This paper deals with the order-batching problem in low-level picker-to-part warehousing system. In order batching, orders are combined as much as possible so that the order picker can pick a set of combined orders at the same time. For each of the three routing policies, traversal, return, and midpoint routing policy, we develop an efficient order-batching algorithm based on a cluster analysis. To show the validity of the algorithms, they are compared with an existing algorithm in terms of the total travel time and number of batches grouped.