<?xml version="1.0" encoding="UTF-8"?><rss xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:atom="http://www.w3.org/2005/Atom" version="2.0" xmlns:cc="http://cyber.law.harvard.edu/rss/creativeCommonsRssModule.html">
    <channel>
        <title><![CDATA[Stories by UberATG on Medium]]></title>
        <description><![CDATA[Stories by UberATG on Medium]]></description>
        <link>https://medium.com/@UberATG?source=rss-4275c7808cea------2</link>
        <image>
            <url>https://cdn-images-1.medium.com/fit/c/150/150/1*6yMcz_vr_DNccy-71-2rpQ.jpeg</url>
            <title>Stories by UberATG on Medium</title>
            <link>https://medium.com/@UberATG?source=rss-4275c7808cea------2</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Tue, 17 Nov 2026 01:25:48 GMT</lastBuildDate>
        <atom:link href="https://medium.com/@UberATG/feed" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Uber ATG Releases 2020 Safety Report]]></title>
            <link>https://medium.com/@UberATG/uber-atg-releases-2020-safety-report-575db33f2bd7?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/575db33f2bd7</guid>
            <category><![CDATA[vssa]]></category>
            <category><![CDATA[safety-report]]></category>
            <category><![CDATA[safety]]></category>
            <category><![CDATA[uberselfdrivingcar]]></category>
            <category><![CDATA[uber-atg]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Fri, 28 Aug 2020 11:57:32 GMT</pubDate>
            <atom:updated>2020-08-28T18:05:13.584Z</atom:updated>
            <content:encoded><![CDATA[<p><strong><em>By: </em></strong><em>Uber ATG Safety Team</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*pRPeqj-UwOVlAS4xR0PoOA.jpeg" /><figcaption>One of Uber ATG’s self-driving vehicles conducts scenario testing at Pittsburgh test track facility.</figcaption></figure><p>As Uber ATG’s self-driving technology continues to mature, so too does our approach to self-driving safety. We’re taking another step forward in our commitment to an open public safety dialogue with the release of our <a href="https://uber.box.com/v/UberATGSafetyReport">2020 Safety Report</a>. This second installment of our report builds on our principled approach to safety, and provides an evolved view of our status while introducing a number of important enhancements.</p><p>Our Safety Report is intended to speak to a number of audiences, including: future users of self-driving vehicle (SDV) technology; those interested in how Uber ATG is working to promote safety throughout the development process; policymakers, including legislators, regulators, and local officials seeking to understand our organization or the current state of the technology; and other developers who may be interested in identifying opportunities to collaborate.</p><h4><strong>Why we’ve updated our Safety Report</strong></h4><p>Our 2020 Safety Report discusses Uber ATG’s current approach and progress in the development and operation of safe SDV technology and the opportunities we see for possible improvement in the future. Important additions to our safety approach are incorporated, such as the release of our public <a href="https://www.uber.com/us/en/atg/safety/safety-case-framework/">Safety Case Framework</a>, the adoption and implementation of a Safety Management System within our organization, and the establishment of our independent <a href="https://medium.com/@UberATG/introducing-uber-atgs-self-driving-safety-responsibility-board-10efc615c9bc">Safety and Responsibility Advisory Board</a>. Further, this edition puts a finer point on each of our five Safety Principles and how they are embodied in our work.</p><p>The U.S. Department of Transportation (USDOT) and its National Highway Traffic Safety Administration (NHTSA) introduced the concept of a Voluntary Safety Self-Assessment (VSSA) with the release of its regulatory guidance <a href="https://www.nhtsa.gov/sites/nhtsa.dot.gov/files/documents/13069a-ads2.0_090617_v9a_tag.pdf"><em>Automated Driving Systems 2.0: A Vision for Safety</em></a>. Uber ATG released its first voluntary safety report, <a href="https://uber.app.box.com/v/UberATGSafetyReport?uclick_id=597e4853-c389-47d5-8e6f-d27aa2ea7b74"><em>A Principled Approach to Safety</em></a>, shortly thereafter as an act of transparency to our stakeholders. This concept of voluntary safety self-reporting has since been maintained through subsequent guidance including USDOT’s <a href="https://www.transportation.gov/sites/dot.gov/files/docs/policy-initiatives/automated-vehicles/320711/preparing-future-transportation-automated-vehicle-30.pdf"><em>Preparing for the Future of Transportation: Automated Vehicles 3.0</em></a><em> </em>and <a href="https://www.transportation.gov/sites/dot.gov/files/2020-02/EnsuringAmericanLeadershipAVTech4.pdf"><em>Ensuring American Leadership in Automated Vehicle Technologies: Automated Vehicles 4.0</em></a>.</p><p>NHTSA’s Voluntary Guidance outlines twelve ADS Safety Elements — which collectively identify various safety goals relevant to automated driving systems and offer approaches for achieving them. In our first voluntary safety report, released in 2018, Uber ATG chose to address these ADS Safety Elements through our internally-developed Safety Principles: <em>Proficient; Fail-Safe; Continuously Improving; Resilient; and Trustworthy</em>. Our Safety Principles encompass all ADS Safety Elements; each Safety Element is addressed by at least one, if not each, Uber ATG Safety Principle.</p><h4><strong>Release of the Uber ATG Safety Case Framework</strong></h4><p>Uber ATG’s five Safety Principles are the foundation for our approach to SDV safety — spanning vehicle through enterprise levels. We believe that for a self-driving vehicle to be acceptably safe to operate, it must be shown to be <em>Proficient, Fail-Safe, Continuously Improving, Resilient, and Trustworthy</em>. These principles represent our view on the set of necessary high-level criteria governing our safety-conscious development and deployment of self-driving technology. Fulfilling them requires both rigorous system development and thorough organizational processes.</p><p>In 2019, we codified these principles and our safety approach in Uber ATG’s Safety Case Framework and released it to the public domain — a standardized framework for achieving acceptable levels of safety for SDV operations on public roads and responsibly developing and deploying SDVs within a self-driving enterprise.</p><p>In our Safety Report, we organize discussion of our technology, processes, and operations around our five Safety Principles in much the same way as we organize the claims and supporting evidence of our individual safety cases. This approach underpins the policies, processes, and philosophies that define the way we currently performs our work and builds confidence in the safety of our systems and operations.</p><h4><strong>Increased Focus on Organizational Safety</strong></h4><p>The 2020 Safety Report also places an increased focus on Uber ATG’s progress in organizational safety — central to which is our instantiation of an enterprise Organizational Approach to Safety Management and the launch of Uber ATG’s Safety Management System (SMS).</p><p>Uber ATG is committed to a formal and systematic approach to managing safety. A robust organizational approach to safety management, generally based on the <a href="https://www.icao.int/safety/fsix/Library/DOC_9859_FULL_EN.pdf">ICAO Safety Management principles</a> and generally referred to as Safety Management System, works to build and reinforce a culture of safety, which in turn helps to continuously improve an organization’s safety performance. It does so by proactively managing safety risk while providing safety assurance oversight of the organization’s many programs and processes. This approach requires planning, organization, communication strategies, key metrics, and direction of the entire organization.