ROS-Industrial Asia Pacific Workshop 2019 Banner Image

ROS-Industrial Asia Pacific Workshop 2019

ROS-Industrial Open Source Software for Automation and Robotics

Tuesday, 18 - 19 Jun, 2019 (Singapore)

Advanced Remanufacturing and Technology Centre, Singapore, 3 Cleantech Loop, #01-01, CleanTech Two, Singapore, , Singapore

Speaker Summary

Speaker

Title

PDF

Video

Mr. Ian Alferez
TechSource Systems

MathWorks Robotics System Toolbox + ROS == Faster Time to Successful Deployment

 Link

Link

Mr. Levi Armstrong
Southwest Research Institute

Updates from ROS-Industrial Consortium Americas

 

Link

Mr. Erik Boasson
ADLINK

From SPLICE to DDS to ROS2 and Cyclone DDS

Link

Link

Dr. Ryan Chen
ADLINK

Release the Power of ROS 2.0 Using ADLINK ROScube and Controller

Link

Link

Mr. Harshavardhan Deshpande
Fraunhofer IPA

Updates from ROS-Industrial Consortium Europe

Link

Link

Mr. Shawn Fernando
Woodside

Intelligent Assets - Incorporating IOT, AI and Robotics to Improve Business Value

 

 

Dr. Michael Grey
Open Robotics

Exciting New Features in Gazebo

 

Link

Mr. Alejandro Hernández
Acutronic Robotics

H-ROS, a Communication Bus for Robots that Provides Real-time, Determinism, Synchronization, Security and Safety

Link

Link

Dr. Risto Kojcev
Acutronic Robotics

MARA, a Fully Modular Articulated Robotic Arm, the First ROS 2.0 Based Industrial Robot

Link

Link

Mr. Tony Lin
Microsoft

Bringing the Power of Intelligent Edge and Intelligent Cloud to ROS

Link

Link

Ms. Sharron Liu
Intel Corporation

Intelligence, Performance, Improvements - Robot Software Kit for ROS2

 

 

Asst. Prof. Mohan Rajesh Elara
Singapore University of Technology and Design, 
Lionsbot

The Rise of ROS Powered Self-reconfigurable Maintenance Robots

Link

Link

Mr. Masaru Ken Morita
Yaskawa Electric Corporation

Implementation Verification of Picking System for Industrial Robot using ROS and MATLAB

Link

Link

Mr. Alok Pathak
Cognicept Systems

Robot-Ops and Intervention: Enabling Faster and Efficient Robots’ Deployment

Link

Link

Dr. Morgan Quigley
Open Robotics

Exciting New Features in ROS 2.0

 

Link

Mr. Lian Jye Su
ABI Research

Open Source Robotics Projects: Current Development, Technology Trends and Best Practices

Link

Link

Mr. Erik Unemyr
Advanced Remanufacturing and Technology Centre

Updates from ROS-Industrial Consortium Asia Pacific

Link

Link

 

Detailed Speaker Information

 

MathWorks Robotics System Toolbox + ROS == Faster time to successful deployment

by Mr Ian Alferez
Senior Application Engineer and Team Leader,
TechSource Systems

< Back

 

Abstract

Robotics System Toolbox™ provides algorithms and hardware connectivity for developing autonomous robotics applications for aerial and ground vehicles, manipulators, and humanoid robots. Toolbox algorithms include path planning and path following for differential drive robots, scan matching, obstacle avoidance, and state estimation. For manipulator robots, the system toolbox includes algorithms for inverse kinematics, kinematic constraints, and dynamics using a rigid body tree representation.

The system toolbox provides an interface between MATLAB® and Simulink® and the Robot Operating System (ROS) that enables you to test and verify applications on ROS-enabled robots and robot simulators such as Gazebo. It includes examples showing how to work with virtual robots in Gazebo and with actual ROS-enabled robots.

In this session, you will learn how to leverage Robotics System Toolbox™ algorithms to support workflows related to articulated robots. For example, given a set of desired joint configuration waypoints and a torque-controlled manipulator, you can implement the computed-torque controller using the robotics.RigidBodyTree.inverseDynamics function. The controller enables the robot to follow the given configuration waypoints along a smooth trajectory.

