Verification of Autonomous Systems Workshop

Full Day Workshop

IROS 2017

SUNDAY – SEPTEMBER 24, 2017

08:30 – 17:00

Objectives

Self-driving cars, robotic home assistants, medical robots, and other diverse autonomous systems are becoming a reality worldwide. In order for these systems to be adopted in everyday life, autonomous systems must be shown to perform their required functions and do so in a trustworthy and safe manner.  Consequently, verification of autonomous systems—compelling evidence that autonomous systems satisfy their requirements—has become increasingly important. From software engineering to control systems design, we must ensure that autonomous systems behave as intended. In particular, that they behave safely—do not cause human injury or death, or damage or destruction of property. Efforts to propose methodologies and to develop tools related to the verification or verified design of autonomous systems are increasing worldwide. As technology progresses, and autonomous systems become more complex, with added intelligence and adaptive capabilities, the challenges of verification increase.

Our goal is to bring together experts in verification, autonomous and intelligent systems designers, and leading roboticists to discuss the main challenges in verification of autonomous systems, including the difficulty of defining meaningful requirements and of reasoning about highly unpredictable environments and complex interactions with people, as well as adaptation and learning mechanisms. We will present the state-of-the-art in verification of autonomous systems in terms of methodologies, techniques, ontologies, languages and successful applications. A major goal will be to find common ground to address the challenges relating to design for verification in robotics and verified robotic designs. We hope to open new avenues for future interdisciplinary collaboration among participants and expect that this will significantly advance the state of the art in this important area.

This workshop builds upon previous efforts, including a workshop that took place at ICRA 2016. More information on that workshop may be found here.

 

Organizers

Stephen Balakirsky, Georgia Tech Research Institute, US

Robin D. Ashmore, DSTL, UK

Elizabeth Leonard, NRL, US

Constance Heitmeyer, NRL, US

Don Sofge, NRL, US

Signe Redfield, NRL, US

Calin Belta, Boston University, US

Craig Schlenoff, NIST, US

David Scheidt, Weather Gage Technologies, LLC, US

John Sustersic, Penn State, US

Marc Steinberg, ONR, US

David Sparrow, Poornima Madhavan, IDA, US

Agenda

  • 9:00 – 10:30 First Session: Research Challenges
    • Speaker: Signe Redfield, Naval Research Lab (NRL) (confirmed)
    • Speaker: Robin Ashmore, DSTL (confirmed)
    • Panelist: Elena Messina, National Institute of Standards and Technology (NIST) (confirmed)
    • Panelist: Marc Steinberg, Office of Naval Research (ONR) (confirmed)
  • 10:30 – 11:00 Morning Break
  • 11:00 – 12:30 Second Session: Quantification of Trust
    • Speaker: Poornima Madhavan, Institute for Defense Analyses (confirmed)
    • Panelist: James Bliss, Old Dominion University (confirmed)
    • Panelist: Alan Wagner, Penn State (confirmed)
    • Panelist: Yue Wang, Clemson University (confirmed)
  • 12:30 – 14:00 Lunch
  • 14:00 – 15:30 Third Session: Common Evaluation Frameworks
    • Speaker: David Scheidt, Weather Gage Technologies, LLC (confirmed)
    • Panelist: Fabio Bonsignorio, Heron Robots and Scuola Superiore Sant’ Anna (SSSA) (confirmed)
    • Panelist: Joe Falco, NIST (confirmed)
    • Panelist: Galen Mullins, John Hopkins University, Applied Physics Lab (JHU/APL) (confirmed)
  • 15:30 – 16:00 Afternoon Break
  • 16:00 – 17:30 Fourth Session: Task Representation and Ontologies
    • Speaker: Stephen Balakirsky, Georgia Tech Research Institute (GTRI) (confirmed)
    • Panelist: Andrew Bouchard, Naval Surface Warfare Center Panama City Division (NSWC PCD) (confirmed)
    • Panelist: Paulo Goncalves, Polytechnic Institute of Castelo Branco (IPCB) (confirmed)
    • Panelist: Craig Schlenoff, NIST (confirmed)

Intended Audience

Our intended audience includes

(1) participants from well established research networks; both academic and industry related, since they can provide greater insight to the current challenges of autonomous systems verification, and provide real-life first-hand knowledge on a range of applications.

(2) early career researchers, including current graduate students and postdoctoral researchers, since our workshop will include a discussion of the currently open research areas within this domain.

(3) persons new to the field of verification, such as robotics designers attending the main conference tracks at IROS, since the dramatic increase in real-world applications means that many designers of robots and intelligence algorithms will need to take verification into account at the design stage.

For More Information, Please Contact One of Following:

Stephen Balakirsky (Stephen.Balakirsky@gtri.gatech.edu)

Signe Redfield (signe@ieee.org)

Craig Schlenoff (Craig.Schlenoff@nist.gov)