</p><p>By focusing on four key components — a detailed Safety Risk Management structure, a robust Safety Assurance program, disciplined documentation of its Safety Policy, and Safety Promotions and Education — Uber ATG’s organizational safety management approach influences our engineering decisions and promotes a positive Safety Culture supported by the organization’s leadership, core values, and employee engagement. Each component plays an important role in cultivating a strong and effective organization-wide safety program and is necessary to enable a high functioning organization. The SDV technology industry lends itself to benefitting from this organizational safety approach when met with the challenges of developing a rapidly-evolving technology in a complex and varied environment.</p><p>Since releasing our first safety report, Uber ATG has architected and enhanced many components within its organizational safety management structure, beginning with the foundation of a clearly defined and documented Safety Policy to include specific accountability and commitment to safety throughout the organization. Uber ATG stood up a Safety Review Board and defined an open and just culture with various voluntary and confidential tools for reporting safety concerns and issues without fear of reprisal. Borrowing from established examples in other industries, Uber ATG has defined a Safety Risk Management process that captures organizational change, analyzes the risk with that change and presents the risk to organizational leadership to determine if it is tolerable. Through our Safety Case Framework, we have developed a safety assurance and oversight program designed to be effective at proactively and reactively identifying safety risk and the effectiveness of existing safety risk controls. Finally, Uber ATG has built a robust Safety Promotions and Education program that is continually communicating to and educating the organization.</p><p>We believe that tailoring and systematically applying the four key components of Uber ATG’s organizational safety approach are critical for the acceptably safe and responsible development, and eventual full-scale operation, of SDVs. Discussion of Uber ATG’s organizational safety management approach is found throughout the 2020 Safety Report.</p><h4><strong>External Engagements and Uber ATG’s Safety and Responsibility Advisory Board</strong></h4><p>Uber ATG’s external engagements and independent advisory activities have evolved significantly since the release of its first safety report. Chief among these are contribution to the <a href="https://avsc.sae-itc.org/">Automated Vehicles Safety Consortium</a> convened by SAE, participation in the Underwriters Laboratory industry effort to create a standard for safety argument (<a href="https://ul.org/UL4600">UL4600</a>), and establishment of our self-driving <a href="https://medium.com/@UberATG/introducing-uber-atgs-self-driving-safety-responsibility-board-10efc615c9bc">Safety and Responsibility Advisory</a> (SARA) Board.</p><p>In 2019, Uber ATG established the SARA Board to provide objective reviews of and input to varied aspects of our self-driving program. This external safety advisory board consists of independent, recognized experts in a variety of relevant fields — drawing from aviation safety, insurance, emergency/trauma medicine, automotive safety, and academia. The board meets quarterly to review and recommend improvements to the way Uber ATG develops self-driving technology and brings fully self-driving vehicles to market. Relevant areas of consideration include: organizational goals and priorities; internal policies and procedures; potential risks and remediation; ways to increase public understanding and trust in self-driving vehicles; industry engagement and responsibilities.</p><h4><strong>Looking Forward</strong></h4><p>Our 2020 Safety Report provides a holistic look into the overall progress of our organization, technology, and operations — along with the path we see ahead. Delivering on our commitment to update the public along that path sits at the core of Uber ATG’s belief in transparency in self-driving safety, and we look forward to a continued dialogue with our readers, our stakeholders, and our partners through this update and future editions of our Safety Report.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=575db33f2bd7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Uber ATG issues enhancements to Safety Case Framework]]></title>
            <link>https://medium.com/@UberATG/uber-atg-issues-enhancements-to-safety-case-framework-1b5a02c62159?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/1b5a02c62159</guid>
            <category><![CDATA[uber-atg]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[uber]]></category>
            <category><![CDATA[uberselfdrivingcar]]></category>
            <category><![CDATA[self-driving]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Mon, 27 Jul 2020 19:57:41 GMT</pubDate>
            <atom:updated>2020-07-27T19:57:41.410Z</atom:updated>
            <content:encoded><![CDATA[<p>By: Nat Beuse, Head of Safety at Uber Advanced Technologies Group</p><p>In July 2019, the team at Uber ATG <a href="https://medium.com/@UberATG/trailblazing-a-safe-path-forward-e02f5f9ef0cc">released</a> our first, open-sourced <a href="https://www.uber.com/us/en/atg/safety/safety-case-framework/">Safety Case Framework</a>, which clearly organizes the goals, claims, and evidence necessary to substantiate that our self-driving vehicles (SDVs) are acceptably safe to operate on public roads. The framework charted an outline for prioritizing safety during testing and development with Mission Specialists behind the wheel, but it also projected Uber ATG’s safety argument to support future use cases, including eventual driverless operations.</p><p>Committing to the public release of our Safety Case Framework is a key component of our overall safety strategy, as transparency in our current and future safety operations is key to building trust and identifying areas for improvement. Through the lens of the Safety Case Framework, internal and external safety discussions have become more specific and tangible. The Framework has facilitated and will continue to facilitate productive conversations with regulators, industry partners, and others in the self-driving space.</p><p>Having started this conversation in 2019, today we are pleased to announce that we have significantly expanded our Safety Case Framework in both depth and breadth, with the intent to bring further clarity to industry self-driving safety dialogue.</p><h4><strong>Influence on the Safety Case Framework</strong></h4><p>Quite a few events have transpired since the 2019 release of the Safety Case Framework that informed the content found in our latest release.</p><p>Following last year’s release, ATG participated in the creation of the <a href="https://ul.org/UL4600">UL4600 standard</a>, which was published in April 2020. This standard embodies the spirit and intent of the Safety Case Framework by encouraging the development of a safety case for all SDV developers. UL4600 harmonizes existing industry safety standards and brings a comprehensive look at safety across the entire SDV lifecycle. This version of the Safety Case Framework seeks to incorporate lessons from the UL4600 standard by fully mapping the UL4600 standard to the Framework. It is worth noting that this Framework is broader and deeper than UL4600 in a few key areas, specifically operations with a Mission Specialist and in the content related to the fifth safety principle, “Trustworthy.”</p><p>At Uber ATG, we are developing our own self-driving technology while simultaneously developing resources to enable other self-driving vehicle developers to share and verify their approach to safety to help responsibly onboard their SDVs to the Uber network. The Framework helps clarify expectations for SDV companies seeking to operate on the Uber network by sharing it publicly. It provides a technology agnostic yardstick for our self-driving partners to gauge and develop their safety case <em>prior</em> to seeking access to the Uber network. This process also helps inform Uber ATG’s evaluation of the safety posture of a potential partner.