The detection, and diagnosis, of sensor faults in real-time is necessary for satisfactory performance of vehicle Electronic Stability Control (ESC) and Roll Stability Control (RSC) systems. This paper presents an observer designed to detect faults of a roll-rate sensor that is robust to model uncertainties and disturbances. A reference vehicle roll angle estimate, independent of roll-rate sensor measurement, is formed from available ESC inertial sensor measurements. Residuals are generated by comparing the reference roll angle, and roll-rate, with the observer outputs. Stopping rules based on the current state of the vehicle and the magnitude of the residuals are then used to determine if a sensor fault is present. The system’s low order allows for efficient implementation in real-time on a fixed-point microprocessor. Modification of the roll-rate sensor signal during in vehicle experiments shows the algorithm’s ability to detect faults. Different vehicles and multiple driving surfaces are tested to show the fault detection is independent of vehicle parameters, sensor noise and driving conditions.