• Talks slides and video archives have been posted below in the program

Attempting to load ROSCon Archive Listings.

ROSCon will happen October 31st - November 1st, 2019 (Workshops on October 30th) in Macau

ROSCon 2019

ROSCon 2019

ROSCon 2019 is a chance for ROS developers of all levels, beginner to expert, to spend an extraordinary two days learning from and networking with the ROS community. Get tips and tricks from experts and meet and share ideas with fellow developers.

ROSCon is a developers conference, in the model of PyCon and BoostCon. Following the success of the past six annual ROSCons, this year’s ROSCon will be held in Macau. Similar to previous years, the two-day program will comprise technical talks and tutorials that will introduce you to new tools and libraries, as well as teach you more about the ones you already know. The bulk of the program will be 10-30 minute presentations (some may be longer or shorter).

We aim for ROSCon to represent the entire ROS community, which is global and diverse. Whoever you are, whatever you do, and wherever you do it, if you’re interested in ROS, then we want you to join us at ROSCon. We encourage women, members of minority groups, and members of other under-represented groups to attend ROSCon. We expect all attendees to follow our code of conduct.

The ROSCon planning committee acknowledges that the barriers to attendance for traditionally under-represented groups may be many and varied, and we are striving throughout the planning process to make the event as inclusive and accessible as possible. This year we are proud to continue the ROSCon Diversity Scholarship to help make ROSCon 2019 more representative of the global ROS community.

We also welcome suggestions for what else we can do to encourage more participation. Contact us if you have ideas that you’d like to share.

If you don’t want to make a formal presentation, you should still bring your new project or idea to ROSCon and present it in a lightning talk.

There will be an opportunity to give a lightning talk at ROSCon. These are 2-3 minute talks, one session each day (3 minutes in the past but this may be reducing to 2.5 or 2 minutes this year). We expect to have many more people who want to present than slots are available. For fair access there will be a lottery for requesting to give a lightning talk. A summary of the process is in the Call for Proposals Talks from 2016 can be seen in this blog post or browse the recordings from past years.

There will also be open space for impromptu hacking sessions and informal presentations.

If you are looking for information on past ROSCons, including past programs, slides and videos of the presentations, see their separate websites.

IROS 2019

ROSCon will be held the week prior IROS 2019 which will be held at the Venetian Macao. Come for ROSCon, enjoy your weekend exploring this interesting city, and stay for IROS to optimize your 2019 robotics events experience!


Important dates to keep in mind for ROSCon 2019.

Call for Proposals circulated

April 22nd, 2019

Workshop submission deadline

May 22nd, 2019

Diversity Scholarship application deadline

June 2nd, 2019

Proposal submission deadline

July 15th, 2019

Proposal acceptance notification

July 29th, 2019

Early registration deadline

August 24th, 2019

Late registration starts

October 1st, 2019

ROSCon 2019 in Macau.

October 31st - November 1st, 2019 (Workshops on October 30th)


Find our sponsors in the exhibit area. See this layout to find specific exhibitors.

Platinum Sponsor

Gold Sponsors

Silver Sponsors

Bronze Sponsors

Friends of the Conference

Diversity Scholarship Sponsors

The following sponsors are supporting the ROSCon Diversity Program, which is designed to enable participation in ROSCon by those typically underrepresented in the robotics community to make the conference a more fulfilling experience for all attendees. To get a sense of the impact of prior years’ programs, which funded travel and lodging costs for dozens of scholars from around the world, we encourage you to watch this 2016 lightning talk from Ahmed Abdalla and Husam Salih, two students at the University of Khartoum in Sudan who talked about starting a robotics lab under extremely challenging conditions.

Video Archive Sponsor

The video archive sponsorship supports the recording of the talks as well as the publication of the video archives online for the greater community.

If you are interested in finding out more about sponsoring ROSCon please contact the organizing committee. Or view our sponsor prospectus.



Conrad Macao, Cotai Central

The event will be held at the Conrad Macao, Cotai Central.


Registration for ROSCon 2019 is now open.

Register Now

Note that the early registration deadline is August 24th, 2019 or until supplies run out. For information registering please visit the registration page


The Parisian

The Parisian is the official hotel of ROSCon 2019 held in Macau October 31 – November 1, 2019. Your reservation at the Parisian supports the conference as the group block provides incentives and reductions in rental fees that enable us to provide you with the quality that ROSCon is known for while maintaining affordable registration rates.

The Parisian is the premier 5-star destination resort located in the center of the Cotai Strip Area. A 5 minute drive away from Macao International Airport and Taipa Ferry Terminal and a 20 minutes drive away from Macao Ferry Terminal and Macao city center. During your stay, you may enjoy the charming sight of the Eiffel Tower or enjoy one of the many restaurants in the hotel which serve international cuisine with exquisite dishes.


Rooms at the discounted group rate were available until October 7, 2019.

If you’d still like to stay at The Parisian at the prevailing rates, please make your reservation via phone at 853 2882 8852 or visit


Here’s a map with the location of the Hotel and the Venue indicated. There is a short walk between them.

Getting There

The nearest airport is Macau International Airport (IATA: MFM, ICAO: VMMC).

The Parisian, the official ROSCon hotel, provides a complimentary 5-minute shuttle to the venue. The shuttle runs from 10:00 - 22:30 every 15 - 20 minutes. View the shuttle schedule

View the Parisian website for additional transportation options or the Government of Macau’s website for helpful travel information.

Via Hong Kong

Macau International Airport (MFM) is a regional airport that primarily serves destinations in east and southeast Asia. If you are traveling from elsewhere, you may have more choices if you fly into Hong Kong International Airport (HKG). From HKG, you have several options to get to the Parisian in Macau, including those listed below.

Note: If you choose to travel via Hong Kong, you may need to apply for a visa for Hong Kong in addition to a visa for Macau. Be sure to check the visa requirements for entering Hong Kong.

  • Via the Hong Kong-Zhuhai-Macau Bridge (HZMB):
    • Shuttle bus (24 hours/day): Clear Hong Kong immigration; go outside to the bus area; catch bus B4 to HZMB Hong Kong Port (10 minutes; HKD$6; pay in cash with exact change or use an Octopus card); clear Hong Kong emigration; buy a ticket and then board the bus to Macau (40 minutes; HKD$65-70; credit cards accepted at the ticket counter); clear Macau immigration at the HZMB Macau Port; get to the Parisian via taxi (20 minutes; MOP$110), local bus, or hotel shuttle.
    • Cross-boundary coach (hours vary): Multiple companies operate private coach service from HKG to Macau. Clear Hong Kong immigration; follow signs for “Mainland/Macao Transport” to find the ticket counters.
  • Via ferry:
    • Directly from HKG via SkyPier (very limited schedule): Do not clear immigration but instead follow signs for “Mainland/Macao Ferries” to Transfer Area E2; follow the procedure to arrange for your checked baggage to follow you. Cotai Water Jet will take you from SkyPier to the Macau Taipa Ferry Terminal (65 minutes; HKD$270), from where you can get to the Parisian via free hotel shuttle or a short taxi ride. TurboJET will take you from SkyPier to the Macau Outer Harbour Ferry Terminal (70 minutes; HKD$270), from where you can get to the Parisian via taxi (20 minutes; MOP$110), local bus, or hotel shuttle.
    • From central Hong Kong (7am-midnight): If you are already in Hong Kong, then you can catch a ferry from the Hong Kong Macau Ferry Terminal. Cotai Water Jet will take you to the Macau Taipa Ferry Terminal and TurboJET will take you to the Macau Outer Harbour Ferry Terminal. This option does not make sense if you are going directly from HKG to Macau, as you would first need to catch a train from the airport to central Hong Kong (~1 hour).