</p><p>This version of the Framework also reflects Safety Management System (SMS) concepts, which we’ve been implementing over the last several years. We have incorporated a variety of SMS elements in this version of our Framework, as we see the value of this approach for different self-driving developers and use cases to promote safe operations.</p><h4><strong>What has changed?</strong></h4><p>Since the July 2019 release, our Safety Case Framework has expanded in both depth and breadth. We have retained our five safety principles of:</p><ul><li>Proficiency</li><li>Fail Safe</li><li>Continuously Improving</li><li>Resilient</li><li>Trustworthy</li></ul><p>The first release of the framework broke down the principles into another 2–3 levels. In the current release, the safety principles are addressed at an even more granular level — in some cases, reflecting an additional 5 levels of specificity often supported by example evidence wherever appropriate. This example evidence is indicative of what would be required to substantiate that an individual claim has been satisfied.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*tQ7yEVRgfDZdEHa8" /></figure><p>In the above example claim for the latency of the Motion Planning software, you can see an approach by which five pieces of evidence would be needed to justify the claim. This evidence is intended to define, justify, verify and validate the claim of the safety case is true.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/0*hg-79Q_s_9uuMoxN" /></figure><p>Additionally, the breadth of the claims have expanded since the last release of the Safety Case Framework. This increased precision in the language of The Framework reduces ambiguity and increases transparency. In the example above, the Safety Case Framework G2.1.3.1 is expanded to over twenty “child” claims. The child claim breakdown in this way supports the claim of G2.1.3.1 that all identified risks and hazards have been appropriately mitigated.</p><p>With this additional specificity, the Safety Case Framework has grown in size by a factor of roughly six. We feel this increased level of detail increases developer and stakeholder ability to meaningfully discuss safety by providing specificity around the safety argument.</p><h4><strong>Validation of the Safety Case Framework</strong></h4><p>The review and evaluation of the Safety Case Framework by others is a strategic objective of Uber ATG. We have sought multiple independent industry experts to review and scrutinize the content of the Safety Case Framework. Through these reviews, we elicited feedback on the logic of the argument, on the soundness of the relationship between parent and child claims (i.e., that the child claims provided a valid roadmap to proving up the higher-level parent claims), and on the sufficiency of the evidence used to support the claims. Lastly, we sought feedback on how well the Safety Case Framework maps and aligns with UL4600. To support this alignment, Uber ATG enlisted the support of <a href="https://edge-case-research.com/">Edge Case Research</a>, whose team of independent experts reviewed the Safety Case Framework and provided valuable feedback over a three month review period. This in-depth review improved the clarity and completeness of the Safety Case Framework.</p><p>Furthermore, Uber ATG engaged our <a href="https://medium.com/@UberATG/introducing-uber-atgs-self-driving-safety-responsibility-board-10efc615c9bc">Self-Driving Safety &amp; Responsibility Advisory</a> (SARA) Board for their review and assessment of the Safety Case Framework. The SARA Board includes a diverse set of experts in areas ranging from academia, automotive, aerospace, and non-governmental agencies.</p><h4><strong>How will the Safety Case Framework be used?</strong></h4><p>At Uber ATG, the Safety Case Framework is the basis for developing our internal safety cases — meaning, specific accumulations of evidence that substantiate the safety for a particular program and/or stage of operation (e.g., operations with two Mission Specialists; operations with passengers; etc.). We utilize the Framework today, tailoring it to address the scope and objectives of a particular project or program by focusing on the elements of the Framework that are most relevant to a given project or program, and assembling supporting evidence for that use case. The result provides a blueprint for our teams to develop our technology safely and responsibly. Our internal work plans, objectives, and deliverables align to create evidence to support the safety case. A complete safety case is required <em>prior</em> to SDV operation for any use case, including operations on public roads and on our test track.</p><h4><strong>Looking Ahead</strong></h4><p>With the update of the Safety Case Framework, we recommit to leading on safety through transparency. We encourage the use of the Safety Case Framework by others without license or attribution. The Safety Case Framework is licensed for use by all under <a href="https://creativecommons.org/publicdomain/zero/1.0/legalcode">Creative Commons Zero</a>. We will continue to develop and refine the Safety Case Framework based on our lessons learned as we test and deploy new vehicles, while always keeping in mind the evolution of self-driving vehicle standards.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=1b5a02c62159" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[On the road to Washington, D.C.]]></title>
            <link>https://medium.com/@UberATG/on-the-road-to-washington-d-c-86889b5dd85?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/86889b5dd85</guid>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[self-driving]]></category>
            <category><![CDATA[uber]]></category>
            <category><![CDATA[washington-dc]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Thu, 23 Jan 2020 17:31:05 GMT</pubDate>
            <atom:updated>2020-01-29T19:15:42.407Z</atom:updated>
            <content:encoded><![CDATA[<p><strong><em>Data collection beginning in D.C.</em></strong></p><p><em>By: Danielle Burr, Head of Uber Federal Affairs</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*aPuu-_I3Xa_T7NS1vrhUvA.jpeg" /></figure><p>We’re on a mission to deliver safe and reliable self-driving technology to Uber users around the world. Uber Advanced Technologies Group has already started this journey in Dallas, Pittsburgh, San Francisco, and Toronto. Today, we’re adding another city to that list 一 our nation’s capital.</p><p>Uber first launched in Washington, D.C. in late 2011, the sixth city launched globally. Since then, we’ve been proud partners in our nation’s capital, expanding into new modes like shared POOL rides, wheelchair accessible options, JUMP e-bikes and dockless scooters, and linking Uber users with public transit to help them access the transportation modes that best fit their needs.</p><p>Starting on January 24, we will begin exploring a new mode of transportation in Washington, D.C. when we bring our self-driving cars to District roads for data collection. Importantly, these cars will be in manual driving mode 一 meaning a Mission Specialist (a specially trained vehicle operator) will maintain control of the vehicle at all times.</p><p>We are using a phased approach to develop and deploy our self-driving vehicles, taking the necessary steps to operate safely in every city. Manual data collection is the first step in our development process and part of how we are validating our self-driving expansion approach. This manual data collection allows us to:</p><ul><li>Develop high-definition maps, the foundational information layer for our self-driving system.</li><li>Capture scenarios that might be different from city to city to simulate and incorporate into on-track testing.</li><li>Further refine our expansion methodology, which involves identifying key characteristics within an operational domain in a new city, and then running that data through our autonomy system in simulation and on our test track to verify that our self-driving system performs as intended before it drives on the road.</li></ul><p>Our hope is that this first round of manually driven data collection will lay the foundation for testing our vehicles in self-driving mode in Washington, DC. While we are excited about the possibilities, we remain committed to ensuring that every mile we drive on public roads contributes safe and meaningful learnings to inform our development work.