BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//WASP - ECPv6.16.3//NONSGML v1.0//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
X-ORIGINAL-URL:https://wasp-sweden.org
X-WR-CALDESC:Events for WASP
REFRESH-INTERVAL;VALUE=DURATION:PT1H
X-Robots-Tag:noindex
X-PUBLISHED-TTL:PT1H
BEGIN:VTIMEZONE
TZID:+01:00
END:VTIMEZONE
BEGIN:VEVENT
DTSTART;TZID=+01:00:20210212T000000
DTEND;TZID=+01:00:20210212T235959
DTSTAMP:20260602T135701
CREATED:20201216T074711Z
LAST-MODIFIED:20260601T083910Z
UID:10000324-1613088000-1613174399@wasp-sweden.org
SUMMARY:PhD Defense: Digital Cognitive Companions for Marine Vessels - On the Path Towards Autonomous Ships
DESCRIPTION:Thesis title: Digital Cognitive Companions for Marine Vessels – On the Path Towards Autonomous Ships \nAuthor: Mårten Lager\, Department of Computer Science\, Lund university \nFaculty opponent: Professor Henrik I. Christensen\, University of California\, USA \nLocation: Online – link by registration
URL:https://wasp-sweden.org/event/phd-defense-digital-cognitive-companions-for-marine-vessels-on-the-path-towards-autonomous-ships/
LOCATION:Online\, Online\, Other
CATEGORIES:Defense
ATTACH;FMTTYPE=image/png:https://wasp-sweden.org/wp-content/uploads/2020/12/PhD-Defense-MårtenLager.png
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20210201T140000
DTEND;TZID=+01:00:20210201T235900
DTSTAMP:20260602T135701
CREATED:20210127T103456Z
LAST-MODIFIED:20260601T083909Z
UID:10000320-1612188000-1612223940@wasp-sweden.org
SUMMARY:Lic. Thesis Seminar: Adaptiveness and Lock-free Synchronization in Parallel Stochastic Gradient Descent
DESCRIPTION:Lic. thesis seminar \nFebruary 1\, 14.00 via zoom \nKarl Bäckström\, Computer Science and Engineering\, Chalmers University of Technology\, will present his lic thesis Adaptiveness and Lock-free Synchronization in Parallel Stochastic Gradient Descent. \n 
URL:https://wasp-sweden.org/event/lic-thesis-seminar-adaptiveness-and-lock-free-synchronization-in-parallel-stochastic-gradient-descent/
LOCATION:Online\, Online\, Other
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20210129T131500
DTEND;TZID=+01:00:20210129T235900
DTSTAMP:20260602T135701
CREATED:20210112T114937Z
LAST-MODIFIED:20260601T083909Z
UID:10000322-1611926100-1611964740@wasp-sweden.org
SUMMARY:Lic. Thesis Seminar: Integration of Clouds to Industrial Communication Networks
DESCRIPTION:Title: Integration of Clouds to Industrial Communication Networks \nPresenter: Haorui Peng\, Electrical and Information Technology\, LTH\, Lund University and Wallenberg AI\, Autonomous Systems and Software Program (WASP) \nReviewer: Prof. Åke Arvidsson från Kristianstad University \nWhen: 29 January 2021 at 13.15 \nLocation: Online at the zoom platform. Please register at https://www.lth.se/digitalth/events/register-2021-01-29/ in order to get an access link. \nAbstract\nCloud computing\, owing to its ubiquitousness\, scalability and on-demand ac- cess\, has transformed into many traditional sectors\, such as telecommunication and manufacturing production. As the Fifth Generation Wireless Specifications (5G) emerges\, the demand on ubiquitous and re-configurable computing resources for handling tremendous traffic from omnipresent mobile devices has been put forward. And therein lies the adaption of cloud-native model in service delivery of telecommunication networks. However\, it takes phased approaches to successfully transform the traditional Telco infrastructure to a softwarized model\, especially for Radio Access Networks (RANs)\, which\, as of now\, mostly relies on purpose-built Digital Signal Processors (DSPs) for computing and processing tasks. \nOn the other hand\, Industry 4.0 is leading the digital transformation in manufacturing sectors\, wherein the industrial networks is evolving towards wireless connectivity and the automation process managements are shifting to clouds. However\, such integration may introduce unwanted disturbances to critical industrial automation processes. This leads to challenges to guaran- tee the performance of critical applications under the integration of different systems. \nIn the work presented in this thesis\, we mainly explore the feasibility of inte- grating wireless communication\, industrial networks and cloud computing. We have mainly investigated the delay-inhibited challenges and the performance impacts of using cloud-native models for critical applications. We design a solution\, targeting at diminishing the performance degradation caused by the integration of cloud computing.
URL:https://wasp-sweden.org/event/lic-thesis-seminar-integration-of-clouds-to-industrial-communication-networks/
LOCATION:Online\, Online\, Other
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20210127T000000
DTEND;TZID=+01:00:20210127T235959
DTSTAMP:20260602T135701
CREATED:20201218T072742Z
LAST-MODIFIED:20260601T083910Z
UID:10000323-1611705600-1611791999@wasp-sweden.org
SUMMARY:Webinar: WASP Industrial PhD Student Call
DESCRIPTION:Interested in WASP’s upcoming Industrial PhD Student call? Join our webinar to learn more! \nWASP invites everyone interested in the upcoming WASP Industrial PhD Student Call to an information webinar on January 27th\, 2021\, 13:15-15:15. The webinar will be held through Zoom. If you wish to attend\, please register through the link below. You will receive a meeting invitation a couple of days before the webinar. \nAbout the WASP Industrial PhD Student Call\nWASP is offering up to 10 industrial doctoral student positions within AI\, Autonomous Systems and Software at the five partner universities Chalmers\, KTH\, Linköping University\, Lund University and Umeå University as well as the research groups at Örebro University and Uppsala University that are members of WASP AI. The industrial partner should have research activities in Sweden. \nThe projects are expected to address fundamental research problems within any of WASP’s research areas and expect to have a strong visionary and novelty nature\, i.e.\, not only application development. The call opens January 25th\, 2021. \nWASP industrial PhD students will be part of the WASP graduate school. The graduate school is making efforts to actively attract industrial PhD students. To make the industrial PhD studies relevant to companies\, courses offered in the program are tailored to meet the future needs in industry. \nAbout Industrial PhD studies\nIn our Industrial PhD Report\, an overall comment from the editors is the possibilities for industry to think of industrial PhD students as a strategic instrument. The main types of results for participating industry are partly concrete in the form of research results and a doctoral degree but also\, as shown in recent research\, participating industries improve their overall innovation capability.
