' daily life. However, robot assistance in everyday living still suffers from limited autonomy dictaded by the robot battery. This paper presents the approach taken in the project in order to reduce, to the extent possible, the usage of the power-hungry processing components. This minimizes the need for revisiting the robot charging station during the day, by using hardware accelerated ultra-low-power monitoring during the periods of inactivity.