Where to from here? Algorithmic, Legal, and Societal Challenges for Autonomous Driving

Where to from here? Algorithmic, Legal, and Societal Challenges for Autonomous Driving

The BROAD workshop

What are the new frontiers of autonomous driving: Are there open technical or non-technical issues that impede autonomous driving now or in the upcoming future? Can cognitive inspiration and machine learning (ML) help us here or do these approaches lead to new problems?

The workshop focuses on two major aspects of these questions. The first is the identification of major challenges across all aspects of autonomous driving (algorithmic, societal, law-related, standardization, etc.) that are supposed to or that could probably impede the development of autonomous driving (AD) or its introduction on the market. These could be technical issues (how many test miles need to be driven? is ML reliable? do we need explainable ML methods in general? how to select training data?). But these could also be non-technical questions like law-, insurance-related, or ethical questions.

The second aspect is the discussion of potential, cognitively-inspired and ML-based solutions. Here, we will focus on two approaches: pure ML, and bio-inspired approaches that try to mimic cognitive mechanisms observed in humans and/or animals in a reasonable amount of detail. Each approach has their own particular advantages and limitations. For example pure ML often requires large amounts of training data, yet is typically very brittle while bio-inspired approaches are by necessity based on incomplete theories, and we’re still missing convincing demonstrations in real applications.

Presentations

Workshop format: half day

Date and site: The BROAD WS will take place as part of the IEEE Intelligent Vehicles Symposium 2021 at Nagoya, Japan, again as an online conference. The date of the workshop is July, 12th 18:00 JST till 21:00 JST .

The Zoom link to the BROAD workshop session can be found on the IV website (“ZOOM” for WS 50): https://2021.ieee-iv.org/workshops/

Attendance

This year it is possible to attend at the BROAD workshop for free! However, a registration is needed. The IV21 portal site is now open. Please create an account on the portal site before joining the session.

Portal Site URL: https://iv21-nagoya.com/registration/

Workshop Program

(All times given in Nagoya local time (JST)!)

Time (JST) Topic
18:00-18:15 Welcome talk: “What Are This Year’s Challenges for AD?” (Tim Tiedemann, HAW Hamburg)
18:15-19:00 “Auction Based Parking Lot Assignment and Empty Cruising Limitation of Privately Owned Autonomous Vehicles in a Simple City Model” (Levente Alekszejenkó, Budapest University of Technology and Economics, Hungary)
19:00-19:15 Coffee break (short)
19:15-20:00 “A Metric For Explainable AI in Automotive Applications (wt)” (Juri Zach, HAW Hamburg, Germany)
20:00-20:15 “Self-updating agent architectures for learning emergent behaviors in corner cases” (Mauro da Lio, University of Trento, Italy)
20:15-20:30 Round Table Discussion 1 “Sticking to the old, beaten paths – When people get nervous when the old paradigms do not work any longer” (Mauro da Lio, University of Trento, Italy and Tim Tiedemann, HAW Hamburg, Germany)
20:30-21:00 Round Table Discussion 2 “These Were The BROAD Topics 2019 till 2021 – What did we learn? Anything?”

(preliminary, further contributions/changes will be included in the next days)

Presenters

There will be a mixture of invited talks, regular paper presentations, and discussion rounds.

CFP / Submission

Paper submission site is closed.

- Workshop paper submission: April 30th, 2021 (extended!) (the submission code is 1w6j2 (WS50))
- Notification of workshop paper acceptance: May 15th, 2021
- Final Workshop paper submission: May 31st, 2021
- IV 2021: July 11th - 15th, 2021 (workshop: July 12th) -- tentative!

Authors of accepted workshop papers will have their paper published in the conference proceeding. At least one author needs to be registered for the workshop and the conference. Information on paper and submission is common with all symposium papers and is available at https://2021.ieee-iv.org/information-for-authors/

Chairs

  • Tim Tiedemann:
    Affiliation: Department of Computer Science, Faculty TI, University of Applied Sciences Hamburg
    Email address: Tim.Tiedemann@haw-hamburg.de

  • Serge Thill:
    Affiliation: Interaction Lab, School of Informatics, University of Skövde, Sweden and Donders Institute for Brain, Cognition, and Behaviour, Radboud University, The Netherlands

  • Sean Anderson:
    Affiliation: Department of Automatic Control and Systems Engineering, University of Sheffield

Acknowledgement

This workshop is supported by the European H2020 project Dreams4Cars, grant agreement number 731593.