URL:https://wasp-sweden.org/event/webinar-wasp-industrial-phd-student-call/
LOCATION:Online\, Online\, Other
CATEGORIES:Webinar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20201210T150000
DTEND;TZID=+01:00:20201210T235900
DTSTAMP:20260602T135701
CREATED:20201113T114820Z
LAST-MODIFIED:20260601T083911Z
UID:10000325-1607612400-1607644740@wasp-sweden.org
SUMMARY:Autonomous Vehicle Maneuvering at the Limit of Friction
DESCRIPTION:Title: Autonomous Vehicle Maneuvering at the Limit of Friction\nRespondent: Victor Fors\nDivision: Vehicular Systems at the Department of Electrical Engineering\, Linköping University\nSupervisors: Lars Nielsen\, Björn Olofsson\, Jan Åslund\nOpponent: Professor J. Christian Gerdes\, Department of Mechanical Engineering\, Stanford University\, CA\, US\nDate and time: 2020-12-10\, 15:00\nPlace: Online via Zoom (can be viewed in Ada Lovelace\, B-building\, Campus Valla\, Linköping University) \nJoin Zoom Meeting https://liu-se.zoom.us/j/65015486154?pwd=eFhNMHFkcTNMOGNNQ1NZUWplV3MvZz09 \nAbstract: \nWithout a driver to fall back on\, a fully self-driving car needs to be able to handle any situation it can encounter. With the perspective of future safety systems\, this research studies autonomous maneuvering at the tire–road friction limit. In these situations\, the dynamics is highly nonlinear\, and the tire–road parameters are uncertain. \nTo gain insights into the optimal behavior of autonomous safety-critical maneuvers\, they are analyzed using optimal control. Since analytical solutions of the studied optimal control problems are intractable\, they are solved numerically. An optimization formulation reveals how the optimal behavior is influenced by the total amount of braking. By studying how the optimal trajectory relates to the attainable forces throughout a maneuver\, it is found that maximizing the force in a certain direction is important. This is like the analytical solutions obtained for friction-limited particle models in earlier research\, and it is shown to result in vehicle behavior close to the optimal also for a more complex model. \nBased on the insights gained from the optimal behavior\, controllers for autonomous safety maneuvers are developed. These controllers are based on using acceleration-vector references obtained from friction-limited particle models. Exploiting that the individual tire forces tend to be close to their friction limits\, the desired tire slip angles are determined for a given acceleration-vector reference. This results in controllers capable of operating at the limit of friction at a low computational cost and reduces the number of vehicle parameters used. For straight-line braking\, ABS can intervene to reduce the braking distance without prior information about the road friction. Inspired by this\, a controller that uses the available actuation according to the least friction necessary to avoid a collision is developed\, resulting in autonomous collision avoidance without any estimation of the tire–road friction. \nInvestigating time-optimal lane changes\, it is found that a simple friction-limited particle model is insufficient to determine the desired acceleration vector\, but including a jerk limit to account for the yaw dynamics is sufficient. To enable a tradeoff between braking and avoidance with a more general obstacle representation\, the acceleration-vector reference is computed in a receding-horizon framework. \nThe controllers developed in this thesis show great promise with low computational cost and performance not far from that obtained offline by using numerical optimization when evaluated in high-fidelity simulation.
URL:https://wasp-sweden.org/event/autonomous-vehicle-maneuvering-at-the-limit-of-friction/
LOCATION:Online\, Online\, Other
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20201130T123000
DTEND;TZID=+01:00:20201201T235900
DTSTAMP:20260602T135701
CREATED:20200206T120505Z
LAST-MODIFIED:20260601T083914Z
UID:10000334-1606739400-1606867140@wasp-sweden.org
SUMMARY:WASP Virtual Industry Meeting 2020
DESCRIPTION:We invite industry\, WASP researchers and WASP PhD students for two virtual days of research ideas exchanges and networking. \nThis is a two-day event with the purpose to identify\, initiate and catalyze exchanges and collaborations between WASP researchers and industry*. \nDay one is devoted to addressing business and industry challenge driven research problems in scientific thematic discussions between WASP researchers and researchers from the industry*. The second day is a job fair where participating companies are invited to sign up for short meetings with WASP PhD students to inspire and engage in career discussions. \n*Swedish Industry with R&D operations in Sweden. \nTimeline\nOctober 1st Registration opens \nOctober 30th Registration deadline\nNovember 6th Participation will be confirmed\nNovember 25th Deadline for industry representatives to book time slots with PhD students (a separate invitation will be sent out during week 47)
URL:https://wasp-sweden.org/event/wasp-virtual-industry-meeting-2020/
LOCATION:Online\, Online\, Other
CATEGORIES:Conference
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2020/02/Industrymeeting_new_virtual_basic.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20201105T100000
DTEND;TZID=+01:00:20201105T235900
DTSTAMP:20260602T135701
CREATED:20200305T115145Z
LAST-MODIFIED:20260601T083913Z
UID:10000331-1604570400-1604620740@wasp-sweden.org
SUMMARY:WASP4ALL 2020 - Virtual Worlds for Artificial Intelligence
DESCRIPTION:Are you looking for WASP4ALL 2021? Click here. \nOur flagship conference WASP4ALL this year presents high-profile international speakers\, and researchers from WASP and Swedish industry on the topic “Virtual Worlds for Artificial Intelligence”. \nTogether we will explore how simulation and artificially generated environments can facilitate machine learning and other AI-development. If you are interested in technology\, methods\, challenges and problems – this is a conference you don’t want to miss! \nThe conference is an open\, virtual conference\, not limited to the WASP community. \nThe number of participants is limited – first come-first serve \n  \n\nWASP\, the Wallenberg AI\, Autonomous Systems and Software Program is the largest research program in Sweden ever. WASP4ALL is our yearly flagship conference with 400+ participants from academia and industry. 
