<?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[Autonomous Systems - Medium]]></title>
        <description><![CDATA[A blog about autonomous systems and artificial intelligence. - Medium]]></description>
        <link>https://medium.com/autonomous-systems?source=rss----8ce91ec8fb7b---4</link>
        <image>
            <url>https://cdn-images-1.medium.com/proxy/1*TGH72Nnw24QL3iV9IOm4VA.png</url>
            <title>Autonomous Systems - Medium</title>
            <link>https://medium.com/autonomous-systems?source=rss----8ce91ec8fb7b---4</link>
        </image>
        <generator>Medium</generator>
        <lastBuildDate>Mon, 16 Nov 2026 05:16:47 GMT</lastBuildDate>
        <atom:link href="https://medium.com/feed/autonomous-systems" rel="self" type="application/rss+xml"/>
        <webMaster><![CDATA[yourfriends@medium.com]]></webMaster>
        <atom:link href="http://medium.superfeedr.com/" rel="hub"/>
        <item>
            <title><![CDATA[Valet Parking]]></title>
            <link>https://medium.com/autonomous-systems/valet-parking-3e4fc2c8beec?source=rss----8ce91ec8fb7b---4</link>
            <guid isPermaLink="false">https://medium.com/p/3e4fc2c8beec</guid>
            <dc:creator><![CDATA[Klemens Esterle]]></dc:creator>
            <pubDate>Fri, 25 May 2018 15:39:19 GMT</pubDate>
            <atom:updated>2018-05-25T15:39:18.583Z</atom:updated>
            <content:encoded><![CDATA[<img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=3e4fc2c8beec" width="1" height="1" alt=""><hr><p><a href="https://medium.com/autonomous-systems/valet-parking-3e4fc2c8beec">Valet Parking</a> was originally published in <a href="https://medium.com/autonomous-systems">Autonomous Systems</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
        <item>
            <title><![CDATA[Motion Planning in Autonomous Driving]]></title>
            <link>https://medium.com/autonomous-systems/motion-planning-in-autonomous-driving-5fa568f31e81?source=rss----8ce91ec8fb7b---4</link>
            <guid isPermaLink="false">https://medium.com/p/5fa568f31e81</guid>
            <category><![CDATA[self-driving-cars]]></category>
            <dc:creator><![CDATA[Patrick Hart]]></dc:creator>
            <pubDate>Fri, 25 May 2018 15:13:42 GMT</pubDate>
            <atom:updated>2018-05-25T15:50:54.859Z</atom:updated>
            <content:encoded><![CDATA[<p><em>Written by: </em><a href="https://medium.com/u/43dfcabbf257"><em>Patrick Hart</em></a><em>, </em><a href="https://medium.com/u/83c7d4d59eaa"><em>Klemens Esterle</em></a></p><p>Motion planning is one of the core aspects in autonomous driving, but companies like Waymo and Uber keep their planning methods a well guarded secret. A motion planner can be seen as the entity that tells the vehicle where to go.</p><p>There are several ways to plan a motion for an autonomous vehicle. Classic motion planning techniques can mainly be classified into</p><ul><li>Optimization-based,</li><li>Interpolation-based</li><li>and Search-based</li></ul><p>methods. All of the above mentioned methods have been applied in autonomous vehicles. In the DARPA-Challenge in 2008, Dolgov et. al. have designed an autonomous vehicle that uses search- and interpolation-based methods. Moreover, the Bertha-Benz Memorial Drive, conducted by Daimler used an optimization-based planning approach. This raises a couple of questions:</p><ul><li>What are the advantages of these individual algorithm groups?</li><li>Are these methods sufficient (or do we need machine learning)?</li></ul><p>The questions above are not easy or possible to answer in a general manner. The already existing methods are capable of planning a motion based on kinematics, but they might not neccessarily be able to handle situations that, for example, require interactions or situations that have not been foreseen in the design phase. In these cases, machine learning could provide essential benefits as it is capable to learn from data, especially, real-world situations.</p><p>Therefore, a lot of research has been conducted recently using machine learning in oder to plan the motion of autonomous vehicles. Especially, reinforcement learning seems to be a promising method as the agent is able to learn which actions are good (reward) or negative. However, the research is not only limited to reinforcement learning, but now also includes Generative Adversarial Networks (GANs), supervised- and even unsupervised learning.</p><img src="https://medium.com/_/stat?event=post.clientViewed&referrerSource=full_rss&postId=5fa568f31e81" width="1" height="1" alt=""><hr><p><a href="https://medium.com/autonomous-systems/motion-planning-in-autonomous-driving-5fa568f31e81">Motion Planning in Autonomous Driving</a> was originally published in <a href="https://medium.com/autonomous-systems">Autonomous Systems</a> on Medium, where people are continuing the conversation by highlighting and responding to this story.</p>]]></content:encoded>
        </item>
    </channel>
</rss>