Childcare Options

Guests of the Parisian are able to source child care through the hotel. If you require childcare, please complete the form and submit the completed form to the priority service desk in the Parisian Macao hotel lobby when you arrive at the hotel.

Childcare services require a 4 hour advance notice to reserve. To confirm a reservation, call the hotel’s front desk 853-2882-8852 in advance of your arrival onsite or call hotel’s Priority Service Center from your room phone.

ROSCon 2019 and the Open Source Robotics Foundation do not guarantee or make warranties for the provider and assume no liability by providing this reference.

Explore Macau

Macau has a rich and vibrant history, originally settled during the Han dynasty and developed by the Portuguese starting in the 16th century. In 1999, Macau became a Special Administrative Region of the People’s Republic of China. Take a few minutes and read a brief history of this fascinating location.

Come early or stay late for sightseeing, world class dining, and shopping.


Please check the weather and be prepared before you depart.

For historical data you can see here.

The current weather is here.


The official currency of Macau is the Macanese pataca (MOP). The Hong Kong dollar (HKD) is also widely accepted at 1:1.

Visa Requirements

There are currently 76 countries exempt from visa or entry permits.

Attendees from Bangladesh, Nepal, Nigeria, Pakistan, Sri Lanka, and Vietnam must apply for a pre-arrival visa and entry permit.

For attendees from countries not included on the list of exempted countries or the countries requiring pre-approval, you may purchase an entry permit upon arrival.

It is the attendees responsibility to confirm the visa requirements from their country of origin.


Keynote Speakers

Selina Seah

Selina Seah, Changi General Hospital

Appointed as Assistant Chief Executive Officer CGH on 1 Sep 2012 focusing on campus development and care transformation, Ms Seah has oversight over expansion and remodelling of the campus, looking at new models of care and developing enablers in infrastructure, technology and innovations. In 2015, she was also appointed Director of the Centre for Healthcare Assistive & Robotics Technology (CHART), a partner of the National Robotics Program, to build a collaborative platform that will enable healthcare professionals to work closely with academia, industry and research institutions to develop impactful healthcare solutions leveraging on robotics and assistive technology. In 2016, she also took on the role of Director, Smart Systems Program Office for the Ministry of Health, to lead in the adoption of Smart Systems, and build innovation incubation capabilities to bring successful ideas to mainstream.
Morgan Quigley

Morgan Quigley, Open Robotics

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.
Ian Sherman

Ian Sherman, Formant

Ian Sherman is Head of Software at Formant, a company building cloud infrastructure for robotics. Prior to Formant, Ian led engineering teams at Google X and Bot & Dolly. The through line of his career has been tool building, for engineers and artists alike. He's inspired by interdisciplinary collaboration of all types; currently this takes the form of applying patterns and practices from distributed systems operations to emerging applications in robotics. Ian earned his BA in Computer Science from Brown University.

Day 0, October 30th

Pre-conference Workshops

(jump to Day 1) (jump to Day 2)


Workshop Registration

Preregistration required. Please arrive early to allow time to collect your badge and conference bag before the workshops start. We expect there to be a queue for registration.


Is your robot secure? ROS 1 & ROS 2 Security Workshop

14:00 - 17:00
Thomas Moulard (Amazon), Víctor Mayoral Vilches (Alias Robotics) Website With the advent of IoT, more and more robots and devices are accessible from the internet. Those rarely updated, vulnerable systems, can become an easy target for hackers. In this workshop, you will learn how to detect and mitigate security issues in your ROS 1 or ROS 2 applications using tools and framework developed by the Alias Robotics and AWS RoboMaker teams.

How to use OpenAI baselines to train ROS robots

14:00 - 17:00
Ricardo Tellez (The Construct) Website Learn how to use reinforcement learning (RL) to train your ROS robot for tasks using the OpenAI baselines. You will learn how to build a Gazebo simulation for training, how to specify a task as an RL problem, how to connect training to the simulation, and how to use the OpenAI baselines to actually train. This is a hands on workshop. Bring your laptop. No need to install anything.

Doing real-time with ROS 2: Capabilities and challenges

14:00 - 17:00
Dejan Pangercic (Apex.AI), Ingo Lütkebohle (Bosch), Víctor Mayoral Vilches (Alias Robotics), David Crawley (Ubiquity Robotics), Geoff Biggs (Tier IV) Website Deterministic behaviour is crucial for many aspects of successful robot systems; from industrial welding robots following an exact path, to safety-critical robots doing drone package delivery, autonomous driving or warehouse conveyance. In this workshop participants will be introduced to the on-going work to use ROS 2 as a foundation for soft, firm and hard real-time robot systems. You will learn what the current capabilities are of ROS 2 for real-time robotics, what still remains to be done, and how you can contribute to the system.

The Future of the ROS Infrastructure Ecosystem

14:00 - 17:00
Bill Smart (Oregon State University) Website The community infrastructure on which ROS depends, like the wiki, Answers, and our community standards, are starting to show their age. This workshop is your chance to help improve this infrastructure, and help ensure that ROS continues to thrive. We'll describe the results of our NSF-funded work to identify pain points and hear ideas that have worked in other open-source communities. We will work as a group to come up with good solutions to these problems, and begin a proposal to implement them.


Day 1, October 31st

(jump to Day 0) (jump to Day 2)



Please arrive with enough time to register before the opening remarks.


Opening Remarks

Brian Gerkey

Video Slides


Keynote: Robotics Middleware Framework for Hospitals - redefining the approach

Selina Seah (Changi General Hospital), Morgan Quigley (Open Robotics)

Video This presentation will share how the Singapore Public Healthcare domain’s roadmap to adopting robotics and smart systems; and the need for interoperability of complex and disparate technological systems with HIT and infrastructure. The Centre for Healthcare Assistive & Robotics Technology (CHART), appointed by Ministry of Health, works with various government agencies and industry partners to use ROS 2 as part of the Robotics Middleware Framework and Gazebo as part of the QA cycle before deployment. The developed framework is not only for ROS devices; it is able to support near real time communications between ROS and non-ROS devices; and models to harmonise the navigation of heterogeneous robotic fleets to optimize utilization of common infrastructure resources, meeting healthcare needs.


ROS F1/10 Autonomous Racecar Simulator

Varundev Suresh Babu, Madhur Behl (University of Virginia)

Video Slides F1/10 is a ROS based 1/10 scale autonomous racing testbed designed to test racing algorithms. The ROS F1/10 Autonomous Racecar Simulator is a Gazebo based virtual racing environment which includes a realistic model of the F1/10 autonomous racecar and associated race controllers. The F1/10 simulator provides users with the opportunity to optimize autonomous racing algorithms and a framework for designing and visualizing head-to-head racing with multiple simulated racecars.


