pfn in warehouse automation
play

PFN in Warehouse Automation Then, now, and the future May 30, 2018 - PowerPoint PPT Presentation

Dec 28, 2022 •477 likes •656 views

PFN in Warehouse Automation Then, now, and the future May 30, 2018 Wilson Ko Who are we? Tokyo based company focused on Machine Learning and Distributed Computing, branch office in Berkeley Were hiring at both locations! Major fields of

  1. PFN in Warehouse Automation Then, now, and the future May 30, 2018 Wilson Ko

  2. Who are we? Tokyo based company focused on Machine Learning and Distributed Computing, branch office in Berkeley We’re hiring at both locations! Major fields of interest • Autonomous Driving • Bio healthcare • Manufacturing www.toyota.ca www.bioprocessonline.com www.fanuc.co.jp 2 / 17

  3. Brief history 2006 • Preferred Infrastructure founded 2014 • Preferred Networks founded 2014 • Partnered with Toyota Motor Corporation 2015 • Released Chainer 2015 • Partnered with Fanuc Corporation 2016 • Amazon Picking Challenge (2nd place) 2016 • Partnered with Japan National Cancer Center 2017 • Launched private supercomputer 2017 • Trained ImageNet in 15 minutes 3 / 17

  4. Powered by Chainer • Flexible: Flexibility to represent new complex models • Intuitive: Suitable for rapid prototyping - Define by run • Powerful: Supports CUDA and multiple GPUs with little effort. • Open Source: https://github.com/chainer/chainer 4 / 17

  5. Visual Inspection Detect anomalies on products, e.g. scratches, stains, bumps etc. Used to inspect car exteriors, smartphones, fabric etc. Challenges • Not much data available of damaged products • Detailed annotations of the anomaly location are needed Our solution • Automated defect detection system powered by Chainer • Only 100 normal pictures and 20 for defects to train 1 1 The number of pictures may change per target 5 / 17

  6. Fanuc Bin-picking https://youtu.be/ydh_AdWZflA 6 / 17

  7. APC 2016 7 / 17

  8. Warehouse Bin-picking - APC 2016 8 / 17

  9. Warehouse Bin-picking - APC 2016 • 200 msec inference time per scene 9 / 17

  10. Warehouse Bin-picking - ICRA 2017 10 / 17

  11. Warehouse Bin-picking - Latest system • Asynchronous planning/movement by decoupling camera • Average cycle time of 6 seconds vs 12 seconds for humans • Handling unknown objects - no registration needed 11 / 17

  12. Warehouse Bin-picking - Latest system https://youtu.be/5pSq7qFAL0M https://youtu.be/x0IEHDy5G-8 12 / 17

  13. Interactive Bin-picking Given spoken command, pick an item and place it at desired destination Challenges • A wide variety of object referring expressions ”a bear doll”, ”the animal plush”, ”that brown fluffy thing” • Human instructions are ambiguous and erroneous ”a dog doll?” 13 / 17

  14. Interactive Bin-picking - Architecture Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions - ICRA 2018 14 / 17

  15. Please come by! Interactively picking real-world objects with unconstrained spoken language instructions • Interactive poster session: Wed 10:30-13:00 @ pod T • Best award candidate on HRI: Wed 16:00-16:15 @ Great Hall https://youtu.be/DGJazkyw0Ws 15 / 17

  16. Future work • Visual inspection • Keep improving UX • Ensure quality • Reduce data needed • Bin-picking • Improve picking accuracy • Multi-fingered grasping • Few-shot learning • Online learning 16 / 17

  17. Please come by! We’re hiring in Tokyo and Berkeley! Interactively picking real-world objects with unconstrained spoken language instructions • Interactive poster session: Wed 10:30-13:00 @ pod T • Best award candidate on HRI: Wed 16:00-16:15 @ Great Hall 17 / 17

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

Recommend

Warehouse Safety Regional Challenges Presented by: XXXXXXXXXX Shailen Shukla Business

Warehouse Safety Regional Challenges Presented by: XXXXXXXXXX Shailen Shukla Business

Warehouse Safety Regional Challenges Presented by: XXXXXXXXXX Shailen Shukla Business Head Jumbo Logistics LLC Warehouse Safety and Automation RoundTable Shailen Shukla 31 May 2016 31 May 2016 Warehouse Safety and Automation

472 views • 44 slides
1 Automation Overview Definition Automation (automation, Automation ) : 1) set of all measures

1 Automation Overview Definition Automation (automation, Automation ) : 1) set of all measures

Industrial Automation Spring 2019, EPFL 1 Automation Overview Definition Automation (automation, Automation ) : 1) set of all measures aiming at replacing human work through machines (e.g. automation is applied science) 2) the