URL:https://wasp-sweden.org/event/wasp4all-2020-virtual-worlds-for-artificial-intelligence/
LOCATION:Online\, Online\, Other
CATEGORIES:Conference
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2020/03/huvudbild_virtual-worlds-for-artificial-intelligence_v2_final.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20201013T130000
DTEND;TZID=+01:00:20201014T235900
DTSTAMP:20260602T135701
CREATED:20200924T075931Z
LAST-MODIFIED:20260601T083911Z
UID:10000326-1602594000-1602719940@wasp-sweden.org
SUMMARY:First WASP Workshop on Large-Scale Optimization for Autonomy
DESCRIPTION:The First WASP Workshop on Large-Scale Optimization for Autonomy and Learning (LSOAL) will be held October 13-14\, 2020 at KTH. It will be arranged as a hybrid conference\, where those who prefer can attend via a Zoom Webinar. There will be a strict limit on the number of participants on-site. \nWe are looking forward to an exciting workshop where we can exchange ideas on large-scale optimization from theory to applications. The workshop is not limited to autonomy and learning\, but we expect a strong interest in this area. \n  \nWelcome\, \nBo Wahlberg (KTH) and Anders Hansson (LiU) \n\n 
URL:https://wasp-sweden.org/event/first-wasp-workshop-on-large-scale-optimization-for-autonomy/
LOCATION:Online\, Online\, Other
CATEGORIES:Workshop
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200914T130000
DTEND;TZID=+01:00:20200917T235900
DTSTAMP:20260602T135701
CREATED:20200225T102618Z
LAST-MODIFIED:20260601T083913Z
UID:10000332-1600088400-1600387140@wasp-sweden.org
SUMMARY:WARA-PS Field Test and Data Collection
DESCRIPTION:Original location: Gränsö slott\, Västervik
URL:https://wasp-sweden.org/event/wara-ps-field-test-and-data-collection/
LOCATION:Gränsö Slott\, Västervik\, Gränsö Slott\, Västervik\, Västervik\, Sweden
CATEGORIES:Workshop
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2019/11/32454_WASPVastervik2019094KDJI_0679MP400_00_23_06Still002_50045_12-1024x576.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200821T000000
DTEND;TZID=+01:00:20200821T235959
DTSTAMP:20260602T135701
CREATED:20200507T083024Z
LAST-MODIFIED:20260601T083911Z
UID:10000327-1597968000-1598054399@wasp-sweden.org
SUMMARY:Veronika Domova – Designing Visualization and Interaction for Industrial Control Rooms of the Future
DESCRIPTION:Location to be decided. \nTentative abstract: \nDuring the last decades\, the industry has been undergoing extensive digitization leading to complex ensembles of humans\, machines\, autonomous agents\, and sensors. With this new setup comes the challenge of how to appropriately support work-practices of industrial operators who now need to monitor and control complex industrial processes through remote interfaces. Information overflow and restrictive interfaces are two significant problems that operators face in their daily routines. In this PhD\, I explore approaches to visualization and interaction that would reduce industrial operators’ information load and enable them to perform their duties in an efficient\, reliable\, and safe manner. The industrial user and the context are the starting points of my research. \nIn this thesis\, I describe multiple examples of custom-tailored data visualizations that reduce the operator’s visual load by consolidating large amounts of data into compact overview displays with often nontrivial data presentation. With respect to interaction\, I propose several tangible and tactile interfaces\, as well as concepts for natural interaction\, that let the user freely interact with the control station rather than be its prisoner. Finally\, I propose several concepts of adaptive systems that adjust to the operator’s context to ensure their high situational awareness and convenience of interaction. \nEven though this thesis is primarily intended for the community of interaction designers\, I expect it to be of interest to a broader audience due to its relation to the user experience field. To a certain extent\, everyone can resonate with the user’s problems because\, in our everyday life\, we all are users of some technology and services. Furthermore\, for a lay reader\, this work lifts the veil of mystery from the industrial domain and can be seen as a comprehensive introduction to how the industry works and what role the human plays there. \n  \nBetygsnämnd \nProfessor Virpi Roto\, Aalto University \nProfessor Morten Fjeld\, Chalmers \nDocent Erik Prytz\, LiU \n  \nOpponent \nProfessor Thomas Porathe\, NTNU Trondheim
URL:https://wasp-sweden.org/event/veronika-domova-designing-visualization-and-interaction-for-industrial-control-rooms-of-the-future/
LOCATION:Location TBD\, Location TBD\, Other\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200529T101500
DTEND;TZID=+01:00:20200529T235900
DTSTAMP:20260602T135701
CREATED:20200507T081432Z
LAST-MODIFIED:20260601T083912Z
UID:10000328-1590747300-1590796740@wasp-sweden.org
SUMMARY:Oskar Ljungqvist – Motion Planning and Feedback Control Techniques with Applications to Long Tractor-Trailer Vehicles
DESCRIPTION:Title: Motion planning and feedback control techniques with applications to long tractor-trailer vehicles \nRespondent: Oskar Ljungqvist\, WASP affiliated PhD student \nOpponent: Prof. Sebastien Gros \nSupervisor: Associate Prof. Daniel Axehill \nCo-supervisors: Associate Prof. Johan Löfberg \nPlace: Online via Zoom. Join Zoom Meeting https://liu-se.zoom.us/j/61330592701 Meeting ID: 613 3059 2701 Password: 300553 \nLanguage: English \nAbstract\nDuring the last decades\, improved sensor and hardware technologies as well as new methods and algorithms have made self-driving vehicles a realistic possibility in the near future. At the same time\, there has been a growing demand within the transportation sector to increase efficiency and to reduce the environmental impact related to transportation of people and goods. Therefore\, many leading automotive and technology companies have turned their attention towards developing advanced driver assistance systems and self-driving vehicles. \nAutonomous vehicles are expected to have their first big impact in closed environments\, such as mines\, harbors\, loading and offloading sites. In such areas\, the legal requirements are less restrictive and the surrounding environment is more controlled and predictable compared to urban areas. Expected positive outcomes include increased productivity and safety\, reduced emissions and the possibility to relieve the human from performing complex or dangerous tasks. Within these sites\, tractor-trailer vehicles are frequently used for transportation. These vehicles are composed of several interconnected vehicle segments\, and are therefore large\, complex and unstable while reversing. This thesis addresses the problem of designing efficient motion planning and feedback control techniques for such systems. \nThe contributions of this thesis are within the area of motion planning and feedback control for long tractor-trailer combinations operating at low-speeds in closed and unstructured environments. It includes development of motion planning and feedback control frameworks\, structured design tools for guaranteeing closed-loop stability and experimental validation of the proposed solutions through simulations\, lab and field experiments. Even though the primary application in this work is tractor-trailer vehicles\, many of the proposed approaches can with some adjustments also be used for other systems\, such as drones and ships. \nThe developed sampling-based motion planning algorithms are based upon the probabilistic closed-loop rapidly exploring random tree (CL-RRT) algorithm and the deterministic lattice-based motion planning algorithm. It is also proposed to use numerical optimal control offline for precomputing libraries of optimized maneuvers as well as during online planning in the form of a warm-started optimization step. \nTo follow the motion plan\, several predictive path-following control approaches are proposed with different computational complexity and performance. Common for these approaches are that they use a path-following error model of the vehicle for future predictions and are tailored to operate in series with a motion planner that computes feasible paths. The design strategies for the path-following approaches include linear quadratic (LQ) control and several advanced model predictive control (MPC) techniques to account for physical and sensing limitations. To strengthen the practical value of the developed techniques\, several of the proposed approaches have been implemented and successfully demonstrated in field experiments on a full-scale test platform. To estimate the vehicle states needed for control\, a novel nonlinear observer is evaluated on the full-scale test vehicle. It is designed to only utilize information from sensors that are mounted on the tractor\, making the system independent of any sensor mounted on the trailer.
