When an organism estimates a property of the environment so as to make a decision (“Do I flee or do I fight?”) or plan an action (“How do I grab that salt shaker without tipping my wine glass along the way?”), there are typically multiple sources of information (signals or “cues”) that are useful. These may include different features of the input from one sense, such as vision, where a variety of cues—texture, motion, binocular disparity, and so forth—aid the estimation of the three-dimensional (3D) layout of the environment and shapes of objects within it. Information may also derive from multiple senses such as visual and haptic information about object size, or visual and auditory cues about the location of a sound. In most cases, the organism can make more accurate estimates of environmental properties or more beneficial decisions by integrating these multiple sources of information. In this chapter, we review models of cue integration and discuss benefits and possible pitfalls in applying these ideas to models of behavior. Consider the problem of estimating the 3D orientation (i.e., slant and tilt) of a smooth