Pick Planning Strategies for Large-Scale Package Manipulation

TL;DR

This paper discusses the deployment of learned pick success predictors in Amazon's large-scale package manipulation system, improving efficiency and reliability in warehouse automation.

Contribution

It introduces the first large-scale deployment of learned pick quality estimation methods in a real production warehouse system.

Findings

Successful manipulation of over 2 billion packages

Implementation of a pick success predictor trained on real data

Improved efficiency in large-scale package handling

Abstract

Automating warehouse operations can reduce logistics overhead costs, ultimately driving down the final price for consumers, increasing the speed of delivery, and enhancing the resiliency to market fluctuations. This extended abstract showcases a large-scale package manipulation from unstructured piles in Amazon Robotics' Robot Induction (Robin) fleet, which is used for picking and singulating up to 6 million packages per day and so far has manipulated over 2 billion packages. It describes the various heuristic methods developed over time and their successor, which utilizes a pick success predictor trained on real production data. To the best of the authors' knowledge, this work is the first large-scale deployment of learned pick quality estimation methods in a real production system.