Migrating a large ROS 1 codebase to ROS 2

Geoffrey Biggs (Tier IV/The Autoware Foundation) Esteve Fernandez (Apex.AI/The Autoware Foundation)

Video Slides With ROS 1 having its last Open Robotics-supported release in May 2020 and ROS 2 becoming increasingly mature, migrating to ROS 2 is becoming a necessity for every ROS-based project. In this talk we present the case of Autoware, an autonomous driving stack that originally started as a ROS 1 R&D project and is being migrated to ROS 2 and re-targeted at production. We describe the approach we are implementing to migrate to ROS 2 and improve quality, while also ensuring the software remains usable and the community remains engaged throughout the process.


Coffee Break


Webviz: a complete ROS visualization suite in the browser

Jacob Bandes-Storch, JP Posma (Cruise Automation) Video Slides The ROS ecosystem of visualization and dev tools (Rviz, RQt, etc..) is powerful but challenging to scale across large teams. That's why Cruise developed and open-sourced Webviz, a browser-based alternative that consolidates all their functionality in an easy to deploy, customize, and extend web application. This talk will introduce the tool and show how it improves the debugging and development workflow compared to the existing suite (both desktop and browser-based). We’ll also walk through implementing custom components for data loading (e.g. CSV dumps from a remote server) and visualization (3D paths) to demonstrate how the architecture is easy to extend.


How to Achieve Realistic Visuals in Ignition Gazebo

Cole Biesemeyer (Open Robotics) Video Slides This talk will cover the creation of realistic environments for Ignition Gazebo, the next generation of Gazebo. We’ll present the new physically based rendering system implemented in Ignition Gazebo, and discuss the tools and processes we use to make our 3D content pipeline more efficient. We’ll also explore how to look outside the robotics industry for help in making your virtual worlds as realistic as possible.


Panel: ROS at Scale

Moderator: Roger Barga (Amazon); Panelists: Tomoya Fujita (Sony Corporation), Shinpei Kato (Tier IV), Melonee Wise (Fetch Robotics) Video The panel will share their experiences using ROS at scale with large systems of robots in production settings. They will discuss and take questions on the advantages, challenges, and trade-offs of using ROS as part of a system with SLAs for uptime and reliability.




The New Architecture of Gazebo Wrappers for ROS 2

13:40 - 14:00 Track: Simulation Louise Poubel, Jose Luis Rivero (Open Robotics) Video Slides Gazebo is one of the most popular simulators in the ROS ecosystem, and now it's fully integrated with ROS 2! This talk will cover improvements in the major rewrite of gazebo_ros_pkgs, including what's new in the Gazebo/ROS 2 wrappers: plugin loading/unloading at runtime, better flexibility to combine features, standardization of common functionality, and much more. Both new and long-time developers and users of the Gazebo/ROS wrappers will learn how to get started through a live demo and several online resources meant to ease the transition.

Migrating to ROS 2: Advice from Rover Robotics

13:40 - 14:00 Track: Applications Nick Fragale, Nick Padilla (Rover Robotics) Video Slides Rover Robotics has been working hard to bring its ground robot hardware to ROS 2 Dashing with lots of engineering assistance from Intel, ADLINK Technology, Open Robotics, and AWS RoboMaker. We have catalogued the journey on our blog and in video form but what we have learned could fill several books so come learn about the nitty gritty details.


Using ROS and Gazebo to Safely Validate and Verify Autonomous Systems

14:00 - 14:20 Track: Simulation Joshua P. Hecker (Lockheed Martin) Video Slides The validation and verification of autonomous systems is both a significant hurdle and a necessary imperative for the robotics community. While pure simulation frameworks such as Gazebo or Webots may provide useful benchmarks for evaluating the performance of these systems, the ever-present reality gap inevitably casts doubt on the credibility of such benchmarks. This tutorial presents a hybrid implementation that uses existing ROS and Gazebo tools to blend physical and virtual assets into a unified, constructed environment. This new approach supports the evaluation of autonomous robotic systems in challenging real-world scenarios while minimizing the risk of damage to the system.

A ROS based architecture for an autonomous chemistry laboratory

14:00 - 14:10 Track: Applications David Marquez-Gamez, Phillip Maffettone (University of Liverpool) Video Slides In this talk we will present the use of ROS in scientific laboratories. We will focus on the integration and development of hardware and software architecture for chemist robots (robots that research chemistry). We consider the use of heterogeneous hardware platforms: robotics arms, mobile manipulators and standard laboratory equipment (e.g. solid dispensing, liquid dispensing). By defining a ROS based software architecture, we construct a seamless exploitation of these diverse platforms under “real-time”, safety and reliability requirements.


Wheeled Humanoid Hubo API

14:10 - 14:20 Track: Applications Moonyoung Lee, Yujin Heo, Saihim Cho (KAIST Institute - Hubo Lab) Video Slides The adoption of DRC competition winning humanoid platform, DRC-Hubo, is steadily expanding, with over 30 similar platforms used in various research institutes globally. While the custom RT software framework for Hubo, PODO, provides easy interface for motion generation, it lacks access for handling vision-related data. This has significantly hindered prior collaboration efforts on vision-based motion generation such as terrain navigation or manipulator collision detection. We discuss the overall development and challenges faced creating Hubo API that adopts standard ROS interfaces, facilitating motion generation of the robot over ROS.


Code Manipulation through Interactive Markers in a Live Preview

14:20 - 14:40 Track: Simulation Thomas Witte, Matthias Tichy (Ulm University) Video Slides We present a hybrid editor for quadcopter missions. A lua-based DSL is used to prototype simple quadcopter applications using an imperative API. To facilitate programming, a live preview of the flight is shown in rviz and can be manipulated through interactive markers; any changes are mirrored to the textual source. This WYSIWYG-style editing is non-trivial, if the underlying representation is not declarative or immutable at runtime. We work around this by tracking source locations through the execution of the imperative program, reversing the calculation of values and modifying literals, such that the program produces the desired preview.

Industrial Manufacturing Automation Leveraging ROS

14:20 - 14:50 Track: Applications Levi Armstrong, Chris Lewis (Southwest Research Institute) Video Slides Aerospace, Excavator Machinery manufactures and other industries require large automated manufacturing systems for painting, surface-finishing, inspection, and more. These systems often employ a gantry outfitted with an industrial manipulator to extend the work envelope over many meters. Due to their sheer size and associated costs, these systems must perform multiple operation to ensure adequate return on investment. Automating these large, multi-use-systems has challenges including motion planning for redundant kinematics, calibration of 3D scanning sensors, environment management, user-interface and collision monitoring. Southwest Research Institute will share its experiences applying ROS to implement several complex automation systems for large scale manufacturing processes.


