A disk drive is disclosed comprising a disk, a head, and a voice coil motor (VCM) for actuating the head over the disk. The disk drive executes a rotational position optimization (RPO) algorithm to select a next command to execute relative to an estimated seek time computed for each command in a command queue. A seek time parameter is estimated and a seek time delta computed in response to the estimated seek time parameter. The seek time delta is added to a nominal estimated seek time to generate a modified estimated seek time for each command in the command queue, thereby optimizing the RPO algorithm.