Virtual Autonomous Driving Meetup #4

We are pleased to announce that after the summer break, we are continuing our 4th virtual Meetup on Autonomous Driving on Nov 26th!

Our special take on the matter will certainly remain: the Meetup aims to provide a broad overview, with talks from software companies, startups, OEMs, and Tiers; addressing anything from convolutional neural networks to safety and legal questions.

The link to the web conference will be made accessible to everyone who made it to the attendee's list. 😉

___ Agenda ___

_ Introduction & Welcome

_Session 1: The Molly Problem and Global Regulation for Automated Driving
Bryn Balcombe, Chief Strategy Officer, Roborace & Founder of ADA.ngo
www.ada.ngo

Safety and public trust are essential for the successful and widespread deployment of automated vehicles. Trust is defined as "a firm belief in the reliability, truth or ability" which in this case applies to both the self-driving software and those who develop/operate it. The Molly Problem was created to explore the public's expectations of reliability, truth, and ability in the event of a collision or near-miss incidents. During this session, we'll review the formulation of The Molly Problem, the initial public’s survey results, and the implication for global regulations of automated driving.

_ Session 2: On Data Quality and Reliable Machine Learning Development
Felix Friedmann, Co-Founder & Managing Director Incenda AI
www.incenda.ai

The hype is past - Machine Learning is in the transition from research to product grade. This transition requires to pay considerably more attention to quality and reliable development processes. The session will take a closer look at the different stages of machine learning development with a focus on labeling and data quality.

_ Session 3: Smart Recording of high bandwith data
Johannes Zangerle, Technical Business Developer
www.b-plus.com

Over the years OEMs and TIERs in the area of ADAS/AD focused on harvesting as much data as possible from real world test drives for validation. As petabytes accumulated now a paradigm shift happens: Only the relevant corner cases shall be recorded.
This technical presentation shows a holistic measurement architecture, which allows “intelligent and efficient recording”. It covers detection of relevant scenes in the vehicle based on algorithms/AI and managing the test fleet efficiently.

___ Further Details ___

_ The talks are all held in English and will take ~15 minutes each + ~10 minutes Q&A
_ Sponsor: Warmest thanks to Mathworks for enabling this online Meetup event by providing the web conferencing tool!
_ Exact time slots for the presentations may be adapted