Closed-loop Pallet Engagement in Unstructured Environments

This paper addresses the problem of autonomous manipulation of a priori unknown palletized cargo with a robotic lift truck. More specifically, we describe coupled perception and control algorithms that enable the vehicle to engage and drop off loaded pallets relative to locations on the ground or arbitrary truck beds. With little prior knowledge of the objects with which the vehicle is to interact, we present an estimation framework that utilizes a series of classifiers to infer the objects’ structure and pose from individual LIDAR scans. The different classifiers share a low-level shape estimation algorithm that uses a linear program to robustly segment input data to generate a set of weak candidate features. We present and analyze the performance of the segmentation and subsequently describe its role in our estimation algorithm. We then evaluate the performance of the motion controller that, given an estimate for a pallet’s pose, we employ to safely engage a pallet. We conclude with a validation of our algorithms for a set of real world pallet and truck interactions.