Robust Planning and Control for Agile Robotics for Logistics

As part of the Agile Robotics for Logistics (ARL) program, we are developing a planning and control framework for advanced autonomous vehicle operations in an environment of unprecedented complexity. The ARL program seeks to develop and demonstrate semi-autonomous robotics capabilities in an unstructured environment, through the operation of a full-scale forklift in an outdoor warehouse scenario. This autonomous forklift must be able to manipulate and transport pallet loads in the presence of cluttered spaces, dynamic obstacles (including humans), and uncertain terrain. Furthermore, the system architecture cannot depend on existing infrastructure, including prior maps or reliable GPS data.

We have implemented a hierarchical planning and control strategy to achieve the desired autonomy. Using closed-loop rapidly-exploring random trees (RRT), the navigation planner can identify and robustly track obstacle-free trajectories. This planner guarantees waypoint arrival within desired position and heading tolerances, at which point there is a handoff to the manipulation phase. Using a steering controller coupled with perception filters, the manipulation phase guides the forklift to autonomously pick up and drop off arbitrarily placed-pallets, whether on a truck bed or the ground.

At a June 2009 demonstration of the prototype forklift at Fort Belvoir, VA, our framework demonstrated robust path planning capabilities in a realistic warehouse environment.