</p><p>When we think about safety, it goes beyond solely passengers. We care about keeping everyone on the road safe — whether you’re in one of our self-driving cars or crossing the street in front of one. That’s why we believe in working closely with local stakeholders and city officials and engaging with the Washington, D.C. community every step of the way.</p><p>Offering Uber riders a choice in how they get around their city is a powerful thing. That’s why at Uber we’re proud to help bring people closer to the things they need. We believe self-driving technology can play an important role in expanding transportation access, and we’re committed to developing this technology with safety at its core.<em> </em>To learn more about our testing process, check out <a href="https://www.uber.com/us/en/atg/cities/">https://www.uber.com/atg/cities/</a>.</p><p>Washington, D.C. we’ll see you soon!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=86889b5dd85" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Becoming a Mission Specialist: Piloting the Development of Safe Self-Driving Technology]]></title>
            <link>https://medium.com/@UberATG/becoming-a-mission-specialist-piloting-the-development-of-safe-self-driving-technology-bd0d4439a50a?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/bd0d4439a50a</guid>
            <category><![CDATA[safety]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[autonomous-cars]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[tech]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Tue, 12 Nov 2019 20:29:59 GMT</pubDate>
            <atom:updated>2019-11-12T21:27:52.484Z</atom:updated>
            <content:encoded><![CDATA[<h4>By: Nick Wedge, Learning and Development at Uber ATG</h4><p>Developing a self-driving vehicle is challenging, dynamic, and captivating, as there are changes and advances almost on a daily basis. Take a moment to consider what it’s like to be responsible for safely monitoring our developmental technology in the real world from behind the wheel. At Uber Advanced Technologies Group (ATG), that is the primary function of the Mission Specialist. As the pilots (driver’s seat) and co-pilots (passenger’s seat) of our developmental self-driving vehicles, they are just a handful of people who will experience the development of automated vehicle (AV) technology unlike anyone else in the world.</p><p>The job requires them to continuously scan the operating environment, compare the vehicle’s behavior with their mental model of appropriate vehicle behavior, and correct any undesired behavior. Here’s the kicker: it’s only going to get more challenging as the technology improves and capabilities expand — undesired behaviors become more subtle and infrequent requiring more vigilance.</p><p>At Uber ATG we have the responsibility of maintaining (human) learning systems that can match a rapid development cadence — to ensure that testing of AV technology in the real world is done safely and effectively. That’s the role of the Learning and Development Team.</p><p><strong>First, some context</strong></p><p>Having recently released our <a href="https://medium.com/@UberATG/trailblazing-a-safe-path-forward-e02f5f9ef0cc">Safety Case Framework</a>, you can see where our Mission Specialist education efforts fit (G1.3.1) in supporting our claim that our self-driving vehicles are acceptably safe to operate on public roads.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*cCM1TppNWwQYk2_d5ukvnw.gif" /><figcaption>Mission Specialist training and development can be found in G1.3.1 of our Safety Case Framework.</figcaption></figure><p>Not only is Mission Specialist training a part of our safety case for testing activities with a Mission Specialist, but the team responsible for developing the curriculum is a part of the 40+ person multi-disciplinary Safety Team at Uber ATG, giving us the opportunity to represent operational needs and perspective to the entire organization. While the scope of the Learning and Development Team has evolved over the years to meet the unique needs of those piloting and co-piloting our self-driving vehicles, the team continues to support all test operations, both at the track and on the road.</p><h3><strong>Training Mission Specialists</strong></h3><p>The responsibilities of a Mission Specialist are safety-critical and we have designed our training programs to reflect that. Before they join the team, Mission Specialists go through a screening process to ensure they have a current driver&#39;s license and clean record. Then they must be internally certified to safely and effectively supervise a self-driving vehicle through an in-depth training regime. These trainings are designed to ensure that the Mission Specialist has the information, knowledge and support that they need to succeed in their role.</p><p>Throughout a Mission Specialist’s career, they will be expected to maintain this internal certification to carry out their responsibilities, which requires continuous education and yearly recertifications. Below are some key focus areas of our programs that help Mission Specialists receive and maintain their certifications.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*d1awweFT8nTR_Ial7Q2q4Q.png" /><figcaption>Our certification and continuous education process.</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*rS_XSLTXXlCul14wfOzClg.jpeg" /><figcaption>Mission Specialists training and instruction takes place at our test track.</figcaption></figure><figure><img alt="" src="https://cdn-images-1.medium.com/max/639/1*95FcBjUXshAVvLN0jwCnIw.gif" /><figcaption>A Mission Specialist practicing constant touch of the steering wheel while the vehicle is in self-driving driving mode.</figcaption></figure><p><strong>Understanding the Mission</strong></p><p>Before Mission Specialists get behind the wheel of an Uber developmental self-driving vehicle, they spend their first week learning about the organization and how the work they do supports our mission to bring safe, reliable self-driving transportation to the world. We believe that, as educators, we are responsible for our learners’ understanding of the impact their work has on the company’s success. It’s also easier to train learners who find meaning and take pride in their work.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*vb39UeicN-O_mvXJ_rR4Ew.jpeg" /><figcaption>From the track to the classroom Mission Specialists are a vital part of our development process.</figcaption></figure><p><strong>Becoming A Best-in-Class Driver</strong></p><p>Not everyone personally drives a Volvo XC90 Sport Utility Vehicle — the base vehicle we currently use to test our self-driving system. It stands to reason then that it’s important to familiarize our Mission Specialists with our modified development vehicle on its own, without self-driving capabilities enabled. Mission Specialists spend time getting certified solely to operate our self-driving cars manually. This gives us the opportunity to focus on subjects such as:</p><ul><li>Defensive driving techniques</li><li>Emergency maneuvering exercises</li><li>Fatigue management techniques</li><li>Distracted driving prevention</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*-BDGpe45RllQI2upPUDi2Q.gif" /><figcaption>Our Mission Specialists negotiate a range of challenging manual vehicle maneuvers including emergency lane change scenarios.</figcaption></figure><p>Anyone piloting or co-piloting the vehicle while in self-driving will have to complete this certification, which means passing a series of in-classroom and in-vehicle assessments.</p><p><strong>Understanding the AV System</strong></p><p>Aside from familiarity with the vehicle itself, we spend a considerable amount of time educating Mission Specialists about <em>how</em> and <em>why </em>the vehicle is making the decisions it is. By taking Mission Specialists through the detailed data flows from the sensors of the vehicle to the controls that execute a trajectory or behavior, we create a more prepared pilot and co-pilot. Mission Specialists gain a strong practical understanding of the complete development program and process that Uber ATG undertakes giving them an advanced understanding of self-driving technology.