1.39k views • 63 slides
STRATEGIC LOCATION Add: Warehouse No.5, 2 nd Floor, Tan Cang-Cat Lai warehouse, Cat Lai Ward,

STRATEGIC LOCATION Add: Warehouse No.5, 2 nd Floor, Tan Cang-Cat Lai warehouse, Cat Lai Ward,

CAT LAI BONDED WAREHOUSE Dear Valued Customers, Firstly, Tan Cang Warehousing JSC would like to express our sincere thanks for your interest in our service. From December 2015, we opened new service of Bonded warehouse inside Tan Cang Cat Lai

162 views • 3 slides
Data Warehouse Update March 19, 2019 Agenda Why a data warehouse? Why THIS data

Data Warehouse Update March 19, 2019 Agenda Why a data warehouse? Why THIS data

Data Warehouse Update March 19, 2019 Agenda Why a data warehouse? Why THIS data warehouse, and how? What does the data warehouse do? What can the data warehouse do for me ? Next steps, a promise, a pledge, an invitation, and

206 views • 10 slides
An Overview of Data Warehousing and OLAP T echnology What is a data warehouse? A

An Overview of Data Warehousing and OLAP T echnology What is a data warehouse? A

An Overview of Data Warehousing and OLAP T echnology What is a data warehouse? A multi-dimensional data model Data warehouse architecture Data warehouse implementation lecture 2 1 What is Data Warehouse? A decision support

488 views • 35 slides
Financial Data Financial Data Financial Data Financial Data Warehouse Warehouse Warehouse

Financial Data Financial Data Financial Data Financial Data Warehouse Warehouse Warehouse

11/3/2015 WA S H I N G T O N S T AT E U N I V E R S I T Y Financial Data Financial Data Financial Data Financial Data Warehouse Warehouse Warehouse Warehouse Some day, on the corporate balance sheet, there will be an entry which

311 views • 13 slides
Europe Manchester, England North America - Factory Lehi, UT HQ & Warehouse Salt Lake

Europe Manchester, England North America - Factory Lehi, UT HQ & Warehouse Salt Lake

Europe Manchester, England North America - Factory Lehi, UT HQ & Warehouse Salt Lake City, UT Warehouse Vancouver, BC Warehouse Los Angeles, CA Warehouse & Factory New York Warehouse Texas Factory Missouri -

622 views • 28 slides
BI and WIC Data Warehouse Project Overview Reason for the Data Warehouse project EBT

BI and WIC Data Warehouse Project Overview Reason for the Data Warehouse project EBT

BI and WIC Data Warehouse Project Overview Reason for the Data Warehouse project EBT introduces to WIC a wealth of valuable information Thousands of individual food products, multiple NTEs for each Possibilities to improve program

429 views • 13 slides
2. Role of Warehouse Managers Warehouse managers are expected to recognize and balance other trade

2. Role of Warehouse Managers Warehouse managers are expected to recognize and balance other trade

2. Role of Warehouse Managers Warehouse managers are expected to recognize and balance other trade offs as follows: accuracy; increased throughput vs. reduction in labour cost control; costs; cleanliness; storage density vs. quicker

474 views • 6 slides
Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance

Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance

Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance other tradeoffs as follows: accuracy; increased throughput vs. reduction in labour cost control; costs; cleanliness; storage density vs.

244 views • 9 slides
Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance

Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance

Chapter 2: Role of Warehouse Managers Warehouse managers are expected to recognize and balance other tradeoffs as follows: accuracy; increased throughput vs. reduction in labour cost control; costs; cleanliness; storage density vs.

397 views • 6 slides
Industrial Automation Automation Industrielle Industrielle Automation 9.2 Dependability -

Industrial Automation Automation Industrielle Industrielle Automation 9.2 Dependability -

Industrial Automation Automation Industrielle Industrielle Automation 9.2 Dependability - Evaluation Estimation de la fiabilit Verlsslichkeitsabschtzung Dr. Jean-Charles Tournier CERN, Geneva, Switzerland 2015 - JCT The material

1.78k views • 91 slides
Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average

Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average

Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average between 1 and 5 % of total sales depending on the type of company and the value of its goods. Warehousing also makes up around 22 % of a companys

621 views • 14 slides
Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average

Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average

Chapter 12, 13 Warehouse Cost and Performance Cost The cost of operating a warehouse can average between 1 and 5 % of total sales depending on the type of company and the value of its goods. Warehousing also makes up around 22 % of a companys

