In this paper we propose a novel design for the Lane Change Assistant (LCA). For drivers on the highway, LCA advises them on whether it is safe to change lanes under the current traffic conditions. We focus on how the LCA can provide a reliable advice in practice by considering the issues of changing circumstances and measurement uncertainties. Under some generic assumptions we develop a microsimulation model for the lane change safety assessment. The model is in line with the car following models and lane change algorithms available in literature. It retains a probabilistic character to accurately represent realistic situations. Based on a sensitivity study we are able to develop a robust design for the LCA. In this design the system accounts for the practical uncertainties by including appropriate extra safety distances. The driver interface consists of a spectrum of five LED lights, each operating on a distinct color (varying from red to green) and guaranteeing a certain safety degree. Our results allow car developers to easily acquire reliable designs for the LCA.