URL:https://wasp-sweden.org/event/oskar-ljungqvist-motion-planning-and-feedback-control-techniques-with-applications-to-long-tractor-trailer-vehicles/
LOCATION:Online\, Online\, Other
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200526T130000
DTEND;TZID=+01:00:20200528T235900
DTSTAMP:20260602T135701
CREATED:20200225T102324Z
LAST-MODIFIED:20260601T083914Z
UID:10000333-1590498000-1590710340@wasp-sweden.org
SUMMARY:POSTPONED WARA-PS Field Test and Data Collection
DESCRIPTION:Important information \nDue to the current situation with COVID-19 we regret to inform that this event has been postponed. \n  \n  \nWe will meet and do field tests in WASP Public Safety Research Arena. Research projects will be tested and data collected. PhD students and supervisors will be invited for inspiring workshops where our core team and platforms will be available. Activities will be based on research needs and we encourage supervisors and students to contact WARA-PS with your requests and interest. More info will come. \nTime: May 26 13.00 – May 28 13.00 \nLocation: Gränsö slott\, Västervik \nOriginal location: Gränsö slott\, Västervik
URL:https://wasp-sweden.org/event/postponed-wara-ps-field-test-and-data-collection/
LOCATION:Gränsö Slott\, Västervik\, Gränsö Slott\, Västervik\, Västervik\, Sweden
CATEGORIES:Workshop
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2019/11/32454_WASPVastervik2019094KDJI_0679MP400_00_23_06Still002_50045_12-1024x576.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200429T131500
DTEND;TZID=+01:00:20200429T235900
DTSTAMP:20260602T135701
CREATED:20200406T131036Z
LAST-MODIFIED:20260601T083912Z
UID:10000329-1588166100-1588204740@wasp-sweden.org
SUMMARY:Olov Andersson – Learning to Make Safe Real-Time Decisions Under Uncertainty for Autonomous Robots
DESCRIPTION:Abstract\nRobots are increasingly expected to go beyond controlled environments in laboratories and factories\, to act autonomously in real-world workplaces and public spaces. Autonomous robots navigating the realworld have to contend with a great deal of uncertainty\, which poses additional challenges. Uncertainty in the real world accrues from several sources. Some of it may originate from imperfect internal models of reality. Other uncertainty is inherent\, a direct side effect of partial observability induced by sensor limitations and occlusions. \nRegardless of the source\, the resulting decision problem is unfortunately computationally intractable under uncertainty. This poses a great challenge as the real world is also dynamic. It will not pause while the robot computes a solution. Autonomous robots navigating among people\, for example in traffic\, need to be able to make split-second decisions. Uncertainty is therefore often neglected in practice\, with potentially catastrophic consequences when something unexpected happens. \nThe aim of this thesis is to leverage recent advances in machine learning to compute safe real-time approximations to decision-making under uncertainty for realworld robots. We explore a range of methods\, from probabilistic to deep learning\, as well as different combinations with optimization-based methods from robotics\, planning and control. Driven by applications in robot navigation\, and grounded in experiments with real autonomous quadcopters\, we address several parts of this problem. From reducing uncertainty by learning better models\, to directly approximating the decision problem itself\, all the while attempting to satisfy both the safety and real-time requirements of real-world autonomy. \n————————————————– \nThis work has been supported by the Wallenberg AI\, Autonomous Systems and Software Program\, the Swedish Foundation for Strategic Research (SSF) project Symbicloud and the ELLIIT Excellence Center at Linköping-Lund for Information Technology\, in addition to those sources already acknowledged in the individual papers. \nOriginal location: Linköping University\, Online Disputation
URL:https://wasp-sweden.org/event/olov-andersson-learning-to-make-safe-real-time-decisions-under-uncertainty-for-autonomous-robots/
LOCATION:Linköping University\, Linköping University\, Linköping\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200415T133000
DTEND;TZID=+01:00:20200415T235900
DTSTAMP:20260602T135701
CREATED:20200406T130241Z
LAST-MODIFIED:20260601T083913Z
UID:10000330-1586957400-1586995140@wasp-sweden.org
SUMMARY:Rebekka Wohlrab – Living Boundary Objects to Support Agile Inter-Team Coordination at Scale
DESCRIPTION:Context: In the last decades\, large-scale agile development has received increasing attention\, as also organizations with many stakeholders and large systems aim for higher development speed and focus on customer value. A recognized research challenge in large-scale agile development relates to inter-team coordination. To coordinate effectively\, organizations need to identify what knowledge is required across team borders and how it can be managed over time. Knowledge is potentially manifested in boundary objects – artifacts that create a shared understanding between teams (e.g.\, requirements or architecture descriptions). Traceability between artifacts is a key necessity to manage change in agile contexts. Moreover\, agile practitioners aim to reduce the documentation effort to absolutely crucial artifacts and trace links. \nObjective: This thesis aims to improve how practitioners can manage knowledge for inter-team coordination in large-scale agile development. We focus especially on how knowledge can be made explicit in artifacts and trace links that are evolved over time. \nMethod: We empirically investigated problems and developed solutions using a research approach that was inspired by design science. Case studies\, an in-depth design science study\, a mixed methods study\, and surveys were performed. Using this mix of research methods\, we leveraged both qualitative and quantitative data. \nResults: We coined the concept of living boundary objects to manage knowledge for inter-team coordination. Living boundary objects are boundary objects that are traced to other artifacts\, kept up to date\, and serve for inter-team coordination. They should be established early in the lifecycle to create a common understanding of the product to be developed. We scrutinized architecture descriptions\, interfaces\, and requirements and traceability information models as examples of concrete boundary objects. We recommend establishing alignment using a common high-level structure\, but also supporting diverse knowledge management practices to fulfill the individual needs of agile teams. \nConclusions: Our contributions help to establish knowledge management practices that are considered beneficial by practitioners and focus on the crucial aspects to align agile teams on. We suggest concepts and requirements for knowledge management tools that take the distinct role of living boundary objects into consideration and can be adjusted as organizations’ needs evolve. \nOriginal location: Online Disputation
