This paper came from a summer internship at Willow Garage in 2010. The project's goal was easy to describe: Get a PR2 to navigate successfully around the building while pushing a utility cart, without hitting anyone or anything. The project turned into a collaboration with Sachin Chitta, Bhaskara Marthi, and Maxim Likhachev, and worked quite nicely in the end (due in no small part to the ROS nav-stack).
Abstract
Robust navigation in cluttered environments has been well addressed for mobile robotic platforms, but the problem of navigating with a moveable object like a cart has not been widely examined. In this work, we present a planning and control approach to navigation of a humanoid robot while pushing a cart. We show how immediate information about the environment can be integrated into this approach to achieve safer navigation in the presence of dynamic obstacles. We demonstrate the robustness of our approach through long- running experiments with the PR2 mobile manipulation robot in a typical indoor office environment, where the robot faced narrow and high-traffic passageways with very limited clearance.