371 views • 13 slides
DATA WAREHOUSE How Business Intel and Data Warehouse works Information DEG uses Teacher

DATA WAREHOUSE How Business Intel and Data Warehouse works Information DEG uses Teacher

DATA WAREHOUSE How Business Intel and Data Warehouse works Information DEG uses Teacher Intervention Attendance Assessment Assign Teacher Schedules Programs Absence Enrollment Special Ed Qualifications Professional Behavior Finance

562 views • 6 slides
Industrial Automation Automation Industrielle Industrielle Automation Safety analysis and

Industrial Automation Automation Industrielle Industrielle Automation Safety analysis and

Industrial Automation Automation Industrielle Industrielle Automation Safety analysis and standards 9.6 Analyse de scurit et normes Sicherheitsanalyse und Normen Prof Dr. Hubert Kirrmann & Dr. B. Eschermann ABB Research Center,

799 views • 31 slides
T agging CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu T odays Agenda

T agging CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu T odays Agenda

Part-of-Speech T agging CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu T odays Agenda What are parts of speech (POS)? What is POS tagging? How to POS tag text automatically? Source: Calvin and Hobbs Parts of

1.29k views • 68 slides
Preliminary Injunctions, TROs and Declaratory Judgments Requests for emergency or non-monetary

Preliminary Injunctions, TROs and Declaratory Judgments Requests for emergency or non-monetary

Preliminary Injunctions, Temporary Restraining Orders and Declaratory Judgments Jerry Brown January 25, 2012 Preliminary Injunctions, TROs and Declaratory Judgments Requests for emergency or non-monetary relief: -Preliminary Injunctions

371 views • 34 slides
Algorithms for NLP IITP, Spring 2020 Lecture 5: Vector Semantics Yulia Tsvetkov 1 Neural LMs

Algorithms for NLP IITP, Spring 2020 Lecture 5: Vector Semantics Yulia Tsvetkov 1 Neural LMs

Algorithms for NLP IITP, Spring 2020 Lecture 5: Vector Semantics Yulia Tsvetkov 1 Neural LMs (Bengio et al, 03) Low-dimensional Representations Learning representations by back-propagating errors Rumelhart, Hinton & Williams,

1.36k views • 68 slides
and then we will discuss the process and the outcome. 1 2 Assortment of thoughts in no

and then we will discuss the process and the outcome. 1 2 Assortment of thoughts in no

In this presentation we discuss the processing of the first water reservation adjudication between the state (DNR) and the USFSW. We present details about each agency and our policies, details about the Uganik River and why it was selected

388 views • 26 slides
An overview of the Fires, Asian, and Stratospheric Transport - Las Vegas Ozone Study 2017 ( FAST

An overview of the Fires, Asian, and Stratospheric Transport - Las Vegas Ozone Study 2017 ( FAST

An overview of the Fires, Asian, and Stratospheric Transport - Las Vegas Ozone Study 2017 ( FAST -LVOS) 2013 Where does the high springtime ozone in the Southwest come from? Angel Peak Andrew O. Langford NOAA/ESRL Chemical Sciences Division

201 views • 9 slides
Adversarial Examples are a Natural Consequence of Test Error in Noise Nic Ford*, Justin Gilmer*,

Adversarial Examples are a Natural Consequence of Test Error in Noise Nic Ford*, Justin Gilmer*,

Adversarial Examples are a Natural Consequence of Test Error in Noise Nic Ford*, Justin Gilmer*, Nicholas Carlini, Dogus Cubuk *equal contribution Confidential + Proprietary Confidential + Proprietary Robust (out of distribution)

546 views • 16 slides
The Human Component in Automated Bug Finding Christian Holler (:decoder) Staff Security Engineer

The Human Component in Automated Bug Finding Christian Holler (:decoder) Staff Security Engineer

The Human Component in Automated Bug Finding Christian Holler (:decoder) Staff Security Engineer ~ 16M lines source code ~ 16M lines source code Last month: 340 authors with 2,475 commits Interfaces Media Formats Markup Fonts Languages

1.12k views • 72 slides
Precise and Scalable Detection of Double-Fetch Bugs in OS Kernels Meng Xu , Chenxiong Qian,

Precise and Scalable Detection of Double-Fetch Bugs in OS Kernels Meng Xu , Chenxiong Qian,

Precise and Scalable Detection of Double-Fetch Bugs in OS Kernels Meng Xu , Chenxiong Qian, Kangjie Lu + , Michael Backes*, Taesoo Kim Georgia Tech | University of Minnesota + | CISPA, Germany* 1 What is Double-Fetch? Address Space

1.21k views • 67 slides

More recommend