Pose Frame Specification for SDFormat 1.7

14:40 - 14:50 Track: Simulation Eric Cousineau (TRI), Addisu Taddese (Open Robotics) Video Slides The Pose Frame Specification is an extension of SDFormat that enables defining arbitrary coordinate frames and allows poses of various elements to be expressed relative to these frames. The resulting frame semantics provide powerful expressiveness for constructing models using relative coordinate frames. This reduces duplication of pose information and eliminates the need to use forward kinematics to compute the assembled poses of links. One outcome of this extension is that robot modeling can be done in SDFormat in a similar manner as URDF, significantly reducing the effort needed to transition between the two formats.


pcg_gazebo_pkgs: A Python library for scripting and rapid-prototyping of simulated Gazebo models and worlds

14:50 - 15:10 Track: Simulation Musa Morena Marcusso Manhães (Bosch) Video Slides The new pcg_gazebo_pkgs1 was developed at Bosch Research to allow quick construction and control of simulated Gazebo scenarios and prototyping of robot models via the pcg_gazebo Python library. The library uses concepts of procedural generation to allow the user to have full control over the parametrization and setup of the simulation, parsing and conversion between SDF and URDF formats and algorithms of randomization of scenario layouts and Gazebo models

ROS2 on VxWorks - Challenges in porting a modern, software framework to RTOS

14:50 - 15:10 Track: Applications Andrei Kholodnyi (Wind River) Video Slides A slim ROS2 design with minimal external dependencies makes it a promising candidate for the direct deployment in the mobile robot environment. Such embedded systems are the area where VxWorks RTOS historically plays a leading role. This presentation describes the motivation and challenges of porting Robot Operating System to VxWorks, gives some recommendations to the ROS2 community and discusses possible next steps.


ROS in the Jupyter Notebook

15:10 - 15:30 Track: Simulation Wolf Vollprecht (QuantStack) Chaitanya Deep (Rapyuta Robotics) Video Interactive computing is coming to ROS: The Jupyter Notebook is well-known in data science as a means to explore datasets and create immediate, interactive visualizations. We are trying to make the new JupyterLab IDE a more productive environment for ROS developers with specialized widgets: the jupyter-ros package offers RViz-like interactive 3D robot visualizations, as well as tools to make message sending, topic subscribing and live plotting more convenient. On top of that, we will demonstrate using the JupyterLab as a Cloud Robotics IDE and the Jupyter voilá toolkit to turn notebooks into standalone web applications.

ROS on OpenEmbedded: Simpler robotics development for embedded Linux

15:10 - 15:30 Track: Applications Lokesh Kumar Goel, Herb Kuta, Brian Shin (LG Electronics America R&D Center) Video Slides Come and join us as we present how the new Tier-3 platform (OpenEmbedded with webOS) for ROS1 and ROS2 makes an easy path to deployment and productization of the next generation of low-cost robots. In this talk, we shall explain how to leverage this productized platform optimized for embedded devices, and create various robot experiences from a common codebase for different hardware architectures like Intel, ARM, and others. Leverage the benefits of cross compiling everything on host and generating reproducible robot images, enabling seamless software-updates, rich media-playback, central power-management, remote diagnostics, control through cloud, and development with frameworks like Qt/HTML/JS to develop compelling user experiences.


Coffee Break


Navigation 2 Overview

16:00 - 16:30 Track: Navigation Matthew Hansen (Intel) Video Slides An overview of Navigation2, the evolution of ROS Navigation into ROS2 will be presented. This includes some significant architectural changes and improved testing capability.

Lessons learned: a brief history of autonomous robot operations

16:00 - 16:30 Track: Deployment Florencia Grosso (Ekumen), Julian Cerruti (InOrbit) Video Slides In this talk we will share our experience from the last seven years working jointly with dozens of robotics companies to deploy and operate fleets of ROS-based autonomous robots in production. We will talk about the challenges seen, practices observed and technologies used in a variety of industries. Our focus is on the often-neglected aspects that surround robotics technology which are not core yet necessary to bring a robotics product out into the field at scale.


On Use of SLAM Toolbox

16:30 - 16:50 Track: Navigation Steve Macenski (Samsung Research America) Video Slides We introduce the SLAM Toolbox. It implements synchronous and asynchronous SLAM for massive indoor and changing environments as well as life-long mapping and localization modes. SLAM Toolbox brings several improvements over the existing solutions. This includes plugin optimizers with default Ceres, speed-ups in Karto's scan matcher, pose-graph manipulation tools, serialization, continued mapping on serialized SLAM graphs, pose-graph localization rolling window technique as a replacement for AMCL, and enables fully distributed mapping without the use of derived 2D occupancy image maps. This package was built for mapping of massive retail and warehouse applications, though likely effective out of those scopes. This talk will go over key points of SLAM Toolbox, demonstrations in production environments, and how to enable it in your application.

Tailor CI: How Locus deploys ROS robots at scale

16:30 - 16:50 Track: Deployment Paul Bovbel, Gary Servin (Locus Robotics) Video Slides When setting out to build a commercial robot around the ROS ecosystem, developers have to face the decision of running their own fork of OSRF's build infrastructure, or rolling a bespoke continuous-integration (CI) solution. In this talk, we present Tailor - an open-source version of Locus’ CI infrastructure that is free-standing, or can form the basis of a larger CI pipeline. This talk will explain our approach to converting a ROS distribution into binary packages and bare-metal/container images, as well as how to deploy images to production robots as over-the-air (OTA) updates.


D-ORCA: Distributed Aerial Swarm Collision Avoidance

16:50 - 17:10 Track: Navigation Harish Sampathkumar, Senthil Hariharan Arul, Adarsh Jagan Sathyamoorthy, Akshay Rajaraman, Dinesh Manocha (University of Maryland, College Park) Video In this work, we present D-ORCA, the first decentralized collision avoidance simulation package for quadrotor swarms. Our package is based on ORCA (Optimal Reciprocal Collision Avoidance), a local collision avoidance scheme that is scalable to a large number of swarm agents and PX4 SITL package for high fidelity quadrotor simulation in Gazebo. Users of the package can simulate a swarm of up to 50 quadrotors which can avoid collisions with each other and with static obstacles in a known environment, and easily add and test their own perception or global path planning code with the package.

Launch Testing - Launch description and integration testing for ros2

16:50 - 17:10 Track: Deployment Peter Baughman (Apex.AI), Michel Hidalgo (Ekumen), William Woodall (Open Robotics) Video Slides In ROS2, writing automated tests is easier than it was in ROS because it is no longer necessary to coordinate a ROS master with the tests, however this is still a need for robust multi-process testing as well as testing of ROS2's new launch descriptions, which can contain arbitrarily complex operations. Launch Testing aims to provide rostest-like functionality for ROS2, as well as provide new functionality to allow for more robust integration testing.


Transition Time



Group Picture




Day 2, November 1st

(jump to Day 0) (jump to Day 1)




Keynote: Beyond Autonomy: ROS in solution architecture

Ian Sherman (Formant)

Video ROS is increasingly powering businesses with paying customers, production SLAs, and scaling challenges. These impose a new set of requirements for robotics software. This presentation draws on experience at a small ROS startup, a large non-ROS robotics initiative, and now a company helping ROS customers go to market, to explore questions including: What does ROS look like as part of a larger solution architecture? What are the natural complements to the ROS software ecosystem? What technologies, patterns, and practices in disciplines adjacent to our own -- disciplines such as backend distributed systems and IoT -- can the ROS community beg, borrow, and steal?


