bin picking
{{short description|Problem in computer vision and robotics}}
{{for|the problem of efficiently packing items into a bin|bin packing}}
Bin picking (also referred to as random bin picking) is a core problem in computer vision and robotics. The goal is to have a robot with sensors and cameras attached to it pick-up known objects with random poses out of a bin using a suction gripper, parallel gripper, or other kind of robot end effector.
Early work on bin picking made use of Photometric Stereo
{{cite journal |
title=Photometric Method for Determining Surface Orientation from Multiple Images |
author = Robert J. Woodham |
journal = Optical Engineering |
year=1980 |
volume=19 |
number=1
|
page = 139 |
doi = 10.1117/12.7972479 |
bibcode = 1980OptEn..19..139W }}
in recovering the shapes of objects and to determine their orientation in space.
Amazon previously held a competition focused on bin picking referred to as the "Amazon Picking Challenge", which was held from 2015 to 2017.{{cite web|url=http://www.robocup2016.org/en/events/amazon-picking-challenge/|title=Amazon Picking Challenge - RoboCup -|website=Robocup2016.org|access-date=2018-08-16|archive-url=https://web.archive.org/web/20180814134514/http://www.robocup2016.org/en/events/amazon-picking-challenge/|archive-date=2018-08-14|url-status=usurped}} The challenge tasked entrants with building their own robot hardware and software that could attempt simplified versions of the general task of picking and stowing items on shelves. The robots were scored by how many items were picked and stowed in a fixed amount of time. {{cite web|url=https://www.amazonrobotics.com/site/binaries/content/assets/amazonrobotics/arc/2017-amazon-robotics-challenge-rules-v3.pdf|title=Challenge Rules}} The first Amazon Robotics challenge was won by a team from TU Berlin in 2015, {{cite web|url=https://www.amazonrobotics.com/site/binaries/content/assets/amazonrobotics/pdfs/2015-apc-summary.pdf|title=2015 Results}} followed by a team from TU Delft and the Dutch company "Fizyr" in 2016. {{cite web|url=https://www.engadget.com/2016/07/05/amazon-robot-picking-challenge-2016-winner/|title=2016 Winner|date=5 July 2016 }} The last Amazon Robotics Challenge was won by the Australian Centre for Robotic Vision at Queensland University of Technology with their robot named Cartman. {{cite web|url=https://spectrum.ieee.org/aussies-win-amazon-robotics-challenge|title=2017 Results}} The Amazon Robotics/Picking Challenge was discontinued following the 2017 competition.
Although there can be some overlap, bin picking is distinct from "each picking"{{cite web|url=https://www.mhlc.com/archives/2015/Track%205-Innovate/T5S8%20Fully%20Automated%20Random%20Each%20Picking%E2%80%A6no,%20really..pdf|title=Fully Automated Random Each Picking…..no really|website=Mhlc.com|accessdate=17 August 2018|archive-url=https://web.archive.org/web/20180817161251/https://www.mhlc.com/archives/2015/Track%205-Innovate/T5S8%20Fully%20Automated%20Random%20Each%20Picking%E2%80%A6no,%20really..pdf|archive-date=17 August 2018|url-status=dead}}{{cite web|url=https://nsf.gov/awardsearch/showAward?AWD_ID=1632460&HistoricalAwards=false|title=NSF Award Search: Award#1632460 - SBIR Phase II: Versatile Robot Hands for Warehouse Automation|website=Nsf.gov}} and the bin packing problem.