DSAi: Autonomous vehicles & Ai - special edition @ Tesla

Are you going?

112 people going

Share:
Location image of event venue

Details

Please note that a ticket is required to reserve a place at this meetup. Sign up for a ticket by following the link below:

https://www.eventbrite.com.au/e/dsai-autonomous-vehicles-ai-special-edition-tesla-tickets-65085207608

We cannot assure you a seat as seating will be distributed on a first come first serve basis on the night. Please arrive early to ensure you get a seat.
________

DSAi is proud to present our next event: Autonomous vehicle special edition @ Tesla

We have two leading experts from academia speaking at this event.
Stewart Worrall, a research fellow at Australian Centre for Field Robotics will talk about the last mile problem of deploying autonomous vehicles in urban areas , the limits of deep learning in solving some of the challenges faced in this area and what ML techniques might be applied to address these issues.

Wei Zhou a 4th year Ph.d student at the same centre, will talk about making image recognition system more robust which is the core of autonomous vehicles.

Tesla, a leader in the field has graciously accepted our request to host the event. We will also have some amazing demos from Tesla.
So if you want to learn about the future of urban mobility, while looking suave and networking with the most pioneering individuals in the field, then join us on 25th July at Tesla in Martin Place.

Food and drinks are provided.

Dress code: smart casual.

Note: By sign in for this event you agree that Tesla might contact you via email later about their products and promotions.

~

Stewart Worrall

The efficient and safe mobility of people and goods in urban areas is a challenging problem that becomes more difficult with increasing population density. Congestion, accidents and pollution are highly undesirable for the financial, environmental and general well-being of the population. The automation of vehicles has long been considered part of a “smart cities” solution to this problem, working towards a utopian, sci-fi vision of the future. These technologies have been long promised, but seem to be always just out of reach. This presentation will highlight some of the key challenges in vehicle automation. The application of machine learning as a “black box” approach does not easily fit with a highly safety critical engineered system. The talk will focus particularly on aspects of autonomous systems that are appropriate for deep learning, but also where these techniques are not appropriate given our current understanding of the problem & what ML techniques might be applied to address these issues.

Stewart Worrall has many years of experience in the research and development of vehicle automation and safety technologies. He is a research fellow at the Australian Centre for Field Robotics, which is part of Sydney University. Over the past three years, he has been leading the development of several small autonomous electric vehicle platforms with the aim of solving the last mile transport problem. His main areas of research range across the spectrum of automation, including localisation, mapping, navigation, perception and path planning.

Wei Zhou

Over the last few years, deep learning techniques for image based semantic segmentation have been demonstrated to produce remarkable results for applications in intelligent transportation systems. However, the issue of the robustness has recently been recognised as a major challenge for the massive deployment of this new technology. In particular, for autonomous vehicles, any erroneous classification could potentially lead to catastrophic consequences. In this talk, I will explain the main challenges we are facing at the moment when applying semantic segmentation to autonomous vehicles. Also, I will present my proposed method to validate the robustness of semantic segmentation by automatically generating ground-truth labels. This method can be used in most real-world driving scenarios without the time and expense of using humans to generate labels by hand.