ROS2 for consumer robotics: the iRobot use-case

Alberto Soragna, Juan Oxoby, Dhiraj Goel (iRobot) Video Slides At iRobot we are proud to offer state-of-the-art robotic systems at an accessible price. In order to do so, we constantly face several challenges in terms of constrained resources and scalability. The quickly growing popularity of ROS2 and its features make it very appealing to consumer robotics companies. This presentation will describe the journey we took to explore ROS2 and the contributions we made to improve it, reaching to the performance target required for running full navigation solutions on thousands of resource-constrained robots.


188 ROS bugs later: Where do we go from here?

Christopher Timperley (Carnegie Mellon University), Andrzej Wasowski (IT University of Copenhagen) Video Slides What kinds of bugs do programmers encounter when developing ROS applications? Are those bugs unique to ROS? What can we do to avoid them? To answer these questions, we have been conducting a joint industry-academia effort over a two-year period to systematically identify and forensically analyse 188 bugs across 9 ROS packages from diverse projects. In this talk, we share our experiences, discuss our findings, and propose a small set of simple interventions that can improve the quality of your ROS applications today.


Coffee Break


Composable Nodes in ROS 2

Michael Carroll (Open Robotics), Michel Hidalgo (Ekumen), William Woodall (Open Robotics) Video Slides Composable nodes (or simply components) allow developers to defer decisions about execution layout until deploy time. This benefit comes at no expense thanks to a unified node API, unlike ROS 1 node and nodelet APIs. Owing to this flexibility, components are now the recommended way of writing ROS 2 C++ code. This talk will cover the basic concepts and architecture, as well as demonstrate writing and deploying components via the tooling available starting in Dashing. The intended audience for this talk is ROS 2 developers interested in latest features, as well as users migrating nodelets from ROS 1.





FetchIt! The Mobile Manipulation Challenge, Results

13:40 - 14:00 Track: Manipulation Alexander Moriarty, Sarah Elliott, Niharika Arora (Fetch Robotics) Video Slides This year, Fetch Robotics hosted a competition at ICRA2019 in Montreal. The Competition focused on Mobile Manipulation using the Fetch Robotics Research Platform. We enforced the use of ROS Melodic, and Open Sourcing all the teams code. This talk aims not to sell our research platform: but to discuss future manipulation competitions and why we did yet another one, and discuss the results of this year's competition.

Concurrency in ROS 1 and 2: from AsyncSpinner to MultithreadedExecutor

13:40 - 14:00 Track: Quality and Performance Nicolo’ Valigi (Cruise Automation) Video Slides While today's robotics systems heavily rely on both concurrency and parallelism for performance, these concepts tend to be confusing and cause many bugs in production. In other words, why can’t your stack use 100% of the CPU without intolerable latency? This talk will trace an overview of the tools available to roboticists, starting from OS-level processes and threads, to the ROS 1 model of spinners and callback queues. We’ll then introduce the improvements in ROS 2, with callback groups and custom executors. Throughout the journey, we’ll discuss gotchas and strategies to help improve throughout without killing latency.


Introducing MoveIt Grasps, a manipulation framework tightly integrated with MoveIt.

14:00 - 14:10 Track: Manipulation Michael Lautman (PickNik) Video MoveIt has long been the leading open source motion planning framework, due in part to the communities' focus on improving core functionality. This has come at the cost of not expanding MoveIt's scope into peripheral manipulation subtasks such as perception and grasping. As we at PickNik have engaged with dozens of companies that use MoveIt, it has become clear that in more of the manipulation pipeline is needed to elevate the capabilities of open source robotic manipulation software. Over the last year PickNik has been collaborating with Rapyuta Robotics to improve a grasping library worthy of the name MoveIt Grasps. Officially released only a few months ago, MoveIt Grasps provides a framework for planning grasps of objects such as blocks or cylinders with multiple gripper types and can be used as a replacement for the often criticized pick-and-place MoveGroup capability. In this talk we will introduce the core components of the MoveIt Grasps framework, explore the use cases and demonstrate the rich visualization functionality provided by the MoveIt Grasps framework.

A true zero copy RMW implementation for ROS2

14:00 - 14:10 Track: Quality and Performance Karsten Knese (Bosch), Michael Pöhnl (Bosch) Video Slides Bosch is going to open source a true zero-copy middleware for inter-process communication on modern robotics and vehicle computers. The shared memory based solution is compatible with Linux/QNX and achieves data independent communication in constant time without serializing data. We would like to present our recent development toward full ROS2 compatibility by providing a working RMW implementation. This implementation enables leveraging the tools around ROS2 with the speed of zero-copy data transfer…a powerful combination. We will present some timing analysis and finally introduce a bridge to existing DDS systems when extending the scope from shared memory to inter-machine communication.


PackML2: State Machine Based System Programming, Monitoring and Control in ROS2

14:10 - 14:20 Track: Manipulation Dejanira Araiza-Illan (ROS-Industrial Consortium Asia Pacific) Video Slides We present a comparison of different state machine implementations in ROS2, used as tools to program, control and/or monitor industrial equipment such as PLCs and robots. We also present the migration of the PackML ROS-Industrial package from ROS 1 to ROS 2, reflecting on the main challenges and lessons learned. This set of packages was originally built to simulate, visualize and control state machines that follow a template dictated by the Packaging Machine Language (PackML) industry technical standard for discrete processes (ISA-TR88.00.02). An example using an industrial PLC and a robot manipulator is shown to illustrate the functionality of the PackML2 packages.

ROS2 Real-Time Behavior: Static Memory Allocation

14:10 - 14:20 Track: Quality and Performance Jaime Martin Losa, Raquel Alvarez Baños (eProsima) Video In last release of ROS2 the code has been improved to be free of dynamic allocations for static scenarios where you know in advance the memory required in terms of number of nodes and entities. In these scenarios you can set-up the memory to be allocated at start-up, avoiding any dynamic allocations at run-time, and thus improving the determinism of your application. Learn how and when to use this new feature in this presentation.


Flexible Framework for Quantitative Reachability Analysis

14:20 - 14:40 Track: Manipulation Michael Ripperger (Southwest Research Institute) Video Slides Kinematic reachability analysis plays a major role in the design of any robotic system. Conventionally we attempt to understand a robot's reach capability by creating CAD models and manually moving them around an anticipated environment. This qualitative type of analysis is subject to poor interpretation and can lead to problematic design choices. Southwest Research Institute is solving this problem through the development of a software framework for analyzing reachability on a workpiece. This approach evaluates reachability using objective metrics and provides interactive visualization to improve the quality of robot reachability assessment.

Quality of Service Policies for ROS2 Communications

14:20 - 14:40 Track: Quality and Performance Emerson Knapp, Nick Burek (Amazon) Video Slides In the ROS2 Dashing release, we introduced three new Quality of Service policies to Publishers and Subscriptions in ROS2 - Liveliness, Deadline, and Lifespan. The policies join the existing History, Reliability, and Durability settings. Using these, you gain finer-grained control of the behavior and guarantees of the topics in your robotic application. In this talk, we present the QoS policies, their API and usage, and real world examples of how they can improve confidence in your robot.


