Human workers in assembly spend a significant portion of their time retrieving and staging tools and parts for each job. A robotic assistant can provide productivity benefit by performing these non-value-added tasks for the worker. In this project, we are developing a mobile robot to assist workers on an automotive assembly line. The robot must navigate a confined and busy space. Motion planning techniques that treat people as obstacles can significantly degrade the efficiency of the system. We're developing planning techniques the incorporate models of human behavior to anticipate human motions and actions. Our aim is to use these models of human behavior to improve the efficiency with which the robot traverses the line and maneuvers around people.