You can then generate C++ code or a ROS node from a Simulink model and automatically deploy it to a ROS network. Support for Simulink external mode lets you view signals and change parameters while your deployed model is running.

The Seminar/Presentation will allow you to understand:

  • How MATLAB and Simulink integrates with ROS
  • Use MATLAB features to create your algorithms to be used in ROS

 

Speaker Biography

Ian M. Alferez is the Senior Application Engineer – Team Lead at Techsource Asia. He specializes in in the field of embedded system (embedded coder configuration), data analytics (Machine Learning) and technical computing with MATLAB/Simulink. He holds a Bachelor of Science in Electronics and Communication Engineering.

Before joining Techsource Asia, he was working as a Software Development Engineer at Lear Corporation where he polished his skills in Model Based Design for Safety Critical Products with regards to the Verification and Validation Workflow and Embedded Software / Hardware.

 

 

 

 

RIC-Americas – A Year of Learning and Growth

by Mr Levi Armstrong
Group Leader Collaborative Systems Section,
Southwest Research Institute

< Back

 

Abstract

An overview of the last year related to the ROS-Industrial Consortium Americas including a review of the roadmap, changes to the technical direction and recent developments and proposed strategies to manage the changing landscape of open-source robotics development. Matt Robinson will review developments that benefitted ROS-Industrial and the Americas Consortium, including an overview of feedback and proposed strategic approaches to address the feedback. Levi Armstrong will share the latest technical developments including new optimized path planning, ROS2 migration challenges, and other technical updates of interest.

 

Speaker Biography

Levi Armstrong is the Technical Lead for the ROS-Industrial Consortium Americas and the group leader of the Collaborative Systems Section at Southwest Research Institute (SwRI). Armstrong has developed technical knowledge in the areas of optimization-based motion planning, graph-based motion planning, collision detection, calibration, meshing and perception to develop custom automation solution for industry. Prior to his current role, Armstrong was an Engineer at Bell Helicopter focused on low-cost composite manufacturing leveraging automation in the areas of drilling, routing, deburring, machining, and heat treat to meet aerospace engineering specifications. He holds a B.S. and M.E. in Aerospace Engineering from the University of Texas at Arlington.

 

 

 

Erik Boasson

 

From SPLICE to DDS to ROS2 and Cyclone DDS

by Mr Erik Boasson
Senior Technologist,
ADLINK

< Back

 

Abstract

With ROS2 robotics has become part of a long history of building real-time control systems using DDS and its predecessors. The system that 35 years ago drove the invention of DDS (née SPLICE) is still around, actively developed and used. Its stable basis allowed integrating new subsystems and upgrading hardware and software. The secret to this longevity is putting the data first and having the right abstractions in place.

DDS today incorporates the many lessons learned over all that time and in many different systems. Lessons that range from simply achieving world-leading performance to the subtleties of efficient reliable multicasting and tolerating failures in applications. Security adds a whole new dimension, and DDS has taken a military-grade approach while minimising impact on performance.

ROS2 inherits all this — but with an easier-to-use interface. No doubt, for ROS2 to flourish over the next decade, new demands will be placed on DDS. At least one, Eclipse Cyclone DDS has picked up the clue will help make this possible.

 

Speaker Biography

Erik Boasson is a member of the Technology Office of ADLINK Technology. His focus is on DDS, its applications and future developments, and currently his efforts are mostly towards developing Eclipse Cyclone DDS. He has more than two decades of experience in the field, starting at the source of data-centric programming model at Hollandse Signaalapparaten BV in the ’90s. His implementation of the SPLICE architecture there has proven itself in several contexts, including as a tool to convince the US DoD to mandate data-centric systems.

 

 

 

 

Release the Power of ROS 2.0 Using ADLINK ROScube and Controller

by Dr Ryan Chen
Special Assistant to Chairman,
ADLINK

< Back

 

Abstract

ADLINK is a global industrial solution company across various vertical markets including industrial robot, transpiration, aerospace, smart city, smart manufacturing, and military. When IIoT makes things connected, there’s an important thing most people miss, that is “distributed IoT platform.” ROS 2 is embedded with DDS (data distribution service) technology, which is an ADLINK Real-Time data connectivity technology, offering the peer-to-peer pub/sub behavior for a larger number of connected devices. With several QoS setting of DDS, ROS 2.0-based ROScube can ensure the quality of transmission among ROS nodes/robots.

