hosted by Apex.AI
We are a community of developers and enthusiasts working on mobility automation technology. Our events aim at sharing knowledge, experiences, and best practices to accelerate the development of safe and reliable self-driving vehicles. The growing ecosystem of academic progress, companies, and technologies around open-source Autoware and ROS provides a path from research to commercial production of this technology stack.
Autonomous Public Transportation
Dr. Ali Peker, CEO and Dr. Kerem Par, CTO of ADASTEC joins Sanjay Krishnan, VP of Product at Apex.AI to share their latest updates on Autonomous Public Transportation.
The discussion goes into ADASTEC’s approach to highly autonomous buses, and how they make use of open source technology such as Autoware. They describe their approach to sensor fusion and how simulation and automation methodologies are used in their development process. Also on the table for discussion are other services required for automated public transportation to become a reality. Finally, the impact of COVID-19 is on people’s minds and the presenters share their perspective on how this affects the industry.
Using AI to Deal with Unpredictable Humans
on the Road
Dr. Pavone shares details on recent advances in deep generative modeling for intent prediction and provides results from experiments on a full-scale steer-by-wire platform. He will also talk about related efforts from his group on infusing safety assurances in autonomy stacks equipped with learning-based components.
Dr. Pavone is the Director of the Autonomous Systems Laboratory (ASL) at Stanford University and is Co-Director of the Center for Automotive Research at Stanford. His main research interests are in the development of methodologies for the analysis, design, and control of autonomous systems, with an emphasis on self-driving cars, autonomous aerospace vehicles, and future mobility systems.
Machine Learning For The Safety Validation
Of Autonomous Vehicles
Autonomous vehicles (AVs) require rigorous testing before deployment. Due to the complexity of these systems, formal verification may be impossible and real-world testing may be dangerous and expensive during development.
This is where AST fits in. Anthony Corso presents his work on Adaptive Stress Testing (AST), a technique for automatically finding the most-likely failures of an autonomous system in simulation.