Demonstrating Large-Scale Package Manipulation via Learned Metrics of Pick Success


Shuai Li
Amazon
Azarakhsh Keipour
Amazon
Kevin Jamieson
University of Washington
Nicolas Hudson
Amazon
Charles Swan
Amazon
Kostas Bekris
Rutgers University
Paper Website

Paper ID 23

Session 3. Self-supervision and RL for Manipulation

Demo

Poster Session Tuesday, July 11

Poster 23

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 workforce fluctuations. The past few years have seen increased interest in automating such repeated tasks but mostly in controlled settings. Tasks such as picking objects from unstructured, cluttered piles have only recently become robust enough for large-scale deployment with minimal human intervention.

This paper demonstrates a large-scale package manipulation from unstructured piles in Amazon Robotics’ Robot Induction (Robin) fleet, which utilizes a pick success predictor trained on real production data. Specifically, the system was trained on over 394K picks. It is used for singulating up to 5~million packages per day and has manipulated over 200~million packages during this paper’s evaluation period.

The developed learned pick quality measure ranks various pick alternatives in real-time and prioritizes the most promising ones for execution. The pick success predictor aims to estimate from prior experience the success probability of a desired pick by the deployed industrial robotic arms in cluttered scenes containing deformable and rigid objects with partially known properties. It is a shallow machine learning model, which allows us to evaluate which features are most important for the prediction. An online pick ranker leverages the learned success predictor to prioritize the most promising picks for the robotic arm, which are then assessed for collision avoidance. This learned ranking process is demonstrated to overcome the limitations and outperform the performance of manually engineered and heuristic alternatives.

To the best of the authors’ knowledge, this paper presents the first large-scale deployment of learned pick quality estimation methods in a real production system.