LOLA Object Manipulation in an Unstructured Environment

Abstract

LOLA won the Office Cleanup event at the 1995 Robot Competition and Exhibition, held as part of the Fourteenth International Conference on Artificial Intelligence. The event called for a robot to pick up trash in an unstructured environment and sort it such that the recyclable trash winded up in the recycle bin and the regular trash in the trash bin. The only allowable information lola was given beforehand were model-based descriptions of the trash and recyclables, which it located using color vision. Much of LOLA's success can be attributed to the simple, fast algorithms and methods that also model sensor uncertainty. The ideas and design philosophy that went into LOLA borrow heavily from those of previous competitors' to which we are greatly indebted. These methods and ideas are discussed here.