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*mjZTGMPHMQQpyZzDnxmX4Q.jpeg" /><figcaption>Similar to a pilot needing to understand avionics, Mission Specialists must understand how the system makes decisions.</figcaption></figure><p>All of the topics that are introduced in-classroom are also reinforced in-vehicle, giving us the opportunity to take a learned concept and put it into action on the track. This helps ensure that our Mission Specialists can anticipate vehicle behavior and maintain safe operations from both positions; the pilot through manual controls, and co-pilot through system oversight.</p><p><strong>Training Through Faults</strong></p><p>At Uber ATG, Mission Specialists are systematically exposed to random faults injected by the vehicle’s self-driving system (such as a sudden lane departure), and environmental factors (such as unexpected road users entering the roadway). They are tested on their ability to respond to the worst possible situations. This type of training helps ensure that they have the appropriate reaction time and execute the appropriate correction maneuver.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*2podFI4oTJxV-N6pBa6Iuw.gif" /><figcaption>While the vehicle is in self-driving mode, a steering fault injection causes the vehicle to veer abruptly off course, requiring the Mission Specialist to disengage the self-driving system and correct the vehicle’s path through manual adjustments to the steering wheel.</figcaption></figure><p>Mission Specialists are first introduced to <em>Basic </em>Fault Injection Tests, which include very simple faults at low speed without outside actors or environmental factors. These injections occur during straight-line driving and are designed to introduce the learner to vehicle behaviors during a fault, such as lane drifting. <em>Basic</em> fault injection is a stepping stone to more complex <em>Scenario</em> Fault Injection Tests that represent possible situations seen out in the real world. The situations tested with a <em>Scenario</em> fault injection add the complexity of different road infrastructure, such as intersections, and actors, such as pedestrians and cyclists simulated using robots.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*ldJWg3aYqawYFcsIIxblEA.gif" /><figcaption>Mission Specialists experience how the vehicle reacts to a real-world scenario, such as a car coming out of an occluded view.</figcaption></figure><p><strong>Staying Relevant and Effective</strong></p><p>The Learning and Development team participates actively in the software development process. This means our team has a process for anticipating and managing change from software, operational policy, or operational design domain, which captures the specific conditions under which our self-driving system will operate, including where and when. When the development process, autonomy (or human) performance, a safety concern, or another avenue indicates that amendments to our training program are required, the team ensures new hire programs stay relevant. This updated training extends to current Mission Specialists by way of in-vehicle, in-classroom, computer-based training, or in a simple pre-shift brief.</p><p>What’s more, all of our training content is reviewed twice a year by the Learning and Development team, internal subject matter experts, and members of the broader Safety Team. These results are collected, analyzed, presented to the organization as evidence of our programs’ effectiveness, and serve as a rationale for the changes we make to our curricula.</p><p><strong>Maintaining Certifications</strong></p><p>Aside from having to pass a number of in-classroom and in-vehicle assessments, Mission Specialists participate in two key programs to maintain their certifications: <em>Recertification</em> and <em>Refresh</em> training.</p><p><em>Recertification Training</em> measures Mission Specialist performance on a yearly basis and ensures continued, high-performance piloting and co-piloting skills. Regardless of a Mission Specialist’s performance or time in role, they are expected to complete Uber ATG’s Autonomy Recertification program. This program provides an opportunity for Mission Specialists to relearn skills that are rarely used in practice, such as fault injection and emergency maneuver exercises.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*ZlAbRmck5FFmRdl4T5Ytrw.jpeg" /><figcaption>Recertification provides an opportunity for Mission Specialists to ensure they maintain their skills at the highest level.</figcaption></figure><p><em>Refresh Training</em> is conducted in response to time out of vehicle, a minor infraction/breach of policy, or when we identify other training opportunities that can improve Mission Specialist performance. Refresh opportunities ensure that, with the right performance diagnostic (infractions, time out of vehicle, performance reviews), Mission Specialists are given the best chance to succeed.</p><p><strong>Building Distrust in the System</strong></p><p>As our self-driving vehicle capabilities and performance increase over time, one may think that a Mission Specialist’s job gets easier. However, monitoring a system that fails less frequently over time is <a href="http://users.ece.cmu.edu/~koopman/pubs/koopman19_TestingSafetyCase_SAEWCX.pdf">even more challenging</a> than one that fails often. The reality is that a Mission Specialist who may have seen the vehicle stop at the same stop sign a thousand times before cannot presume that it will stop the next time. That is why the Learning and Development team’s goal, above all, is to develop a healthy level of distrust in the self-driving system.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*OEq7zZSRPMr4sVvBDWsNVQ.jpeg" /><figcaption>Monitoring a system that fails less frequently over time is even more challenging than one that fails often.</figcaption></figure><h3><strong>What’s Next</strong></h3><p><strong>Organization-Wide Safety Management System Education</strong></p><p>As Uber ATG’s Safety Management System (SMS) begins to take shape, the Learning and Development team is widening its scope to ensure the broader organization understands how it contributes to safety, including how to use safety reporting tools, determine how safety-related decisions are made and who makes them, manager/leadership responsibilities within our SMS, and more. With guidance from our <a href="https://uberatg.com/safetycase/gsn">Safety Case Framework</a>, we will deploy complementary educational initiatives across the company, including hosting company-wide workshops on topics such as Safety Ownership and Risk-Based Thinking.</p><p><strong>Preparing for the Future: Remote Operations</strong></p><p>As we look toward the future, the Learning and Development team aims to continue to support Uber ATG’s business needs, and supporting Remote Operations is a big part of that. While we will always support the in-vehicle Mission Specialist in whatever future scope they have, we are working closely with product and engineering teams to consider training needs for Remote Operators outside of the vehicle, focused on assisting the Rider and Autonomy when no one is behind the wheel of a self-driving car.</p><h3><strong>Conclusion</strong></h3><p>Uber ATG has made a huge commitment to supporting Mission Specialists and has empowered the Learning and Development team to be an influential force within the organization. Having Mission Specialists in our vehicles is a crucial step to delivering a fully self-driving vehicle. This post only scratches the surface of the training that we undertake and we will continue to share our work so that we can move forward as an industry together.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=bd0d4439a50a" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Now, Next, and Future: Sameer Kshirsagar]]></title>
            <link>https://medium.com/@UberATG/now-next-and-future-sameer-kshirsagar-19a85ddfd889?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/19a85ddfd889</guid>
