This was a hybrid event with in-person attendance in Levine 307 and virtual attendance…
Why has autonomous driving, a task demanding significant intelligence, not met the high expectations set by many? Which hurdles have turned out to be more formidable than expected, and how can we refine our testing methodologies for autonomous vehicles (AVs) to address these problems more efficiently? In this talk, I will discuss the targeted research initiatives we have engaged in to overcome these challenges. Leveraging more than a decade of experience from high-speed autonomous racing, particularly with the full-scale Cavalier Autonomous Racing Indy car and the F1Tenth platform, I will demonstrate how racing at speeds exceeding 150 mph (240 kmph) while in close quarters with other vehicles presents unique robotics challenges and offers deep insights into the limits of perception, multi-agent prediction and planning, dynamics modeling, and control. I will recount our journey from algorithms to accelerations, the rigorous engineering required to develop an autonomous racing car from scratch, and how this fast moving field is becoming accessible to researchers and professionals alike. Despite progress, autonomous racing has yet to match expert racing drivers’ skills or navigate the chaos of dense, multi-car racing in the real world; indicating that several more laps are needed on our journey towards artificial general “driving” intelligence.