BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//DATE2023//date-conference.com//EN
CALSCALE:GREGORIAN
BEGIN:VEVENT
DTSTART;TZID=Europe/Brussels:20230417T140000
DTEND;TZID=Europe/Brussels:20230417T153000
LOCATION:Gorilla Room 1.5.4/5
DTSTAMP;TZID=Europe/Brussels:20231002T131345
SUMMARY:ASD2 ASD special session: Information Processing Factory, Take Two on Self-Aware Systems of MPSoCs
URL;VALUE=URI:https://date23.date-conference.com/programme#ASD2
DESCRIPTION:The Information Processing Factory (IPF) project is a collaboration between research teams in the US (UC Irvine) and Germany (TU Munich and TU Braunschweig) looking into Self-aware MPSoCs.  IPF 1.0, was first introduced in ESWEEK 2016 as a paradigm to master complex dependable systems. The IPF paradigm applies principles inspired by factory management to the continuous operation and optimization of highly-integrated embedded systems. IPF 2.0 is an extension of the IPF for recent data-centric approaches and decentralization methodologies. While an IPF 1.0 system can operate independently, IPF 2.0 has a system-of-systems structure in which several IPF 1.0 “factories” interact, thus providing an additional layer of abstraction aimed at this data-centric approach. It horizontally extends core concepts such as self-optimization, self-construction, and runtime verification, while maintaining the strengths of the existing IPF methodology. Four talks in this session highlight the various concepts in IPF 2.0 illustrated through a truck platooning exemplar.  <br><br> The talks outline the challenges introduced when moving from self-organizing local systems in IPF 1.0 to autonomous systems collaboration in IPF 2.0, using commercial vehicle platooning as a use case. The first talk explains how the self-aware truck control systems collaborate towards a platoon-level runtime verification that continuously supervises the state of a platoon, even under a changing platoon formation and external disturbance, e.g., by intersecting traffic participants. The second talk outlines the challenges related to managing enormous amounts of dynamic data in the system, and discusses how self-aware caching can help in mastering the resulting communication and data management requirements. The third talk proposes approaches to mitigate the energy cost of data management across multiple systems. The fourth talk addresses lack of explainability in the underlying machine learning technology in collaborative autonomous systems.
X-ALT-DESC;FMTTYPE=text/html:The Information Processing Factory (IPF) project is a collaboration between research teams in the US (UC Irvine) and Germany (TU Munich and TU Braunschweig) looking into Self-aware MPSoCs.  IPF 1.0, was first introduced in ESWEEK 2016 as a paradigm to master complex dependable systems. The IPF paradigm applies principles inspired by factory management to the continuous operation and optimization of highly-integrated embedded systems. IPF 2.0 is an extension of the IPF for recent data-centric approaches and decentralization methodologies. While an IPF 1.0 system can operate independently, IPF 2.0 has a system-of-systems structure in which several IPF 1.0 “factories” interact, thus providing an additional layer of abstraction aimed at this data-centric approach. It horizontally extends core concepts such as self-optimization, self-construction, and runtime verification, while maintaining the strengths of the existing IPF methodology. Four talks in this session highlight the various concepts in IPF 2.0 illustrated through a truck platooning exemplar.  <br><br> The talks outline the challenges introduced when moving from self-organizing local systems in IPF 1.0 to autonomous systems collaboration in IPF 2.0, using commercial vehicle platooning as a use case. The first talk explains how the self-aware truck control systems collaborate towards a platoon-level runtime verification that continuously supervises the state of a platoon, even under a changing platoon formation and external disturbance, e.g., by intersecting traffic participants. The second talk outlines the challenges related to managing enormous amounts of dynamic data in the system, and discusses how self-aware caching can help in mastering the resulting communication and data management requirements. The third talk proposes approaches to mitigate the energy cost of data management across multiple systems. The fourth talk addresses lack of explainability in the underlying machine learning technology in collaborative autonomous systems.
UID:20231002T131345-20230417T140000-20230417T153000
END:VEVENT
END:VCALENDAR