This paper addresses the problem of merging multiple views of a static scene into a common coordinate frame, explicitly considering uncertainty. It assumes that a static world is observed by an agile vision system, whose movements are known with a limited precision, and whose observations are inaccurate and incomplete. It concentrates on acquiring uncertain three-dimensional information from multiple views, rather than on modeling or representing the information at higher levels of abstraction. Two particular problems receive attention: identifying the transformation between two viewing positions; and understanding how errors and uncertainties propagate as a result of applying the transformation. The first is solved by identifying the forward kinematics of the agile camera system. The second is solved by first treating a measurement of camera position and orientation as a uniformly distributed random vector whose component variances are related to the resolution of the encoding potentiometers, then treating an object position measurement as a normally distributed random vector whose component variances are experimentally derived, and finally determining the uncertainty of the merged points as functions of these variances.