For mobile robots operating in real-world environments, reactive navigation is a useful complement (or even replacement) to pure plan-based metric navigation. Reactive navigation is performed with respect to local perceived features, rather than a global metric reference frame, and can provide reduced installation costs, increased flexibility, and robustness to changes in the environment. To be effective, however, reactive navigation requires fast and reliable perception of the relevant features in the environment. Corridor-like structures are one of the most common features that are used for this purpose. In this paper, we propose a new method for corridor detection from laser data, based on the Hough transform, which is fast, reliable, and noise tolerant. We describe the algorithm, report an extensive experimental evaluation of its performance, and motivate the research with a real application involving the autonomous operation of a loader vehicle in an underground mine.