Reactive Jogger for Teleoperation and Contact Tasks

14:40 - 14:50 Track: Manipulation Andy Zelenak (University of Texas at Austin), Robert G. Reid (Woodside Energy Limited), Mitch Pryor (University of Texas at Austin) Video Slides We developed and released a computationally efficient jogger for mobile manipulation that is well-suited for real-world manipulation tasks. Its fast control rates (>500 Hz) and tolerance for message latency enables teleoperation, admittance control, and end effector pose regulation during base motion. The presentation covers implementation including singularity avoidance, signal filtering, reactive control, and velocity/position control modalities. It includes three use examples: cabinet opening, opening and passing through a sprung door, and contact force regulation. We also quickly present a real-world use case (emergency response in an operational mine). The jogger package is now available as a part of MoveIt.

micro-ROS: ROS 2 on microcontrollers

14:40 - 15:00 Track: Quality and Performance Ingo Lütkebohle (Bosch), Borja Outerelo Gamarra (eProsima), Iñigo Muguruza Goenaga (Acutronic Robotics), Jaime Martin Losa (eProsima), Víctor Mayoral Vilches (Alias Robotics) Video Slides Traditionally, ROS has stopped at the microcontroller boundary, even though robots contain many of them. Usually, they are integrated through serial protocols. This is error-prone work and worse, many existing sensors and actuators have proprietary firmware that cannot be changed, because manufacturers are concerned (not unreasonably so) that user-changes might break it. Therefore, the micro-ROS project is working on bringing full microcontroller support to the ROS 2 ecosystem, and to provide safe mechanisms for composability. In this talk, we will introduce current work, our architectural approach, the hardware we support, challenges we addressed, and challenges that remain.


cartesian_controllers: Motion, Force and Compliance Control for Robotic Manipulators

14:50 - 15:00 Track: Manipulation Stefan Scherzinger, Arne Rönnau (FZI Research Center for Information Technology) Video Slides This package provides a set of Cartesian motion- force- and compliance controllers for the ROS-control framework. The controllers are meant for joint_position and joint_velocity interfaces on the manipulators. As a unique selling point, they use fast forward dynamics simulations of virtually conditioned twins of the real setup as a solver for the inverse kinematics problem. They are designed to trade smooth and stable behavior for accuracy where appropriate, and behave physically plausible for targets outside the robots reach. The package is for users who require interfaces to direct task space control without the need for collision checking.


OpenVINO™ Acceleration for Intelligent Robot

15:00 - 15:10 Track: Manipulation Sharron LIU, Yu YAN (Intel) Video Slides Convolutional Neural Network (CNN) based Artificial Intelligent methods are widely used in intelligent robot. However, the CNN inference consumes large amount of CPU loads and introduces unacceptable latency. Existing acceleration solutions require specific knowledge on CNN frameworks, acceleration libraries, and parallel programming. We introduced OpenVINO™ for CNN inference acceleration. We proved OpenVINO™ acceleration for industrial robot firstly, by establishing a platform solution consists of the OpenVINO™ Grasp Library and the MoveIt based intelligent visual grasp application running on real robot. OpenVINO™ supports self-converted or 100+ pretrained CNN models – using common APIs for all devices.

ROS2 on Large Scale Systems: Discovery Server

15:00 - 15:10 Track: Quality and Performance Jaime Martin Losa, Raquel Alvarez Baños (eProsima) Video The Discovery Server is a new tool to deploy ROS2 in large scale systems with many nodes in which the default discovery mechanism is not practicable because long start-up times or network overhead due discovery traffic. In this presentation we will introduce this new tool and demonstrate how to set-up and deploy it easily, just adding a configuration file to your ROS2 applications.


Safety Certified ROS-native Industrial Manipulator

15:10 - 15:30 Track: Manipulation Christian Henkel (Pilz GmbH & Co. KG) Video Slides The automation company Pilz has released an industrial manipulator PRBT 6. We think that ROS is a key enabling technology for industrial robotic applications. Therefore, we develop our own industrial-level planners and high-quality drivers for our manipulator. In this talk, we want to address how our robot is certifiable under EN ISO 10218-1 to be used with ROS. This is not merely an intricacy of industrial standards; it is an inevitable step towards using ROS in industry. Most market players certify their manipulator combined with their proprietary programming and operation equipment. This makes it a legal grey area to use them with ROS. However, in our system, ROS packages are included in the certification. To our knowledge, this is the first robotics system with ROS as an integral part. which is certifiable as an industrial robotics system. We will explain the meaning for applications with the robot, and how to safely use ROS with it.

Bridging Your Transitions from ROS 1 to ROS 2

15:10 - 15:30 Track: Quality and Performance Mabel Zhang (Open Robotics) Video Slides For ROS 1 users looking to transition their projects to ROS 2, the entry point is often ros1_bridge. The bridge allows communication between ROS 1 and 2, enabling a gradual transition as packages are ported incrementally. Unfortunately, community experience showed that the procedure to set up the bridge is very specific and quickly becomes complex, even with built-in data types. Together with a few hidden caveats, these stumbling blocks can quickly demotivate the ROS 1 community from transitioning to ROS 2. This talk demonstrates steps to use the bridge successfully in different use cases. All examples will be publicly available.


Coffee Break


Black Block Recorder: Immutable Black Box Logging via rosbag2 and DLTs

16:00 - 16:20 Track: Multidisciplinary Ruffin White (University of California, San Diego), Gianluca Caiazza (Ca’ Foscari University) Video Slides Black-boxes or Event-Data-Recorders (EDRs) are crucial in robotics, providing prolonged insights into situational context or internal system-state; invaluable when analyzing R&D experiments ex post facto. Roles and requirements for EDRs in production can broaden to include evidence for legal investigations. As high profile incidents continue to guide regulatory policies, it's paramount that the integrity, authenticity and non-repudiation of logs be maintained to ensure accountability. This talk will address immutablization of rosbags at runtime via linked integrity proofs and permissioned blockchains (a DLT), with special considerations for mobile service robot deployments subject to threats beyond conventional IT.

colcon - Universal Build Tool

16:00 - 16:20 Track: Development Dirk Thomas (Open Robotics) Video Slides Since ROS 2 Bouncy, `colcon` is the build tool of choice for ROS 2. It not only supports all targeted platforms including Windows, but by now also works for ROS 1, Gazebo, Ignition, and other projects. This talk will shed some light into what `colcon` does, how it works and how you can utilize the tool to optimize your workflow.


ROSPlan: AI Planning and Robotics

16:20 - 16:40 Track: Multidisciplinary Gerard Canal, Michael Cashmore (King's College London) Daniele Magazzeni (King's College London) Video Slides AI Planning has proved very useful in robotics domains, from the control of the robot Shakey to challenging problems such as Mars exploration. However, the integration of a task planner can be tedious, with the need for crafting custom interfaces for planning and plan execution. If a different planner needs to be used or tested, the problem must be solved again. ROSPlan tackles this challenge by providing a framework to connect the standard Planning language PDDL and ROS. Its highly modular design allows for easy exchange of components and many additional features.

