Open Source @ AWS AWS RoboMaker Ricardo Sueiras | Principal Evangelist, Amazon Web Services I s t a n b u l L o f t @094459

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 2 What is a robot? Sense Compute Act

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 3 Robotic Arms International Space Station Drones Education Water Home Self-Driving Vehicles Autonomous Walker Rover Robot landscape

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 4 Mobile robotics trends 2018 We are at the beginning of an inflection point, where expected growth in the use of mobile robots will increase by almost tenfold over the next 2–3 years, but…

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 5 Robotics trends in 2018 Robotics is undergoing fundamental change in collaboration, autonomous mobility, and increasing intelligence Source: IDTechEx • Logistics • Construction • Retail • Hospitality • Healthcare Robots are being put to work every day across many industries • Agriculture • Energy Management • Oil and Gas • Facilities Management • Household chores By 2023, it’s estimated that mobile autonomous robots will emerge as the standard for logistic and fulfillment processes By 2030, 70% of all mobile material handling equipment will be autonomous

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 7 Enabling technologies are here Sensors Intel RealSense, FaceID, Velodyne, Quanergy, etc. Arms Universal Robotics, Rethink, Franka Emika, ABB, Kuna, etc. Grippers Soft Robotics, RightHand, GrabIt, Shadow, etc. Mobility Agility Robotics, GreyOrange, Boston Dynamics, etc. Motors Livedrive, Inception Drive, Automata, etc. AI Coprocessors Graphcore, NVIDIA, TPU, Cerebras, etc.

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 8 and yet...

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 11 If demand is high and hardware is cheap, why doesn’t everyone automate?

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 12 Cost breakdown of a robotic work cell

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 13 Robotic development is difficult and time consuming Requires machine learning expertise for intelligent functions Many prototyping iterations Days spent setting up and configuring Months to building a realistic simulation environment Duplicated efforts integrating an application management system

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 14 Robotic development cycle 2) Develop robotics application 1) Select robotics software framework 1) Deploy and manage application 3) Test and simulate application New application release and update

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 15 Most widely used software framework for teaching and learning about robotics – over 16 million .deb (Linux Debian) packages downloaded in 2018, a 400% increase since 2014 Founded in Stanford labs over 10 year ago, now managed by the Open Source Robotics Foundation (OSRF) Global open-source community supports two products—Robot Operating System (ROS) and Gazebo ROS A set of software libraries and tools, from drivers to algorithms, that help developers build robot applications Gazebo Robust physics engine, high-quality graphics, and programmatic and graphical interfaces to help developers simulate robots Robot Operating System (ROS) primer

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 16 Introducing AWS RoboMaker A service that makes it easy for developers to develop, test, and deploy robotics applications, as well as build intelligent robotics functions using cloud services

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 17 AWS RoboMaker service suite Development Environment Simulation Cloud Extensions for ROS Fleet Management

AWS RoboMaker Development Environment v Start development with zero setup effort v Create RoboMaker development environment with a single click v Automatic download, compile and configure operating system, development software, and ROS

sim_ws robot_ws Develop Build Bundle Simulate ROS AWS extensions S3 bucket Robot application Simulation application AWS RoboMaker Development Environment

AWS RoboMaker Cloud Extensions for ROS Cloud extensions written as ROS packages automatically create connections and make API calls to AWS services, such as Amazon Lex, Amazon Polly, Amazon Kinesis Video Streams, Amazon Rekognition, and Amazon CloudWatch LEX speech recognition POLLY speech generation KINESIS VIDEO STREAMS video streams REKOGNITION image and video analysis CLOUDWATCH logging and monitoring

ROS Nodes and topics AWS Cloud Node logic Temporary security credential Stored credential Robot … or … AWS RoboMaker CloudWatch Extension for ROS

AWS RoboMaker Simulation v Pre-built virtual 3D worlds, bring your own v Zero infrastructure to provision, configure or manage. v Run multiple simulations in parallel v Automatically scales, pay-as-you-go simulation resource consumption

Robot App Sim App Applications S3 Bucket Simulation Gazebo Client Simulation Instance Logs S3 Bucket Robot Logs Simulation Logs rqt rviz Terminal Cloud Extensions for ROS VPC Rule Alarm Metrics CloudWatch AWS RoboMaker Simulation

No content

No content

Robot App Simulation Sim_World #1 Robot App Sim_World #2 Robot App Sim_World #n + + + Logs Log Files #1 Log Files #2 Log Files #n Aggregated Metrics AWS RoboMaker Simulation