 

Speaker Biography

Ryan Chen got his Ph.D. degree in National Taiwan University. Now, he’s special assistant to chairman and head/architect of ARPG (advanced robotic platform group) of ADLINK with more than 10 years’ experience in industry automation, industrial connectivity, and AI algorithms. His skill is good at business and Technology development.

 

 

 

 

Updates from ROS-Industrial Europe Consortium

by Mr Harshavardhan Despande
Research Associate
Fraunhofer IPA

< Back

 

Abstract

Introduction to Fraunhofer society, Fraunhofer IPA in Stuttgart and its activities in Robotics and Automation. Focus - open source robotics software development, ROS-Industrial Consortium in Europe and EU funded project ROSIN that aims to make ROS better and business-friendly.

 

Speaker Biography

Harshavardhan completed his Bachelors in Electronics and Telecommunication from Pune University in 2007. He was a founding member of robotics startup Robots Alive, India (now defunct) where they built a lightweight manipulator for Indian SMEs and educational sector. He completed his MSc in Mechatronics from FH Aachen, Germany in 2017.

After a short stint as a student employee, he has been working as a Research Associate at Fraunhofer IPA as ROS developer and ROS trainer.

 

 

 

 

Intelligent Assets - Incorporating IOT, AI and Robotics to Improve Business Value

by Mr Shawn Fernando
Head of Robotics,
Woodside Energy

< Back

 

Abstract

Woodside is applying technologies to provide better than human awareness, enabling our people to work more efficiently while reducing exposure to health and safety risks in the oil and gas environment.

Woodside is currently deploying wireless Industrial Internet of Things (IIOT) and robotic technologies that stream data relating to condition monitoring and operator surveillance directly from our facilities to our analytics platform. Our growing data science team then works to transform the raw data into insights for action. Along with our research collaborators (e.g. NASA, University of Texas, CSIRO and Boeing), Woodside is pioneering autonomous and teleoperated robotic manipulation of equipment.

Woodside looks forward to sharing our learnings, experiences, successes and challenges in deploying advanced technologies such as IIOT, Robotics and Data Science.

 

Speaker Biography

Shawn is the Head of Robotics for Woodside Energy, responsible for leading robotic development and deployment of solutions on site.

Shawn has over 15 years of industry experience.

Starting his career in the military, he moved into the aerospace industry as a mechanical engineer specialising in R&D projects. Subsequently, he joined the resource sector and progressed to becoming an asset integrity specialist and operations manager for a highly-respected consultancy.

Since 2010, Shawn has held roles within Woodside as a Facility Engineer, Engineering Team Leader, Operations Manager and Offshore Installation Manager. He now leads the robotics team within the Technology function of Woodside.

Shawn has BSc with Honours, majoring in Pure and Applied Mathematics, a BE with Honours majoring in Mechanical Engineering and an MBA with Distinction from the University of Western Australia. Shawn is also Chartered Professional Engineer and serves on the panel for the Institute of Engineers Australia.

 

 

 

 

Exciting New Features in Gazebo

by Dr Michael Grey
Software Engineer
Open Robotics
 
< Back

 

Abstract

As the robotics industry rapidly expands into new domains, there is more need than ever for reliable, flexible simulation frameworks. Tools for simulating robotics systems are critical for economically researching new applications and ensuring safe, reliable deployment pipelines for existing applications. We will discuss recent and upcoming developments in the open source Gazebo simulator, with a focus on how simulation can be an invaluable cornerstone of any robot-driven business model.

 

Speaker Biography

Grey joined Open Robotics two years ago after finishing his Ph.D. in robotics at Georgia Tech. Last year he moved to Singapore to help support the Robotics Middleware Framework project, which aims to improve automation and cut healthcare costs in Singapore's hospitals. His focus has been on constructing large-scale simulations of complex hospital environments.