[Reactive] Programming with [Rx]ROS

16:20 - 16:40 Track: Development Henrik Larsen, Andrzej Wąsowski (IT University of Copenhagen) Video Slides RxROS is new C++ API for ROS based on the paradigm of reactive programming. Reactive programming is an alternative to callback-based programming, sometimes dubbed ‘concurrency-made-easy’. This micro tutorial will present the problems of asynchronous programming with callbacks and locks (the standard ROS API). We will argue for declarative program structure based on data-flow and on simple transformations of messages. We will demonstrate advantages on small code examples in a how-to style, using fragments of two simple ROS nodes for tele-operation of a mobile base. RxROS is available open source under a BSD license. The project seeks users and contributors


Universal Meaning Representation Format for Natural Language Task Engines

16:40 - 16:50 Track: Multidisciplinary Robert Valner (University of Tartu), Selma Wanna (University of Texas) Video Slides In order to rapidly deploy natural language interfaces for robotics applications, we developed the Universal Meaning Representation Format (UMRF) and TeMoto Action Engine. The proposed UMRF acts as a middle ground for combining existing and cutting edge solutions in the domains of natural language processing and grounding. The open-sourced TeMoto Action Engine offers developers an UMRF based action execution management system to use as an interface for natural language control, via grounding the UMRF data structures to executable code. We demonstrate the feasibility of the developed work by executing robotic tasks on ROS via different parsing systems, including Google Assistant.

Develop ROS applications with Visual Studio Code and Azure

16:40 - 17:00 Track: Development Sean Yen, Lily Hou (Microsoft) Video Slides Learn how to use Visual Studio Code and Azure to develop your ROS applications. You will learn how to create a ROS project and debug your ROS application in Visual Studio Code, how to deploy your ROS application in Azure services for simulation and training, and how to deploy your ROS application to a physical device running Windows 10 IoT and leverage hardware-accelerated machine learning.


It Takes a Village: Collaboration in ROS

16:50 - 17:00 Track: Multidisciplinary Sophia Kolak, Chris Timperley (Carnegie Mellon University) Video Slides ROS has grown over many years from a small network of developers into a mature, collaborative ecosystem. Collaborative development as such is often considered one of ROS's greatest strengths. And yet, prior investigations into the ecosystem suggest high rates of package abandonment and serious barriers to package reuse. To investigate these claims, we performed statistical and graph-based analysis on the ROS ecosystem, and evaluated how much collaboration is really happening in ROS. Our talk will present findings from this study, introduce our ROS-dependency graph database, and give insights on how to design more effective collaboration in ROS 2.


Experience from ROS Boston

17:00 - 17:20 Track: Multidisciplinary Chris Lalancette (Open Robotics), Ian McMahon (Toyota Research Institute) Video Slides Organizing, running ,and participating in ROS-focused events in your neighborhood is a great way to meet your local community of roboticists, makers, and companies. In this talk, we’ll describe some of the challenges and fun involved with running a community, drawing on our own experience running the ROS Boston community for the last 2 years.

Markup Extensions for ROS 2 Launch

17:00 - 17:20 Track: Development Ivan Paunovic, Michel Hidalgo (Ekumen) Video Slides ROS 2 launch was in need of a launch description standard similar to the de facto roslaunch XML format used in ROS 1. This talk will present our new .launch.xml format for ROS 2 launch, compare it to related formats, show how to use its new features, and provide different methods for how to extend it using its new API, with examples.


Transition Time


Panel: ROS in Research

Moderator: Ryan Gariepy (Clearpath); Panelists: Ingo Lütkebohle (Bosch), Bill Smart (Oregon State University), Musa Morena Marcusso Manhães (Bosch) Video The panel will share their experiences using ROS in academic and industrial research environments. They will discuss and take questions on how using ROS as a tool in support of scientific exploration has impacted research publication, validation, and funding.


Closing Remarks

Video Slides


Call For Proposals

ROSCon is expanding! In past years, members of the community could propose only talks. This year, we are extending the conference format so that you can submit:

  • Talks - As in previous years, the standard presentation format will be a talk, with the presenter(s) talking live in front of slides/video, with a brief question period at the end, fitting into a 10, 20 or 30 minute time slot.
  • Videos - One new format is the video presentation, with up to 2 minutes of self-contained audio-visual content, featured alongside the talks in the program. Videos will be presented without live narration or Q/A afterward.
  • Workshops - Also new this year are workshops, in which the presenter(s) will provide a hands-on in-depth look at a particular topic in a more interactive format, over the course of up to 3 hours.

This year’s ROSCon will also include invited panels and keynote speakers.

We cannot offer content that is not proposed! If there is a topic on which you would like to present, please propose it. If you have an idea for an important topic that you do not want to present yourself, please post it for discussion on ROS Discourse.

General Content Guidelines:

All topics related to ROS are invited. Example topics include:

  • New packages / frameworks
  • Insights / improvements for existing packages
  • Case studies on unique ROS deployments / use cases
  • Developments for specific robots, sensors, platforms
  • Competitions / collaborations / initiatives
  • ROS in commercial / research / teaching environments
  • Standards / best practices / development tools

To get an idea of the content and tone of ROSCon, check out the slides and videos from previous years.

Review Criteria

All submissions will be reviewed by the program committee to evaluate:

  • Relevance to the ROS Community - The proposed content should use ROS in a substantial way, but beyond that, the work must also be relevant and compelling to a general ROS audience. Writing a ROS driver for a specific piece of hardware is an excellent contribution to the community, but describing the intricacies of its firmware may not be relevant to this audience. Furthermore, content should be relevant to a global and diverse community.
  • Quality of Content/Impact - We encourage proposals to contain big ideas with high impact. It is preferable that proposals have a demonstrable quality as opposed to being purely theoretical.
  • Quality of Presentation - Articulating your ideas clearly and grammatically is a key prerequisite for giving a compelling live presentation.
  • Originality/Novelty - Content should be original and not something that has already been heard before. Will this be the 40th talk on a particular topic at ROSCon? Or are you presenting something new?
  • Open Source Availability - Because we are an open-source community, proposals for which the underlying code and other content is available under an open source license have a greater chance of being accepted. It is not a hard requirement, but proposals focused on proprietary systems should contribute in some other way to the community. Promises of future release are difficult to evaluate, so having your content released at the time of proposal submission is preferred.

Additional consideration will be given to balancing the subject matter and duration of presentation.

We encourage proposals from presenters of all backgrounds and experience levels.

If you have any questions about whether your subject matter is appropriate, feel free to post on Discourse or contact the ROSCon 2019 Organizing Committee at

Workshop Submission Information

The deadline has passed; it was: May 22nd, 2019.

Workshop proposals must include

  • Title (maximum 70 characters)
  • Presenter(s) (name and affiliation)
  • Summary - for public consumption, used in the program schedule (maximum 100 words)
  • Description - outline and goals, for review by the program committee. Describe the intended audience and what resources (if any) would be required. Please be sure to include enough information in your proposal for the program committee to evaluate the above review criterion.

Accepted presenters will be required to provide their materials 5 weeks before ROSCon for content review to ensure the quality of the event. Content that does not pass review may be removed from the schedule at the discretion of the program committee.

Talk Submission Information

The deadline has passed; it was: July 15th, 2019.

Talk proposals must include

  • Title (maximum 70 characters)
  • Presenter(s) (name and affiliation)
  • Summary - for public consumption, used in the program schedule (maximum 100 words)
  • Description - outline and goals, for review by the program committee. Describe the intended audience and what they can expect to learn. Please be sure to include enough information in your proposal for the program committee to evaluate the above review criteria.