URL:https://wasp-sweden.org/event/rebekka-wohlrab-living-boundary-objects-to-support-agile-inter-team-coordination-at-scale/
LOCATION:Online\, Online\, Other
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200207T131500
DTEND;TZID=+01:00:20200207T235900
DTSTAMP:20260602T135701
CREATED:20191220T095818Z
LAST-MODIFIED:20260601T083915Z
UID:10000336-1581081300-1581119940@wasp-sweden.org
SUMMARY:Timing-Based Localization using Multipath Information
DESCRIPTION:Degree and subject: Licentiate in Electrical Engineering with specialization in Automatic Control \nSpeaker: Andreas Bergström \nOpponent: Dr. Erik Leitinger\, TU Graz \nSupervisor: Prof. Fredrik Gustafsson \nCo-supervisors: Assoc. Prof. Gustaf Hendeby and Assoc. Prof. Fredrik Gunnarsson \nLanguage: English \nAbstract\nThe measurements of radio signals are commonly used for localization purposes where the goal is to determine the spatial position of one or multiple objects. In realistic scenarios\, any transmitted radio signal will be affected by the environment through reflections\, diffraction at edges and corners etc. This causes a phenomenon known as multipath propagation\, by which multiple instances of the transmitted signal having traversed different paths are heard by the receiver. These are known as Multi-Path Components (MPCs). The direct path (DP) between transmitter and receiver may also be occluded\, causing what is referred to as non-Line-of-Sight (non-LOS) conditions. As a consequence of these effects\, the estimated position of the object(s) may often be erroneous. \nThis thesis focuses on how to achieve better localization accuracy by accounting for the above-mentioned multipath propagation and non-LOS effects. It is proposed how to mitigate these in the context of positioning based on estimation of the DP between transmitter and receiver. It is also proposed how to constructively utilize the additional information about the environment which they implicitly provide. This is all done in a framework wherein a given signal model and a map of the surroundings are used to build a mathematical model of the radio environment\, from which the resulting MPCs are estimated. \nFirst\, methods to mitigate the adverse effects of multipath propagation and non-LOS conditions for positioning based on estimation of the DP between transmitter and receiver are presented. This is initially done by using robust statistical measurement error models based on aggregated error statistics\, where significant improvements are obtained without the need to provide detailed received signal information. The gains are seen to be even larger with up-to-date real-time information based on the estimated MPCs. \nSecond\, the association of the estimated MPCs with the signal paths predicted by the environmental model is addressed. This leads to a combinatorial problem which is approached with tools from multi-target tracking theory. A rich radio environment in terms of many MPCs gives better localization accuracy but causes the problem size to grow large — something which can be remedied by excluding less probable paths. Simulations indicate that in such environments\, the single best association hypothesis may be a reasonable approximation which avoids the calculation of a vast number of possible hypotheses. Accounting for erroneous measurements is crucial but may have drawbacks if no such are occurring. \nFinally\, theoretical localization performance bounds when utilizing all or a subset of the available MPCs are derived. A rich radio environment allows for good positioning accuracy using only a few transmitters/receivers\, assuming that these are used in the localization process. In contrast\, in a less rich environment where basically only the DP/LOS components are measurable\, more transmitters/receivers and/or the combination of downlink and uplink measurements are required to achieve the same accuracy. The receiver’s capability of distinguishing between multiple MPCs arriving approximately at the same time also affects the localization accuracy.
URL:https://wasp-sweden.org/event/timing-based-localization-using-multipath-information/
LOCATION:Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Linköping\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200124T131500
DTEND;TZID=+01:00:20200124T235900
DTSTAMP:20260602T135701
CREATED:20191216T130039Z
LAST-MODIFIED:20260601T083916Z
UID:10000337-1579871700-1579910340@wasp-sweden.org
SUMMARY:Webinar – Call for Industrial PhD Students
DESCRIPTION:Here you can see the recording of the webinar. \n  \nInterested in WASP’s upcoming Industrial PhD call within AI? Join our webinar to learn more! \nWASP invites everyone interested in the upcoming WASP AI Industrial PhD Call to an information webinar at January 24th\, 2020\, 13:15-15:00. The webinar will be held through Zoom. If you wish to attend\, please register through the link below. You will receive a meeting invitation a couple of days before the webinar. \nAbout the WASP AI Industrial PhD Call\nWASP is offering up to 15 industrial doctoral student positions within AI in 2020. The positions are offered at the five partner universities Chalmers\, KTH\, Linköping University\, Lund University and Umeå University\, as well as at the research groups at Örebro University and Uppsala University that are members of WASP AI. The projects are expected to address fundamental research problems within AI and expect to have a strong visionary and novelty nature. The call opens January 20th\, 2020. \nWASP industrial PhD students will be part of the WASP graduate school. The graduate school is making efforts to actively attract industrial PhD students. To make the industrial PhD studies relevant to companies\, courses offered in the program are tailored to meet the future needs in industry. \nAbout Industrial PhD studies\nIn our recently published Industrial PhD Report\, an overall comment from the editors is the possibilities for industry to think of industrial PhD students as a strategic instrument. The main types of results for participating industry are partly concrete in the form of research results and a doctoral degree but also\, as shown in recent research\, participating industries improve their overall innovation capability. \nWebinar Program\n\n\n\n13:15\nIntroduction by Anders Ynnerman\, Linköping University (WASP) and Danica Kragic\, KTH (WASP AI)\n\n\n13:30\nGeneral presentation about WASP Industrial PhD program\, Karl-Erik Årzén\, Lund University\n\n\n13:55\n WASP AI graduate school\, Amy Loutfi\, Örebro University\n\n\n14:15\nPerspectives from a WASP Industrial Supervisor and a WASP Industrial PhD student\, Salla Franzén and Ciwan Ceylan SEB\n\n\n14:45\n Questions and discussion\n\n\n15:00\nWrap up\n\n\n\nPlease register to the webinar no later than January 20th. A link to the webinar will be sent to all registered participants January 21st.