 

 

 

 

H-ROS, a Communication Bus for Robots that Provides Real-time, Determinism, Synchronization, Security and Safety

by Mr Alejandro Hernández
Chief Technology Officer
Acutronic Robotics
 
< Back

 

Abstract

We present the Hardware Robot Operating System (H-ROS) robot bus, a joint hardware and software infrastructure powered by ROS 2, which allows to create modular robots out of different robot components, regardless of their manufacturer. Every H-ROS component can be dynamically modified and extend the internal representation model of the robot, enabling robots to switch components on or off selectively and to exchange hardware between them, reducing the integration and interoperability effort when building robots

 

Speaker Biography

Roboticist. 7+ years of experience in robotics leading 20+ robotics engineers. ROS expert. Led the creation of 10+ different robotic platforms.

 

 

 

 

MARA, a Fully Modular Articulated Robotic Arm, the First ROS 2.0 Based Industrial Robot

by Dr Risto Kojcev
Head of Artificial Intelligence
Acutronic Robotics

< Back

 

Abstract
We present a modular and collaborative articulated robot arm running ROS 2 in each component. A fully distributed hardware and software architecture that empowers new possibilities such as deterministic communications, hardware introspection, hardware component lifecycle or simplified maintenance prediction. We demonstrate this vision through a fully modular collaborative robotic arm, a real product development with ROS 2 at its core.

 

Speaker Biography

Leads a team contributing heavily to the use of AI in robotics. Behind some of the most popular reproducible tools and studies made in the field. Mixing modularity and Machine Learning to simplify the field.

 

 

 

 

Bringing the Power of Intelligent Edge and Intelligent Cloud to ROS

by Mr Tony Lin
Senior Software Engineer
Microsoft

< Back

 

Abstract

Windows has been a trusted partner of robotic and industrial systems for decades. With ROS for Windows, developers will be able to use the familiar Visual Studio toolset along with rich AI and cloud features. We’ll share the latest update of bringing the intelligent edge and intelligent cloud to robotics by bringing advanced features like hardware-accelerated Windows Machine Learning, computer vision, Azure Cognitive Services, Azure IoT cloud services, and other Microsoft technologies to robots.

 

Speaker Biography

Tony Lin is a senior software engineer in Cloud & AI Group, Microsoft. Tony works with ecosystem partners to accelerate digital transformation through IoT and AI technologies, and enrich end-to-end solutions on intelligent edge and intelligent cloud platforms. Tony’s research interest is machine learning and has more than 10 publications in journals and conferences.

 

 

 

 

Intelligence, Performance, Improvements – Robot Software Kit for ROS 2.0

by Ms Sharron Liu
Senior Software Engineer
Intel Corporation

< Back

 

Abstract

On April 24th this year we announced, for the first time, our Robot Software Kit for ROS2, making it even easier to make a robot with our software kit… so you can INNOVATE! It comes with the Intel® technologies: OpenVINO™, Movidius™, Realsense™, and performance that we enabled for robot vision, as well as navigation2 with architecture improvements.

The Navigation2 stack introduces behavior tree for extensible capabilities on new tasks plug-in. The modular design makes it flexible to switch among various planners. You’ll also be shared on the current status and feature planning.

The Vision stack provides ROS2 interfaces for real-time object analytics, people detection, vehicle detection, object segmentation, and person re-identification, optimized with OpenVINO™ and time performance.The coming release will include intelligent manipulation.

The Manipulation stack enables OpenVINO™ for the CNN based grasp pose detection (GPD) and makes it ROS2 OpenVINO™ Grasp Library as a MoveIt plug-in. This work deployed the inference across various Intel vision devices including CPU, GPU and VPU.

OpenVINO™: Intel® Open Visual Inference & Neural network Optimization toolkit (https://software.intel.com/en-us/openvino-toolkit)

Movidius™: Intel® Movidius™ Myriad™ X Vision Processing Unit (VPU) (https://software.intel.com/en-us/neural-compute-stick)

Realsense™: Intel® Realsense™ technology (https://software.intel.com/en-us/realsense)

 

Speaker Biography

Sharron is a Senior Software Engineer in Intel Corporation working on robotics software. She has been working in embedded software development, IoT RTOS, intelligent vision, and robotics the past 17 years.

She enabled grasp detection with Intel® OpenVINO™ technology and made it a MoveIt grasp planning plug-in for industrial robots. She delivered the industrial robot platform solution demonstrating the capability for intelligent visual grasping.

