Händelser: Data- och informationsteknikhttp://www.chalmers.se/sv/om-chalmers/kalendariumAktuella händelser på Chalmers tekniska högskolaFri, 21 Jan 2022 14:12:37 +0100http://www.chalmers.se/sv/om-chalmers/kalendariumhttps://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/licentiate-seminar-Tobias-Johansson.aspxhttps://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/licentiate-seminar-Tobias-Johansson.aspxTobias Johansson, Data- och informationsteknik<p>Online seminar</p><p>​Machine Learning Based Methods for Virtual Validation of Autonomous Driving</p>During the last decade, automotive manufacturers have introduced increasingly capable driving automation functions in consumer vehicles. As the functionality becomes more advanced, the task of driving moves from the human to the car. Hence, making sure that autonomous driving (AD) functions are reliable and safe is of high importance. Often, increased levels of automation result in more complex safety validation procedures, that may be both expensive, time consuming, and dangerous to perform. One way to address these problems is to move parts of the validation to the virtual domain.<br /><br /> In this thesis, we investigate methods for validating AD functionality in virtual simulation environments, using methods from machine learning and statistics. The main focus is on how to make virtual simulations resemble real-world conditions as closely as possible. We tackle this with an approach based on sensor error modeling. Specifically, we develop a statistical sensor error model that can be used to make ideal object measurements from simulations resemble measurements obtained from the perception system of a real-world vehicle. The model, which is based on autoregressive recurrent mixture density networks, was trained on sensor error data collected on European roads.<br /><br /> The second part considers system falsification using reinforcement learning (RL); a flexible framework for validation of system safety, which naturally allows for the integration of, e.g., sensor error models. We compare results of system falsification using RL to an exact approach based on reachability analysis.<br /><br /> With this thesis, we take steps towards more realistic statistical sensor error models for virtual simulation environments. We also demonstrate that approximate methods based on reinforcement learning may serve as an alternative to reachability analysis for validation of high-dimensional systems. Finally, we connect the RL falsification application to sensor error modeling as a possible direction for future research.https://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/licentiate-seminar-Emil-Carlsson.aspxhttps://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/licentiate-seminar-Emil-Carlsson.aspxEmil Carlsson, Data- och informationsteknik<p>Online</p><p>​Efficient Communication via Reinforcement Learning</p>Why do languages partition mental concepts into words the way the do? Recent works have taken a information-theoretic view on human language and suggested that it is shaped by the need for efficient communication. This means that human language is shaped by a simultaneous pressure for being informative, while also being simple in order to minimize the cognitive load. <br /><br />In this thesis we combine the information-theoretic perspective on language with recent advances in deep multi-agent reinforcement learning. We explore how efficient communication emerges between two artificial agents in a signaling game as a by-product of them maximizing a shared reward signal. This is tested in the domain of colors and numeral systems, two domains in which human languages tends to support efficient communication. We find that the communication developed by the artificial agents in these domains shares characteristics with human languages when it comes to efficiency and structure of semantic partitions. even though the agents lack the full perceptual and linguistic architecture of humans.<br /><br /> Our results offer a computational learning perspective that may complement the information-theoretic view on the structure of human languages. The results also suggests that reinforcement learning is a powerful and flexible framework that can be used to test and generate hypotheses in silico.https://www.chalmers.se/sv/styrkeomraden/energi/kalendarium/Sidor/Batteriproduktion-i-stor-skala-miljovinster-och-nya-utmaningar.aspxhttps://www.chalmers.se/sv/styrkeomraden/energi/kalendarium/Sidor/Batteriproduktion-i-stor-skala-miljovinster-och-nya-utmaningar.aspxBatteriproduktion i stor skala — miljövinster och nya utmaningar<p>OOTO Café, café, Sven Hultins Plats 2, Johanneberg Science Park 2</p><p>​OBS! På grund av pandemin så håller vi seminariet på nytt datum och tid.  Den 28  januari är vi tillbaka efter julledigheten med säsongens första Fredagsseminarium &amp; afterwork. Välkomna!Plats: Kafé Ooto, Guldhuset, Johanneberg Science Park, kl 12:30-14.00.  Den här gången bjuder vi in till ett seminarium om ett hett ämne: Batteriproduktion i stor skala — miljövinster och nya utmaningar.</p>​<span style="background-color:initial">Utmaningen med batteriproduktion och elektrifieringen är många. Använder fabriken som producerar batterierna förnyelsebar energi eller inte, en annan är tillgången på metaller och vilken roll återvinningen har.