AutOTranS: an Autonomous Open World Transportation System
This addresses the challenge of automating mobile manipulation tasks in dynamic, unknown outdoor settings, such as roadside trash collection, with incremental improvements in integration and performance.
The paper tackles the problem of autonomously picking up, transporting, and dropping off novel objects in unstructured outdoor environments, achieving an end-to-end success rate of 85% across various objects like trash bags and gardening tools.
Tasks in outdoor open world environments are now ripe for automation with mobile manipulators. The dynamic, unstructured and unknown environments associated with such tasks -- a prime example would be collecting roadside trash -- makes them particularly challenging. In this paper we present an approach to solving the problem of picking up, transporting, and dropping off novel objects outdoors. Our solution integrates a navigation system, a grasp detection and planning system, and a custom task planner. We perform experiments that demonstrate that the system can be used to transport a wide class of novel objects (trash bags, general garbage, gardening tools and fruits) in unstructured settings outdoors with a relatively high end-to-end success rate of 85%. See it at work at: https://youtu.be/93nWXhaGEWA