            <category><![CDATA[careers]]></category>
            <category><![CDATA[supply-chain]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[tech]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Wed, 06 Nov 2019 19:45:02 GMT</pubDate>
            <atom:updated>2019-11-06T19:45:02.941Z</atom:updated>
            <content:encoded><![CDATA[<p><em>A profile series that introduces our team and showcases what we’re working on.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/300/1*-GPQeUdv_5Efr7J6mGRR0g.jpeg" /></figure><p>My name is Sameer Kshirsagar and I’m the Head of Supply Chain and Business Operations here at Uber Advanced Technologies Group (ATG). I started my career by spending a lot of time in school, earning a B.S. in Mechanical Engineering from Virginia Tech, an M.S. in Manufacturing Management from Kettering University, and an MBA from The Ohio State University. In addition, I spent over two decades at various companies specializing in automotive, consumer electronics and high tech. All of this served, I believe, as an excellent grounding for my work on self-driving vehicles as they require a multi-disciplinary approach.</p><p>I came to Uber ATG because of the opportunity to have a positive impact on the ever-changing mobility landscape. I could see the potential to build a world-class team that enables world-changing technology, and would work with leading technical talent. Not only that, but the impact on what Uber is doing in the self-driving space would undoubtedly be on a global scale.</p><p><strong>Now</strong></p><p>My team is heads down on organizing, optimizing and visualizing data streams to facilitate informed, data-driven, proactive business decisions. I’m always looking for innovative ways to mature our business for scale, whether that involves supply chain operations, facilities, manufacturing operations, quality, or some other aspect of the process. To that end, part of my job is to make sure that we have a strong supply base with the right partners, one that allows our team to integrate automotive, consumer electronics, and aerospace technologies into our self-driving vehicles.</p><p>From a big-picture perspective, I’m personally always looking for ways to strike the right balance between moving the needle on innovation while also instilling process discipline within my team. Also top of mind for me is strengthening my skills across multiple areas, which includes developing new supply chain analytics and fostering a strong sense of diversity and inclusion within my team.</p><p><strong>Next</strong></p><p>There are several challenges in my area that I’m eager to tackle next. For example, we are finding ways to collaborate more deeply with both our internal teams and external partners so we can solve some of our toughest problems even faster than ones we’ve solved in the past. We are also working toward mapping our supply chain in a way that allows us to visualize and optimize for scale, continuity, and efficiency. Not only that, but given the ever-changing environment, we are continually working to mature and institutionalize processes across the entire organization, which will unlock future growth. This is a never-ending process that lends itself well to the kaizen (continuous improvement) process…but that’s another blog post in itself!</p><p><strong>Future</strong></p><p>What excites me most about the future is being at the forefront of transforming global mobility to make it safer, more accessible, and more efficient for everyone.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NuNXhTTUgpWzbs9SdZ3o4Q.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=19a85ddfd889" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Introducing Uber ATG’s Self-Driving Safety & Responsibility Board]]></title>
            <link>https://medium.com/@UberATG/introducing-uber-atgs-self-driving-safety-responsibility-board-10efc615c9bc?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/10efc615c9bc</guid>
            <category><![CDATA[safety]]></category>
            <category><![CDATA[self]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[uber]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Tue, 29 Oct 2019 16:04:39 GMT</pubDate>
            <atom:updated>2019-11-01T13:34:52.666Z</atom:updated>
            <content:encoded><![CDATA[<p>By: Chan Lieu, Sr. Safety Program Analyst</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*2DX6BE0O4gDqHjjJGYkH0w.jpeg" /></figure><p>Uber ATG is pleased to announce the creation of our Self-Driving Safety and Responsibility Advisory (SARA) Board. The SARA Board is an independent panel of safety experts charged with reviewing, advising, and suggesting changes to Uber ATG’s self-driving enterprise, including inputs on organizational goals and priorities. We believe that this panel of outside experts will offer valuable independent advice as Uber ATG leads the safe development and deployment of self-driving technology on the Uber platform.</p><p>The SARA Board consists of recognized experts in a variety of relevant fields, drawing from aviation safety, insurance, emergency/trauma medicine, automotive safety, and academia. The inaugural SARA Board members include:</p><ul><li><strong>George Snyder</strong>, President of GHS Aviation Safety Specialists (Board Chair)</li><li><strong>Dr. Jeffrey Runge</strong>, former NHTSA Administrator (Board Vice-Chair)</li><li><strong>David Carbaugh</strong>, former test pilot and Chief Pilot Flight Operations Safety at Boeing (Board Secretary)</li><li><strong>Shailen Bhatt</strong>, President of Intelligent Transportation Society of America</li><li><strong>Adrian Lund</strong>, former President of the Insurance Institute for Highway Safety</li><li><strong>Dr. Victoria Chibuogu Nneji</strong>, Lead Engineer &amp; Innovation Strategist at Edge Case Research and Robotics Lecturing Fellow at Duke University</li></ul><p>The SARA Board members bring their wide range of expertise in various industries and modes of transportation and lend their diverse experiences and perspectives to advising Uber ATG. Mr. Snyder will serve as Board Chair, with Dr. Runge serving as Vice-Chair, and Mr. Carbaugh serving as Secretary. All SARA Board members will serve two-year terms and positions, rotating annually.</p><p>The SARA Board’s role will be to identify and suggest improvements to the way Uber ATG develops self-driving technology and brings fully self-driving vehicles to market. The Board will identify and suggest recommendations on:</p><ul><li>Internal policies, culture, operational procedures, and processes;</li><li>Potential risks and corresponding follow-up actions;</li><li>Ways to increase public understanding and trust in self-driving vehicles;</li><li>Uber ATG’s approach to engaging in industry-wide conversation around relevant topics such as fully driverless operations and responsibility.</li></ul><p>The Board recently held its first in-person meeting and will continue to meet quarterly.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=10efc615c9bc" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Our Public Safety Officials and First Responders’ Guide]]></title>
            <link>https://medium.com/@UberATG/our-public-safety-officials-and-first-responders-guide-73f7a49d4df7?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/73f7a49d4df7</guid>
            <category><![CDATA[safety]]></category>
            <category><![CDATA[first-responder]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[tech]]></category>
            <category><![CDATA[technology]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Thu, 24 Oct 2019 16:00:43 GMT</pubDate>
            <atom:updated>2019-10-24T16:00:43.977Z</atom:updated>