AWS RoboMaker Fleet Management vIntegrated with AWS Greengrass vSecurity & fault-tolerance for updates vDigital Twin for your robot vDeploy application over-the-air with a few clicks from AWS Console

Concurrent deployment 20% Failure threshold 15% Deployment Job (10 Robots) Failure threshold 15% AWS RoboMaker Fleet Management

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 29 AWS RoboMaker Architecture ROS/ROS2 Development Environment Simulation Fleet Management Cloud Extensions for ROS Build Tool Cloud Development Environment Debug ML Model Training Iterative Simulation Regression Testing Registration Deployment Monitoring Management Lex Polly Rekognition Kinesis Video Streams CloudWatch Metrics CloudWatch Logs Metric and Logging

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 30 Benefits of AWS RoboMaker Accelerated development timelines Intelligence out of the box Zero infrastructure provisioning Lifecycle management

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 31 Designed by developers, for developers Application Developer Testing Development iteration Quality Engineer Regression testing Metric monitoring System Engineer Deploy applications Software updates Researchers, Hobbyists, Students Curriculum development R&D

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 32 Customer stories “With AWS RoboMaker, we are able to easily test the robotics related software applications in a cloud environment, and rapidly generate synthetic imaging data to train our 3D site model creation algorithms. AWS RoboMaker also provides the ideal fleet management solution for use on ground vehicles and drones. The integration between fleet management and AWS Greengrass makes it really easy to enable communications among ground vehicles, drones, and IoT solutions.” —Hamid Montazeri, VP of SW Engineering and Robotics at Stanley Black & Decker

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 33 Customer stories “We have been evaluating AWS RoboMaker for our line of Furo robots, used in public venues for guest services, information, and entertainment. Through this evaluation, we’ve discovered that the RoboMaker cloud extensions have provided us with a comprehensive set of intelligence features that can be leveraged with little development effort because they easily integrate into our existing ROS application. As a new AWS customer, the sample applications provided us with exactly what we needed to get started. With the acceleration of development time we expect to gain from AWS and RoboMaker, we now have new ideas and possibilities for market expansion.” —Dr. SeKyong Song, Founder and CEO, Future Robot

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 34 Customer stories “AWS RoboMaker exponentially increases the capabilities of Lea, an autonomous robot assistant for the elderly and disabled. Lea is interactive, keeps elderly safe and active, while it can talk to you, navigate around your house and keep you connected with family and doctors. We have used RoboMaker cloud extensions for ROS to enhance Lea with video and telemetry data streaming, and voice interaction capabilities using services like Amazon Kinesis, Amazon Lex, and Amazon Polly. These cloud services and extensions provided by RoboMaker have enabled us to rapidly develop new features, while breaking the limitations of small on-board computing power.” —Dimitrios Chronopoulos, Lead Mobility Engineer, Robot Care Systems

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 35 AWS RoboMaker Sample Robot Applications Hello World Navigation and Person Recognition Voice Commands Robot Monitoring Object-following using RL Self-driving using RL

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 36 AWS RoboMaker Pricing Structure v Cloud Extensions for ROS: Customers will incur standard AWS service charges when the ROS application utilizes an AWS service through these cloud extensions. v Development Environment: There is no extra charge for the RoboMaker development environment. Customers pay only for the underlying compute and storage resources (e.g. EC2 instances and EBS volumes). v Simulation: Pricing is based on resource consumptions, measured as number of “Simulation Units”. “Simulation Unit” is metered at minute granularity and each unit is comprised of 1 vCPU and 2 GB memory and is charged at $0.4 per hour. v Fleet Management: Customers pay for the underlying Greengrass resources at the standard price of $0.16 per active robot (device) per month.

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark AWS RoboMaker architecture AWS Cloud Robot applications Simulation Log Files Developers Deploy application Robot Rviz Gazebo Rqt

© 2018, Amazon Web Services, Inc. or its Affiliates. All rights reserved. Amazon Confidential and Trademark 38 AWS RoboMaker Investment in ROS Actively guiding the development of the newest version of ROS (ROS2) via representation on the Technical Steering Committee (TSC) of OSRF Investment to provide Long Term Support (LTS) for ROS2 • LTS maintains backwards compatibility • LTS allows developers to release commercial and production-level products on ROS2 Investment to increase ROS2 packages • Packages are reusable and provide unique robotics functions such as mapping and navigation • AWS driving migration of 113 critical packages identified for ground mobility robots to ROS2 by the first ROS2 LTS release Leading the security and logging design of ROS2 and contribution to the ROS2 core messaging system, Data Distribution Service (DDS)