A Summary of Team MIT's Approach to the Amazon Picking Challenge 2015

TL;DR

This paper summarizes Team MIT's approach to the 2015 Amazon Picking Challenge, highlighting their design, performance, lessons learned, and remaining challenges in robotic object picking from shelves.

Contribution

The paper details MIT's innovative robotic system for shelf picking, including design choices, performance results, and insights gained from the 2015 competition.

Findings

MIT's system achieved competitive picking performance

Key lessons learned for future robotic manipulation

Identification of remaining challenges in automation

Abstract

The Amazon Picking Challenge (APC), held alongside the International Conference on Robotics and Automation in May 2015 in Seattle, challenged roboticists from academia and industry to demonstrate fully automated solutions to the problem of picking objects from shelves in a warehouse fulfillment scenario. Packing density, object variability, speed, and reliability are the main complexities of the task. The picking challenge serves both as a motivation and an instrument to focus research efforts on a specific manipulation problem. In this document, we describe Team MIT's approach to the competition, including design considerations, contributions, and performance, and we compile the lessons learned. We also describe what we think are the main remaining challenges.