</span><div><br /></div> <div>Eftermiddagen startar med ett kort seminarium av Anders Nordelöf, med livscykelanalys som verktyg forskar om miljöaspekterna av elektrifierad vägtrafik för att stötta utvecklingen av fordon med minskad miljöbelastning. <br />Anders Nordelöf är temaledare för forskningsområdet Elektromobilitet i samhället inom Swedish Electromobility Centre, ett nationellt kompetenscentrum för elektromobilitet där Chalmers är värduniversitet. Han har även delat ansvar för Chalmers profilområde Hållbara fordonsteknologier.</div> <div><br /></div> <div><span style="background-color:initial">Så </span><span style="background-color:initial">kom, lyssna, och träffa kollegor, och diskutera nya forskningsidéer och nyheter inom området.</span><br /></div> <div><span style="background-color:initial"><br /></span></div> <div><span style="background-color:initial"><div><b>För att vi ska kunna hålla avstånd och slippa trängas så ser vi gärna att ni anmäler er till seminariet.</b></div> <div><a href="https://ui.ungpd.com/Surveys/1adad28e-3b4f-4521-af83-182bce00c2ea"><img class="ms-asset-icon ms-rtePosition-4" src="/_layouts/images/icgen.gif" alt="" />Anmäl dig här​</a></div></span></div> <div><br /></div> <div><b>Program</b></div> <div><ul><li>12:30, Välkommen Tomas Kåberger, Chalmers styrkeområde Energi.</li> <li>Batteriproduktion i stor skala — miljövinster och nya utmaningar, Anders Nordelöf, forksare vid Teknikens ekonomi och organisation, Chalmers.</li> <li>Fr<span style="background-color:initial">ågestund.</span></li> <li>13<span style="background-color:initial">:05-14:00, Mingel.</span></li></ul></div> <div><b><br /></b></div> <div><b>RELATERAT: </b><br /><a href="/sv/styrkeomraden/energi/nyheter/Sidor/EUs-arbete-for-elektrifiering-av-transportsektorn.aspx" style="background-color:rgb(255, 255, 255);outline:0px"><img class="ms-asset-icon ms-rtePosition-4" src="/_layouts/images/ichtm.gif" alt="" />​</a><a href="https://www.di.se/hallbart-naringsliv/atervinning-en-not-att-knacka-for-elbilar/">Återvinning — en nöt att knäcka för elbilar</a><br /><a href="/sv/styrkeomraden/energi/nyheter/Sidor/EUs-arbete-for-elektrifiering-av-transportsektorn.aspx"><img class="ms-asset-icon ms-rtePosition-4" src="/_layouts/images/ichtm.gif" alt="" />Bidrar till EU:s arbete för elektrifiering av transportsektorn</a><br /></div> <div><a href="https://emobilitycentre.se/energy-management-is-the-main-focus-of-our-research/"><img class="ms-asset-icon ms-rtePosition-4" src="/_layouts/images/icgen.gif" alt="" />Swedish Electromobility Centre<br /><span style="font-weight:300"></span></a><span style="background-color:initial"><font color="#1166aa"><a href="/sv/styrkeomraden/transport/profilomraden/Sidor/Hallbara-fordonsteknologier.aspx"><img class="ms-asset-icon ms-rtePosition-4" src="/_layouts/images/ichtm.gif" alt="" />Hållbara fordonsteknologier​</a></font></span><br /></div> ​https://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/thesis-defence-Iulia-Bastys.aspxhttps://www.chalmers.se/sv/institutioner/cse/kalendarium/Sidor/thesis-defence-Iulia-Bastys.aspxIulia Bastys, Data- och informationsteknik<p>Online</p><p>​Principled Flow Tracking in IoT and Low-Level Applications</p><br /><div>Significant fractions of our lives are spent digitally, connected to and dependent on Internet-based applications, be it through the Web, mobile, or IoT. All such applications have access to and are entrusted with private user data, such as location, photos, browsing habits, private feed from social networks, or bank details.</div> <br /> In this thesis, we focus on IoT and Web(Assembly) apps. We demonstrate IoT apps to be vulnerable to attacks by malicious app makers who are able to bypass the sandboxing mechanisms enforced by the platform to stealthy exfiltrate user data. We further give examples of carefully crafted WebAssembly code abusing the semantics to leak user data.<br /><br /> We are interested in applying language-based technologies to ensure application security due to the formal guarantees they provide. Such technologies analyze the underlying program and track how the information flows in an application, with the goal of either statically proving its security, or preventing insecurities from happening at runtime. As such, for protecting against the attacks on IoT apps, we develop both static and dynamic methods, while for securing WebAssembly apps we describe a hybrid approach, combining both.<br /><br /> While language-based technologies provide strong security guarantees, they are still to see a widespread adoption outside the academic community where they emerged. In this direction, we outline six design principles to assist the developer in choosing the right security characterization and enforcement mechanism for their system. We further investigate the relative expressiveness of two static enforcement mechanisms which pursue fine- and coarse-grained approaches for tracking the flow of sensitive information in a system. Finally, we provide the developer with an automatic method for reducing the manual burden associated with some of the language-based enforcements.