            <content:encoded><![CDATA[<h4>By Mark Jones and Wade Stormer, Law Enforcement Operations, Uber</h4><p>At Uber ATG, we recognize that to continue the safe development of self-driving vehicles, it is essential that we be transparent with the public and other stakeholders about our approach. Through proactive information-sharing and ongoing two-way dialogue that takes external views into account, we can both educate and learn from our stakeholders and others in the self-driving community.</p><p>Working with public safety officials and first responders is an important part of how we connect with the communities in which we operate. Our engagement strategy uses a multi-channel communications approach to ensure broad and easy access to the latest relevant information on our operations. This combined with community activities such as in-person briefings, town hall events, and publicly available materials fosters a consultative dialogue. Just as our development and testing activities will iterate over time, our approach in collaborating with public safety officials and first responders will also mature. The results of this will be new and updated guides and tools that aim to keep key stakeholders informed as our technology and operations evolve.</p><p>Today we are releasing our <a href="https://uber.box.com/v/UberATGFirstRespondersGuide">Public Safety Officials and First Responders’ Guide</a>. The purpose of this guide is to provide information to trained public safety officials and first responders on how to safely interact with an Uber ATG developmental self-driving vehicle (SDV) in the event of an emergency. This guide applies specifically to on-road Uber ATG developmental vehicles with a highly trained Mission Specialist behind the wheel. Mission Specialists are trained safety drivers who have undergone internal certification and specialized training that prepares them for a wide range of scenarios and incidents, from manually-directed traffic and routine traffic stops to incidents where a first responder has been called.</p><p>We will release additional guides as our operations continue to develop, such as for driverless testing, or for new vehicle platforms. This guide does not apply to third-party self-driving vehicles that may operate on the Uber network in the future.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*_xWV1Ay5hNP9R-e7H74SVg.png" /><figcaption>Identifying an Uber ATG Vehicle and what’s inside the Uber ATG self-driving system</figcaption></figure><p><strong>What’s Inside the Guide?</strong></p><ul><li><strong>Identifying an Uber ATG Vehicle:</strong> From the top-mounted lidar to the side branding, understand everything that comprises a developmental self-driving vehicle.</li><li><strong>Post-Crash Safety Features:</strong> The Volvo XC90 base vehicle post-impact safety features are enabled and expected to function as designed, depending on the type and severity of collision detected.</li><li><strong>Disengagement, Immobilization, and Powering Down: </strong>In the event of an incident, Mission Specialists follow protocols for disengaging, immobilizing, and powering down the self-driving system.</li><li><strong>Vehicle Extrication and Post-Incident Response: </strong>After an incident, safety protocols for vehicle extrication, relocation, and towing should be followed.</li></ul><p>Additionally, for law enforcement personnel, there is a step-by-step process for submitting post-incident data requests to the Uber Law Enforcement Response Team (LERT) through their portal at <a href="https://lert.uber.com/">lert.uber.com</a>.</p><p>In keeping with our goal of transparency and two-way dialogue, Uber ATG is committed to continued engagement with public safety officials and first responders. We hope to provide additional information-sharing opportunities in the form of in-person briefings and other events to demonstrate how we keep safety at the forefront of self-driving vehicle development and testing. For more information on safety at Uber ATG, you can visit our <a href="https://www.uber.com/us/en/atg/safety/">Safety website</a>, and for more information on our approach to city road testing, visit our <a href="https://www.uber.com/us/en/atg/cities/">Cities website</a>.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*DfXsFZJOVqgJ8bPu6NhCgQ.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=73f7a49d4df7" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Now, Next, and Future: Timothé Adeline]]></title>
            <link>https://medium.com/@UberATG/now-next-and-future-timoth%C3%A9-adeline-2373378afe98?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/2373378afe98</guid>
            <category><![CDATA[tech]]></category>
            <category><![CDATA[simulation]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[careers]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Tue, 01 Oct 2019 01:41:38 GMT</pubDate>
            <atom:updated>2019-10-01T01:49:10.111Z</atom:updated>
            <content:encoded><![CDATA[<p><em>A profile series that introduces our team and showcases what we’re working on.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*Q4sQ5Qi9oTmv9L8-IokiYw.jpeg" /></figure><p>My name is Timothé, I come from France, and I am a data scientist at Uber Advanced Technologies Group (ATG), currently focusing on self-driving simulation. I joined Uber in January 2017, first on the France team in Paris, and then at ATG in San Francisco.</p><p>I joined ATG for several reasons. First, I am extremely inspired by the impact that shared, electric, autonomous vehicles will have on cities, making them safer and better places to live, with less congestion, less pollution, fewer idle parked individual cars, and fewer car accidents. Secondly, bringing self-driving technology to the world is a very hard, unsolved problem, and therefore a super-exciting technical challenge. I am also personally interested in AI and robotics and in the automotive industry, working at the crossroads of these two worlds is just a dream!</p><p><strong>Now</strong></p><p>Simulation enables ATG to test our self-driving technology through common scenarios in a virtual world before it reaches real-world roadways. It allows us to quickly and continuously improve the self-driving system’s ability to <a href="https://medium.com/@UberATG/simulation-the-invisible-gatekeeper-e6ef84ea7647">drive, anticipate, and react safely</a>.</p><p>There are thousands of such scenarios, and each scenario can create thousands of variations with even the slightest modification — for example, changing the speed of an oncoming bicycle or the initial position of a pedestrian. As a result, millions of simulations are run on a regular basis, generating enormous amounts of data to analyze.</p><p>One of our roles in the Data Science team is to build statistical models, machine-learning algorithms, and data visualization products that can extract value from this large amount of simulation data. These efforts help autonomy engineers make the most of simulations and quickly iterate on the self-driving software, and help simulation engineers optimize specific aspects of our simulation technology.</p><p><strong>Next</strong></p><p>Simulation is just one data source among many in the self-driving world! We collect sensor data coming from vehicles driving on the track and on the road, data coming from our mapping efforts, data coming from software behavior, test data coming from our verification and validation procedures. A key challenge for the ATG Data Science Team is to connect the dots between all these data sources to get valuable insights and answer the difficult open questions for different teams across ATG, including safety, autonomy engineering, and leadership teams.</p><p><strong>Future</strong></p><p>I am super-excited by the fact that self-driving technology will make cities safer and better places to live. In particular, coupled with public transit and new modes of transportation like shared bikes and scooters, shared electric self-driving vehicles will allow us to get more people into fewer cars and reduce the public cost of individual car ownership. In some cities, 30% of the land — and sometimes the buildings — are dedicated to parking cars that are idle 95% of the time. With self-driving technology, we’ll have fewer idly parked cars, more park space, less time in traffic, more time with friends and families, and of course far fewer road accidents. More than 1.3 million people die in car accidents each year in the world, of which 95% were caused by a human error. We can change that.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*NuNXhTTUgpWzbs9SdZ3o4Q.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=2373378afe98" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Hello, Texas!]]></title>