She made the initial release of ROS 2.0 Realsense™, which makes Realsense™ the first device to support RGB-D point clouds in ROS 2.0.

Sharron graduated from Fudan University in PRC. She holds a Master’s Degree in Electronics Engineering and a Bachelor’s Degree in Computer Science.

 

 

 

 

The Rise of ROS Powered Self-reconfigurable Maintenance Robots

by Dr Mohan Rajesh Elara
Assistant Professor,
Singapore University of Technology and Design
Co-founder,
Lionsbot

< Back

 

Abstract
Self-reconfigurable robots are intelligent machines capable of autonomously changing their kinematic morphologies to overcome complexities in the traversing environment or task being handled. Their promise of high degree of versatility, robustness and modularity is set to open up a wide range of new applications for robots. However, developing these robots are highly challenging. While some progress has been achieved, there are still many open issues. In this talk, I will share our ongoing efforts at Singapore University of Technology and Design towards development of ROS powered self-reconfigurable robots using well defined set of deployment use cases in maintenance domain. I will present details of our new class of ROS powered self-reconfigurable robots that are able to significantly improve the performance of existing solutions.

 

Speaker Biography

Dr. Mohan is currently an Assistant Professor with the Engineering Product Development Pillar at Singapore University of Technology and Design (SUTD). He received his Ph.D. and M.Sc degrees from the Nanyang Technological University in 2012 and 2005. He obtained his B.E degree from the Amrita Institute of Technology and Sciences, Bharathiar University, India. His research interests are in robotics with an emphasis on self-reconfigurable platforms as well as research problems related to robot ergonomics and autonomous systems. He has published more than 80 papers in leading journals, books, and conferences. He is the recipient of SG Mark Design Award in 2016, 2017 and 2018, ASEE Best of Design in Engineering Award in 2012, Tan Kah Kee Young Inventors’ Award in 2010 and A’ Design award in 2018. He is the co-founder of Lionsbot, a robotics company that develops and deploys a wide range of autonomous cleaning robots. He is also a visiting faculty member of the International Design Institute at Zhejiang University, China.

 

 

 

 

Implementation Verification of Picking System for Industrial Robot using ROS and MATLAB

by Mr Masaru Ken Morita
Engineer
Yaskawa Electric Corporation

< Back

 

Abstract

One of MATLAB®'s product family, Robotics System ToolboxTM, contains a variety of algorithms and functions that are essential to robot development. In particular, orchestratability between the Robot Operating System (ROS) and the toolbox is extremely attractive. The toolbox will easily enable and accelerate combination evaluation of robotics system with high quality MATLAB technologies that can not be covered only by ROS.

I performed verification of the tool box by introducing a picking system for plant robots that combines YASKAWA's MotoMINI model provided as an OSS by the ROS-Industrial Consortium and advanced functions such as image recognition with deep learning, inverse kinematics, trajectory planning, and speech recognition provided by MATLAB.

In this presentation, I will present about its usability and convenience with evaluation results obtained from the system integration verification above, at the point of view of the author of ROS text book.

 

Speaker Biography

2012 - Recieved his Master’s degree in Information Sciences from Tohoku University, Japan

2012 - Current Engineer, System Engineering Division, Yaskawa Electric Corporation, Japan

2015 - Current Ph.D. Student, Department of Mechanical and Control Engineering, Kyusyu Institute of Technology, Japan

Now - An author of book “ROS Robot Programming for practical robotics development” (in Japanese). Committer of smart industrial robotics system with ROS and MATLAB. The first developer of “Ackermann Steering Controller” which is one of official “ros_controllers”. 

 

 

 

 

Robot-Ops and Intervention: Enabling Faster and Efficient Robots’ Deployment

by Mr Alok Pathak
Chief Technology Officer and Co-founder
Cognicept Systems

< Back

 

Abstract

Robots are great! As they continue to be part of our daily lives, they pose certain critical challenges - to the robot manufacturers and the end customers. A standard approach to a robot deployment is a long-integration cycle, with a deployment team monitoring the robot for a few days to a few months, making it a resource-consuming process. While a company grows from a small scale to a mid-scale, they eventually try out multiple methods of error handling, with minimum parallels when the robots’ suddenly have customers’ in a different industry. Robot KPIs and Robot intervention, have different audiences, and hence need a level of abstraction of information, and creation of new processes and dashboards. As robots continue to be deployed, post-sales management of robots’ errors, updates, installation of new safety features, etc are fields that are less explored and hence, immature. 