URL:https://wasp-sweden.org/event/webinar-call-for-industrial-phd-students/
CATEGORIES:Webinar
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2019/12/photo-of-blue-pink-and-green-led-light-775907-e1576499414990.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200116T000000
DTEND;TZID=+01:00:20200116T235959
DTSTAMP:20260602T135701
CREATED:20200109T103605Z
LAST-MODIFIED:20260601T083915Z
UID:10000335-1579132800-1579219199@wasp-sweden.org
SUMMARY:Designing for machine learning in medical image diagnostics – Enabling efficient ensembles of professional medical practitioners and learning machines through interaction design
DESCRIPTION:WASP industrial PhD student Martin Lindvall is having his halftime seminar. A halftime seminar is the equivalent of a licentiate seminar\, where Martin will be presenting his ongoing PhD work and discuss it with docent Ylva Fernaeus of KTH\, our external discussant. \nTitle\nDesigning for machine learning in medical image diagnostics — Enabling efficient ensembles of professional medical practitioners and learning machines through interaction design \nAbstract\nAdvancements in machine learning (ML) has led to a dramatic increase in AI capabilities for medical diagnostic tasks. However\, despite impressive technical advances\, predictive algorithms are to a very small extent used in healthcare today. A lack of design considerations and inefficient human-AI collaborations has been identified as a major factor limiting adoption in clinical settings. \nUsing a constructive design research approach\, my work explores how we might design systems with ML components that aid clinical decision-making. Preliminary results are derived from experiments and experiences from four projects\, all aiming to produce novel interactive systems for or with ML components. \nPreliminary contributions consist of identifying design challenges and suitable interaction strategies for human-ML collaboration at different stages of automatic support. Specifically\, I present three works that address challenges in designing for effective human-machine teaching and two in-progress works that address the challenge of designing interactions that afford successful collaborative strategies despite the uncertainty inherent in machine predictions. \nOriginal location: KO301\, Campus Norrköping\, Kopparhammaren 2\, Third floor
URL:https://wasp-sweden.org/event/designing-for-machine-learning-in-medical-image-diagnostics-enabling-efficient-ensembles-of-professional-medical-practitioners-and-learning-machines-through-interaction-design/
LOCATION:Campus Norrköping\, Linköping University\, Campus Norrköping\, Linköping University\, Norrköping\, Sweden
CATEGORIES:Seminar
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20200113T120000
DTEND;TZID=+01:00:20200115T235900
DTSTAMP:20260602T135701
CREATED:20191108T124025Z
LAST-MODIFIED:20260601T083918Z
UID:10000344-1578916800-1579132740@wasp-sweden.org
SUMMARY:WASP Winter Conference 2020
DESCRIPTION:Winter Conference at Konsert & Kongress in Linköping.\nThe winter conference is an internal WASP conference held in January every year. It includes a kick-off for new PhD students and new supervisors\, in which an introduction is given to the WASP graduate school and related activities. In the conference part\, WASP research results are presented by the PhD students. Also\, shorter and longer talks are given on WASP-related topics. After the actual conference\, the WASP clusters meet to plan for the coming year. \nThis three-day event provides an excellent opportunity to get an overview of WASP’s graduate school and research results. It is mandatory for the PhD students and it is the only recurring occasion where the whole WASP community gathers. Please see the internal webpage for detailed information. \nProgram\nJanuary 13th\n12:00-13:00 Lunch\n13:00-17:00 Kick-off  (new PhD students and supervisors)\n19:00 Kick-off Dinner \nJanuary 14th\n09:00-10:00 Kick-off (cont.)\n10:00-10:30 Get-together Coffee\n10:30-17:00 WASP Conference including lunch (everyone in WASP)\n19:00 Conference dinner \nJanuary 15th\n09:00-12:00 WASP Conference (cont.)\n12:00-13:00 Lunch\n13:00-15:00 Separate WASP Cluster meetings (primarily for PhD students but everyone is welcome)
URL:https://wasp-sweden.org/event/wasp-winter-conference-2020/
LOCATION:Konsert & Kongress\, Linköping\, Konsert & Kongress\, Linköping\, Linköping\, Sweden
CATEGORIES:Conference
ATTACH;FMTTYPE=image/jpeg:https://wasp-sweden.org/wp-content/uploads/2019/11/konsert-och-kongress-liten-1.jpg
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20191216T101500
DTEND;TZID=+01:00:20191216T235900
DTSTAMP:20260602T135701
CREATED:20191126T074826Z
LAST-MODIFIED:20260601T083916Z
UID:10000338-1576491300-1576540740@wasp-sweden.org
SUMMARY:Data-driven Condition Monitoring in Mining Vehicles
DESCRIPTION:Name: Erik Jakobsson\nDegree: Licentiate in Electrical Engineering\nTitle: Data-driven Condition Monitoring in Mining Vehicles\nLink to thesis: http://www.diva-portal.org/smash/record.jsf?pid=diva2%3A1371480&dswid=-8493 \nOriginal location: Ada Lovelace\, B-Huset\, Campus Valla\, Linköping University\, Linköping
URL:https://wasp-sweden.org/event/data-driven-condition-monitoring-in-mining-vehicles/
LOCATION:Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Linköping\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20191212T101500
DTEND;TZID=+01:00:20191212T235900
DTSTAMP:20260602T135701
CREATED:20191125T160748Z
LAST-MODIFIED:20260601T083916Z
UID:10000339-1576145700-1576195140@wasp-sweden.org
SUMMARY:Computation of Autonomous Safety Maneuvers Using Segmentation and Optimization
DESCRIPTION:Name: Pavel Anistratov \nDegree: Licentiate in Electrical Engineering with specialization in Vehicular Systems \nTitle: Computation of Autonomous Safety Maneuvers Using Segmentation and Optimization \nLink to thesis: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-162164 \nLink to calendar: https://old.liu.se/liu-nytt/kalendarium/?l=sv \nOriginal location: Ada Lovelace\, B-Huset\, Campus Valla\, Linköping University\, Linköping
URL:https://wasp-sweden.org/event/computation-of-autonomous-safety-maneuvers-using-segmentation-and-optimization/