            <link>https://medium.com/@UberATG/hello-texas-85630e7d7974?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/85630e7d7974</guid>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[uber]]></category>
            <category><![CDATA[self-driving]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Tue, 17 Sep 2019 15:57:11 GMT</pubDate>
            <atom:updated>2019-09-17T15:57:11.178Z</atom:updated>
            <content:encoded><![CDATA[<p><strong><em>Data collection beginning in downtown Dallas</em></strong></p><p>By: Austin Geidt, Head of Uber ATG Strategy</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*4ztaGNnro4LNYWv-dBy9eg.jpeg" /></figure><p>We’re on a mission to deliver safe self-driving technology to Uber riders around the world. Uber Advanced Technologies Group has already started this journey in Pittsburgh, San Francisco, and Toronto. Today, we’re adding another city to <a href="https://www.uber.com/us/en/atg/cities/"><strong>that list</strong></a> 一 Dallas, TX.</p><p>The City of Dallas has been an exceptional partner to Uber as we continue to expand mobility options for our riders and economic opportunities for restaurants. Dallas users on our platform have many of Uber’s US-based offerings at their fingertips: shared rides, Uber Eats, JUMP scooters, Transit, Uber Freight, and more. Dallas also offers us the opportunity to explore a different type of road network for our self-driving technology. The city’s modern infrastructure, unique traffic patterns, road characteristics, and climate will offer new information that can inform our ongoing engineering efforts.</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/640/1*sACDmiy1E5gI0lVFa151cA.gif" /></figure><p>Starting in early November, we will begin manual driving 一 meaning a Mission Specialist (a specially trained vehicle operator) will maintain control of the vehicle at all times 一 in downtown Dallas, TX.</p><p><strong>This manual data collection allows us to:</strong></p><ul><li>Develop high-definition maps, the foundational information layer for our self-driving system.</li><li>Capture everyday scenarios that we can then recreate in simulation and on our test track.</li><li>Further refine our expansion methodology, which involves identifying key characteristics within an operational domain in a new city, and then running that data through our autonomy system in <a href="https://www.youtube.com/watch?v=U6C0CiSR35Y"><strong>simulation</strong></a> and on our <a href="https://www.youtube.com/watch?v=0E5IQJj_oKY"><strong>test track</strong></a> to verify that our autonomy system, if it were on a road, would perform as intended.</li></ul><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*697NvSnJ5uxd9f1miNyeTA.jpeg" /></figure><p>Manual data collection is the first step in our development process and key to validating our expansion approach. The data we collect will inform our next steps — we may not look to test our self-driving system in Dallas immediately following this first round of data gathering. While we are certainly excited by this possibility, we are also committed to ensuring that every mile we drive on public roads contributes meaningfully to our development work.</p><p>Should we look to operate our vehicles autonomously after the initial data collection phase is complete, we’ll work closely with stakeholders at both the local and state level. In the meantime, we are eager to kick-off public engagement with the Dallas community, as well as key organizations and stakeholders, to both educate and generate awareness for efforts that will soon be underway in Dallas.</p><p>The Uber network is a powerful thing. It brings people closer to the things they need, and self-driving technology has the potential to create even more value to our users. In order to arrive at that future, we must approach building this technology thoughtfully and with a strong sense of responsibility to the communities where we operate, which our team is dedicated to doing everyday.</p><p>Dallas, we’ll see you in November!</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=85630e7d7974" width="1" height="1" alt="">]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Now, Next, and Future: Tara Stentz]]></title>
            <link>https://medium.com/@UberATG/now-next-and-future-tara-stentz-79890f8f8d01?source=rss-4275c7808cea------2</link>
            <guid isPermaLink="false">https://medium.com/p/79890f8f8d01</guid>
            <category><![CDATA[tech]]></category>
            <category><![CDATA[technology]]></category>
            <category><![CDATA[autonomous-cars]]></category>
            <category><![CDATA[self-driving-cars]]></category>
            <category><![CDATA[careers]]></category>
            <dc:creator><![CDATA[UberATG]]></dc:creator>
            <pubDate>Fri, 16 Aug 2019 16:58:28 GMT</pubDate>
            <atom:updated>2019-08-16T16:58:28.149Z</atom:updated>
            <content:encoded><![CDATA[<p><em>A profile series that introduces our team and showcases what we’re working on.</em></p><figure><img alt="" src="https://cdn-images-1.medium.com/max/621/1*FRnL_jKY3A5DhaHtzw41lA.jpeg" /></figure><p>My name is Tara Stentz, and I am a Software Engineer on the Prediction Team!<em> </em>I graduated in 2018 from Carnegie Mellon University with a degree in Electrical and Computer Engineering and a minor in Computer Science. For the summer of 2017, I was looking for an internship that had the feel of a smaller company, even if it was housed within a bigger organization. I was also hoping to get experience in software development, robotics, and machine learning. Uber ATG was the perfect fit! My team made sure I felt my contributions were valuable even though I was “just an intern,” and I enjoyed being immersed in this fast-paced, deeply innovative field.</p><p>I started as a full-time employee in September of 2018. I have enjoyed my time here even more because I’ve gotten to work on some really exciting projects.</p><p><strong>Now</strong></p><p>The Prediction Team is involved in the “brain” of the self-driving car, and we are responsible for determining what the dynamic objects in a scene, like other vehicles, might do next. This is a very hard problem to solve because, to ensure the safety of our vehicles, we must anticipate harmful events before they occur — on time and every time.</p><p>I really enjoy working on the Prediction Team because we’re in the middle of the autonomy pipeline. It’s fun to work with teams both upstream, like Perception (what the car sees), and downstream, like Motion Planning (what the car does next).</p><p><strong>Next</strong></p><p>Evaluating the effectiveness of our Prediction system is a huge challenge. The hard part is defining what it means to have a “good” Prediction system, then designing a metric or set of metrics so we can measure it. However, it’s a very important part of the work we do. We have to understand how and where our predictions could perform better so we can continue to improve them.</p><p><strong>Future</strong></p><p>I truly think this technology will make the world a safer place. Way too many people are killed each year in accidents caused by human error. In addition, I’m excited about the potential for positive environmental impact. If we had a fleet of self-driving cars operating on the streets, think of all the parking lots we could turn into parks!</p><p>And as a final funny story, I once went to an elementary school to talk about self-driving, and it made me so excited to hear the students’ ideas about a world with only self-driving vehicles. One of my favorite suggestions from the group was to make an ice cream parlor within a self-driving car. Sign me up for that!</p><figure><img alt="" src="https://cdn-images-1.medium.com/max/1024/1*yufYBf5DUWad9mJUdmKywg.jpeg" /></figure><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=79890f8f8d01" width="1" height="1" alt="">]]></content:encoded>
        </item>
    </channel>
</rss>