This information must be formatted as a pdf, using the templates available below.

Accepted presenters will be required to provide their materials 5 weeks before ROSCon for content review to ensure the quality of the event. Content that does not pass review may be removed from the schedule at the discretion of the program committee.

Video Submission Information

Video submissions must include

  • Title (maximum 70 characters)
  • Presenter(s) (name and affiliation)
  • Summary - for public consumption, used in the program schedule (maximum 100 words)
  • Link to video online (maximum of two minutes). Do not feel the need to pad your video to two minutes: a concise thirty second video will present better than a slow two minute video.

Videos do not need to provide an extended description, but will need to provide a link to the video online. Note that the submitter is responsible for ensuring that the video is viewable by the reviewers. Note that while revisions may be made between the submission deadline and the conference, it will be reviewed based on the submitted content, which should be “finished quality.”


Workshop proposal submission deadline: May 22nd, 2019

The deadline has passed; it was: May 22nd, 2019.

Talk proposal submission deadline: July 15th, 2019

The deadline has passed; it was: July 15th, 2019.

Proposal Templates

Please use one of the following templates for creating your talk proposal.

Please use one of the following templates for creating your video proposal.

Lightning Talks

If you are interested in giving a lightning talk here’s an overview of how it will work.

On the first morning through the morning break we will provide a form for submitting your name and talk title for a lottery. Before lunch the lightning talk selection will be announced and the presenters should bring any slides they want to present to a volunteer at the registration desk during lunch. Slides are not required, and there’s no particular format. Though it must work on the coordinators laptop so common portable formats such as pdfs are recommended. Videos are also ok but should be edited to fit inside the time limit and should not rely on the audio from the video. Given the time constraint, we would recommend against trying to do a live demo.

Lightning Talk Process

Each year we’ve had lightning talks we’ve ended up with more talks than we have had time to present. We’ve followed various techniques to try to be fair distributing them including a first come first served policy and drawing straws. These are all stressful and a hassle for attendees to hurry to be in the right place.

This year we’re going to follow the following procedure:

  • The committee will post a link to a web form to sign up on-site at the beginning of the first day’s remarks.
  • It will also be posted at the registration desk.
  • Submissions will be allowed until the end of the first Coffee Break.
  • The Organizing Committee will review the submissions and then both days talks will be selected at random and announced at the beginning of lunch on the first day.
  • If you are selected you will be contacted by the committee and will have until the end of lunch the first day to bring your slides to the volunteer(s) at the registration desk.
  • During the lightning talk session your slides will be preloaded and please be ready to talk in order.
More Info

Organizing Committee

General Chair

Brian Gerkey (Open Robotics)

General Co-Chairs

Tully Foote (Open Robotics)

Ryan Gariepy (Clearpath Robotics)

Diversity Co-Chairs

Louise Poubel (Open Robotics)

Steven! Ragnarök (Open Robotics)

Finance Chair

Roberta Friedman (Open Robotics)

Local Arrangements Co-Chairs

Jenssen Chang (Gaitech Robotics)

Wu Nai Qi (Macau University of Science and Technology)

Program Co-Chairs

David Lu!! (Locus Robotics)

Melonee Wise (Fetch Robotics)

Diversity Committee

Esteve Fernandez (Apex.AI)

Irati Zamalloa (Acutronic Robotics)

Jose Luis Rivero (Open Robotics)

Kerri Fetzer-Borelli (Toyota Research Institute)

Laura Alzola (Acutronic Robotics)

Louise Poubel (Open Robotics)

Mabel Zhang (Open Robotics)

Michael Carroll (Open Robotics)

Sarah Elliott (Fetch Robotics)

Steffi Paepcke (Toyota Research Institute)

Steve Peters (Open Robotics)

Steven! Ragnarök (Open Robotics)

ROSCon 2019 Diversity Scholarships

The ROSCon 2019 organizing committee aims for ROSCon to represent the entire ROS community, which is diverse and global. In addition to promoting technology that is open source, we strive to ensure that our community is as open and accessible as possible. Inclusion and diversity benefit the ROS ecosystem as a whole.

Whoever you are, whatever you do, and wherever you do it, if you’re interested in ROS, then we want you to join us at ROSCon in Macau October 31st – November 1st. To help reduce financial barriers to conference attendance, the ROSCon organizing committee is offering a number of scholarships to members of traditionally underrepresented groups in the robotics community. Thanks to the support of the program’s sponsors, each scholarship includes one complimentary conference registration and three nights’ accommodation shared with another recipient*. Limited travel support is available for participants whose travel to the conference would otherwise be infeasible**. Please note that all other expenses (including any visa requirements) will be the responsibility of the participant.

*To maximize the impact of scholarship funds, scholarship recipients will be asked to share a room with another recipient. Under special circumstances alternative arrangements can be accommodated.

**Participants will be responsible for covering their travel expenses up front, as the travel support will be provided after the conference has been attended.

For more information please see the announcement.

Past Events

ROSCon has been held annually since 2012. If you’d like to know more we have archives of all the past programs with recordings of the talks and most of the slides. The sites can be found at the locations below.

Code of Conduct

All attendees, speakers, sponsors and volunteers at our conference are required to agree with the following code of conduct. Organisers will enforce this code throughout the event. We expect cooperation from all participants to help ensure a safe environment for everybody.

The Quick Version

Our conference is dedicated to providing a harassment-free conference experience for everyone, regardless of gender, gender identity and expression, age, sexual orientation, disability, physical appearance, body size, race, ethnicity, religion (or lack thereof), or technology choices. We do not tolerate harassment of conference participants in any form. Sexual language and imagery is not appropriate for any conference venue, including talks, workshops, parties, Twitter and other online media. Conference participants violating these rules may be sanctioned or expelled from the conference without a refund at the discretion of the conference organisers.

The Less Quick Version

Harassment includes offensive verbal comments related to gender, gender identity and expression, age, sexual orientation, disability, physical appearance, body size, race, ethnicity, religion, technology choices, sexual images in public spaces, deliberate intimidation, stalking, following, harassing photography or recording, sustained disruption of talks or other events, inappropriate physical contact, and unwelcome sexual attention.

Participants asked to stop any harassing behavior are expected to comply immediately.

Sponsors are also subject to the anti-harassment policy. In particular, sponsors should not use sexualised images, activities, or other material. Booth staff (including volunteers) should not use sexualised clothing/uniforms/costumes, or otherwise create a sexualised environment.

If a participant engages in harassing behavior, the conference organisers may take any action they deem appropriate, including warning the offender or expulsion from the conference with no refund.

If you are being harassed, notice that someone else is being harassed, or have any other concerns, please contact a member of conference staff immediately. Conference staff can be identified as they’ll be wearing badges as well as there will be staff at the registration desk.

Conference staff will be happy to help participants contact hotel/venue security or local law enforcement, provide escorts, or otherwise assist those experiencing harassment to feel safe for the duration of the conference. We value your attendance.

We expect participants to follow these rules at conference and workshop venues and conference-related social events.

Social Media

#ROSCon2019 #ROSCon @OpenRoboticsOrg @rosorg