LOCATION:Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Linköping\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20191118T090000
DTEND;TZID=+01:00:20191118T235900
DTSTAMP:20260602T135701
CREATED:20191112T092540Z
LAST-MODIFIED:20260601T083918Z
UID:10000343-1574067600-1574121540@wasp-sweden.org
SUMMARY:WASP4ALL – Future Computing Platforms for X
DESCRIPTION:First Annual WASP Open Conference in Stockholm November 18th\nDon’t miss the opportunity to attend the first open WASP conference. The 2019 theme will be future computing platforms. \nWe will dive into hands on aspects of the hottest and most urgent applications in need of state-of-the-art computing and scrutinize the specific needs of areas such as AI/Machine Learning\, Visual Computing\, Data Analytics\, and Autonomous Agents and Software.  The meeting will cover a range of computing related topics\, from both a hardware and software perspective\, of highest possible relevance to WASP researchers and affiliates. \nThe starting point is the near future for computing in terms of GPUs and FPGAs\, tailored energy efficient architectures\, and cloud and edge computing. We will then explore in-depth other architectures and software solutions on the horizon and the possibilities they will offer. We will also provide a glimpse of the long term future and what quantum computing will bring to the table. The complex interplay between platforms and applications and the tools needed for efficient application development will be highlighted. \nOur target audience is general researchers and developers in both academia and industry and the presentations will have a general technical content\, but with a serious touch of interesting research and hard core technology. If you will be in need of leading edge computing platforms for your applications in the future this is a meeting you cannot miss. \nWelcome! \nDetails\nArrival registration and coffee from 8:30 \nTime: Program from 9:00–16:00\nLocation: Folkets hus\, Barnhusgatan 12-14\, Stockholm \nContact\nIf you have any questions regarding the event\, please contact: wasp.event@partner.liu.se  \n\nProgram\n08:30 Registration and coffee \nSession I\nChair: Anders Ynnerman\, Linköping University \n09:00 Opening remarks and introduction to the seminar\, Anders Ynnerman \n09:15 Keynote: GPU Computing for Graphics and AI\, Tomas Akenine-Möller\, NVIDIA \n10:00 The Processing-in-Memory Paradigm for Deep Neural Networks\, Per Stenström\, Chalmers \n10:30 Coffee \nSession II\nChair: Karl-Erik Årzén\, Lund University \n11:00 The Bitter Lesson of ML Pipelines and Deep Learning\, Jim Dowling\, KTH \n11:30 Use-case: Machine Learning for Visual Perception\, Michael Felsberg\, Linköping University \n12:00 Lunch \nSession III\nChair: Danica Kragic\, KTH \n13:00 Computing on the edge\, Erik Elmroth\, Umeå University \n13:30 The Next Industrial Revolution and the Digital Transformation of Society\, Robin Teigland\, Chalmers \n14:00 The SNIC computational landscape\, Hans Karlsson\, Uppsala universitet \n14:30 The evolving commercial computational landscape\, Johan Eker\, Lund University \n14:50 Coffee  \nSession IV\nChair: Johan Håstad\, KTH \n15:10 Quantum computing – from physics research towards a breakthrough in computer technology\, Jonas Bylander\, Chalmers \n15:35 Post quantum cryptography\, Thomas Johansson\, Lund University \n16:00 Wrap up \n\nProgram Committee\nAnders Ynnerman\, Danica Kragic\, Karl-Erik Årzén\, Johan Håstad \nOriginal location: Folkets hus\, Barnhusgatan 12-14\, Stockholm
URL:https://wasp-sweden.org/event/wasp4all-future-computing-platforms-for-x/
LOCATION:Stockholm\, Stockholm\, Stockholm\, Sweden
CATEGORIES:Conference
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190918T100000
DTEND;TZID=+01:00:20190919T235900
DTSTAMP:20260602T135701
CREATED:20191112T103435Z
LAST-MODIFIED:20260601T083918Z
UID:10000342-1568800800-1568937540@wasp-sweden.org
SUMMARY:Public Safety Research Arena Demonstration
DESCRIPTION:WASP Public Safety Research Arena (WARA-PS) will once again host a demonstration with several projects. Invited guests will take part of demos\, discussions and presentations and be a part of defining the future research agenda. News this year is more vehicles\, more autonomy and cooperation with SMaRC research arena. \nDates: 2019-09-18 – 2019-09-19\nLocation: Gränsö Slott\, Västervik\nThis event is open by invitation only \n  \nAgenda\nMonday 16th of September – Wednesday 18th of September \nCore team and PhD student research and preparations \nWednesday 18th of September  \n“What has been done and the direction” \n10-11 Drop in and coffee \n11.00 Welcome and start of workshop \n12.00 Lunch and exhibition \n13.00 Research presentations from PhDs \n14-16.30 Demonstrations: In air\, on water\, under water\, in the cloud\,… \n16.30-17 Summary Day 1 \n17-18 Exhibition\, Posters\, Separate workshops\, free time\,… \n20.00 Dinner \nThursday 19th of September\n“Details\, feedback and looking forward” \n(Depending on weather conditions this day might also contain live demonstrations) \n9-10 Core system\, research topics \n10-10.30 Challenges and trends in Public Safety \n10.30-11.30 Parallel sessions: Project presentations + How to work in WARA-PS \n11.30-12 End of workshop \n12-13 Lunch and exhibition \n13-14 WARA-PS Core team summing up (only Core team) \nOriginal location: Gränsö slott\, Västervik
URL:https://wasp-sweden.org/event/public-safety-research-arena-demonstration/
LOCATION:Gränsö Slott\, Västervik\, Gränsö Slott\, Västervik\, Västervik\, Sweden
CATEGORIES:Workshop
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190914T000000
DTEND;TZID=+01:00:20190914T235959
DTSTAMP:20260602T135701
CREATED:20190708T153536Z
LAST-MODIFIED:20260601T083919Z
UID:10000345-1568419200-1568505599@wasp-sweden.org
SUMMARY:WASP Workshop on Smart Localization Systems
DESCRIPTION:By invitation only \nThe annual conference is this year placed at Gränsö in order to highlight the need for good positioning in autonomous systems used in air\, land and on water. The agenda and content is arranged by FOI\, the Swedish Defence Research Agency in cooperation with WASP WARA-PS.
