We will examine the hopes and dreams of a decade ago when there was a lot of excitement hi the community about what could be accomplished with model-based vision in robotics. Many of those dreams have not yet materialized because of a lack of availability of "vision" models (as opposed to CAD models), difficulty of constructing vision models, inadequate robustness of model-based recognition and pose-estimation schemes, excessive sensitivity of recognition and pose-estimation schemes to variations in ambient illumination and object surface condition, etc. Against a background of these difficulties, we chart out the progress that has been made in the areas of visual servoing, bin-picking, mobile-robot navigation, etc.