 

The idea of a specific/generic robot, deployed in multiple industries, with minimum downtime, seamless integration with existing processes and human workforce, and maximum efficiency in terms of performance, is well received by the industry users and robot manufacturers alike. Robot-Ops and Intervention tools are the proposed critical tools that will help us achieve this idea.

 

The speech will be a commentary on the problems mentioned above and approaches that various entities, including Cognicept and ROS-Industrial APAC, are taking to tackle them. 

 

Speaker Biography

Alok Pathak is a Co-founder and CTO at Cognicept Systems, a technology company that provides tools and services to minimize robot downtime, and to facilitate faster integration and deployment of robots in multiple industries. 

After receiving his masters in electrical engineering in 2012, from National University of Singapore, Alok built the full software stack for the eventual NUS Spin-off Attonics Systems' IR and Visible Spectrometers, from 2012-2018. His key research interests include communication protocols and processes, human-robot interaction, and signal/image processing. 

www.linkedin.com/in/alokpathak9871

 

 

 

 

Exciting New Features in ROS 2.0

by Dr Morgan Quigley
Chief Architect and Founder,
Open Robotics

< Back

 

Abstract

The Robot Operation System (ROS) version 2 promises to build upon the concepts implemented over the past decade in the original ROS framework, now known as ROS 1. This talk will provide an overview of new features and architectural designs made possible by ROS 2, emphasizing those recently added over the past year into the ROS 2 framework, which is now in its third and fourth major releases (ROS 2 Crystal and ROS 2 Dashing, respectively).

 

Speaker Biography

Morgan Quigley received a PhD in Computer Science from Stanford University in 2012, after which he joined Open Robotics as its Chief Architect. His research interests include collaborative open source software development, scalable distributed embedded systems, and hardware/software co-design.

 

 

 

 

Open Source Robotics Projects: Current Development, Technology Trends and Best Practices

by Mr Lian Jye Su
Principal Analyst
ABI Research

< Back

 

Abstract

In recent years, open-source has been critical in driving the growth of the software industry, particularly in the area of cloud computing and artificial intelligence. The presentation looks at the current developments and trends in open-source projects in the robotics industry. As the industry is seeing an increasing number of robots deployed using open source software in commercial and industrial settings, the presentation also looks at best practices and recommendations for robotics developers and end users on open-source robotics projects.

 

Speaker Biography

Lian Jye Su, Principal Analyst at ABI Research, is responsible for orchestrating research relating to robotics, artificial intelligence, and machine learning. He leads research in emerging and key trends in these industries, deep-diving into advancements in key components, regional dynamics in robotics and AI adoptions, and their future impacts and implications.

Prior to joining ABI Research, Lian Jye worked in several healthcare organizations, in both the technical and business domain. He held various roles in quality management, operation reviews, and market research analysis.

Lian Jye earned a B.Sc. in Life Sciences from the National University of Singapore. He then completed his Master in Business Administration at Melbourne Business School in Australia, with a dedicated specialization in market research and business strategy.

 

 

 

 

Updates from ROS-Industrial Asia Pacific Consortium

by Mr Erik Unemyr
Consortium Manager
ROS-Industrial Consortium Asia Pacific

Senior Programme Manager
Advanced Remanufacturing and Technology Centre
 
< Back

 

Abstract

An overview of the past year related to the ROS-Industrial Consortium Asia Pacific including recent activities in areas of training, membership and industry engagement. It will also cover on-going activities and key focus areas going forward to increase industry adoption of ROS in the region.

 

Speaker Biography

Mr. Unemyr manages the ROS-Industrial Consortium Asia Pacific, where he aims to proliferate ROS adoption and advanced robotic applications to be successfully deployed in industry and commercial applications.

He received his Master of Science degree from Chalmers University of Technology, Sweden. Prior to ROS-Industrial, he spent majority of his career in industrial MNCs delivering software and hardware products all the way from concept to mass-production.

Erik holds 7 patents within the fields of printing applications and image processing.