URL:https://wasp-sweden.org/event/wasp-workshop-on-smart-localization-systems/
LOCATION:Gränsö Slott\, Västervik\, Gränsö Slott\, Västervik\, Västervik\, Sweden
CATEGORIES:Workshop
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190905T000000
DTEND;TZID=+01:00:20190905T235959
DTSTAMP:20260602T135701
CREATED:20191112T103640Z
LAST-MODIFIED:20260601T083917Z
UID:10000341-1567641600-1567727999@wasp-sweden.org
SUMMARY:WASP International Scientific Advisory Board Meeting
DESCRIPTION:By invitation only. The annual WASP ISAB meeting.
URL:https://wasp-sweden.org/event/wasp-international-scientific-advisory-board-meeting/
LOCATION:Stockholm\, Stockholm\, Stockholm\, Sweden
CATEGORIES:Meeting
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190903T000000
DTEND;TZID=+01:00:20190903T235959
DTSTAMP:20260602T135701
CREATED:20190708T152028Z
LAST-MODIFIED:20260601T083919Z
UID:10000346-1567468800-1567555199@wasp-sweden.org
SUMMARY:WARA-PS Preparation workshop
DESCRIPTION:By invitation only \nThe WARA-PS Core team and WASP PhD students integrates\, tests and collect data for research and preparation for the September demonstration two weeks later. During these days autonomous boats\, drones and sensors will be tested together with cloud based services for delegation and command and control systems.
URL:https://wasp-sweden.org/event/wara-ps-preparation-workshop/
LOCATION:Gränsö Slott\, Västervik\, Gränsö Slott\, Västervik\, Västervik\, Sweden
CATEGORIES:Workshop
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190614T000000
DTEND;TZID=+01:00:20190614T235959
DTSTAMP:20260602T135701
CREATED:20191112T103938Z
LAST-MODIFIED:20260601T083917Z
UID:10000340-1560470400-1560556799@wasp-sweden.org
SUMMARY:On Motion Planning Using Numerical Optimal Control
DESCRIPTION:Defense by Kristoffer Bergman\nFor: Licentiate in automatic control\nTitle: On Motion Planning Using Numerical Optimal Control\nDate and Time: 2019-06-14\nLocation: Ada Lovelace\, B-building\, Linköpings University\nOpponent: Assoc. Prof. Paolo Falcone\, Chalmers\nSupervisor: Assoc. Prof. Daniel Axehill\nCo-supervisors: Prof. Torkel Glad \nOriginal location: Ada Lovelace\, B-building\, Linköpings University
URL:https://wasp-sweden.org/event/on-motion-planning-using-numerical-optimal-control/
LOCATION:Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Ada Lovelace\, B-building\, Campus Valla\, Linköping University\, Linköping\, Sweden
CATEGORIES:Defense
END:VEVENT
BEGIN:VEVENT
DTSTART;TZID=+01:00:20190605T100000
DTEND;TZID=+01:00:20190605T235900
DTSTAMP:20260602T135701
CREATED:20190531T082636Z
LAST-MODIFIED:20260601T083919Z
UID:10000347-1559728800-1559779140@wasp-sweden.org
SUMMARY:Tactical decision-making for autonomous driving: A reinforcement learning approach
DESCRIPTION:Defense by Carl-Johan Hoel\nFor: Licentiate of Engineering in Adaptive systems\nLocation: Lecture hall FB\, Fysikgården 4\, Chalmers University of Technology\, Göteborg \nDiscussion leader: Associate Professor Christos Dimitrakakis\, Department of Computer Science and Engineering\, Chalmers.\nSupervisors: Associate Professor Krister Wolff (Chalmers)\, Adjunct Professor Leo Laine (AB Volvo).\nExaminer: Professor Mattias Wahde \nThe tactical decision-making task of an autonomous vehicle is challenging\, due to the diversity of the environments the vehicle operates in\, the uncertainty in the sensor information\, and the complex interaction with other road users. This thesis introduces and compares three general approaches\, based on reinforcement learning\, to creating a tactical decision-making agent. The first method uses a genetic algorithm to automatically generate a rule based decision-making agent\, whereas the second method is based on a Deep QNetwork agent. The third method combines the concepts of planning and learning\, in the form of Monte Carlo tree search and deep reinforcement learning. The three approaches are applied to several highway driving cases in a simulated environment and outperform a commonly used baseline model by taking decisions that allow the vehicle to navigate 5% to 10% faster through dense traffic. However\, the main advantage of the methods is their generality\, which is indicated by applying them to conceptually different driving cases. Furthermore\, this thesis introduces a novel way of applying a convolutional neural network architecture to a high level state description of interchangeable objects\, which speeds up the learning process and eliminates all collisions in the test cases. \nOriginal location: Chalmers University of Technology\, Göteborg
URL:https://wasp-sweden.org/event/tactical-decision-making-for-autonomous-driving-a-reinforcement-learning-approach/
LOCATION:Chalmers University of Technology\, Chalmers University of Technology\, Göteborg\, Sweden
CATEGORIES:Defense
END:VEVENT
END:VCALENDAR