Driving Autonomous Vehicles Forward with Real World Applications

The autonomous vehicle industry has made significant progress in recent years, with the launch of fully autonomous ride-hailing services, commercialized autonomous trucking solutions, and local delivery logistics. However, the dynamism of real-world roads presents a set of complex robotics challenges to autonomous driving in urban environments, including busy intersections, narrow streets, ever changing layouts, and social interactions with other drivers, cyclists and pedestrians. In this session, I can provide a look at how autonomous technology has been evolving to meet and overcome the unique scenarios and challenges of driving in dense urban environments. I will go into depth about the hardware and software critical to meeting these ever-growing needs. For example, I’ll discuss how advanced and integrated LiDAR sensor systems, behavior-predicting software, and evaluation and deployment frameworks create safe and efficient autonomous driving technology. Additionally, I’ll discuss how state-of-the-art machine learning helps real world robotics systems develop nuanced understandings when reasoning others’ intentions. I’ll then dive into how autonomous driving technology is trained to understand said pedestrian and cyclist intentions, and how cars are then able to learn and adjust to these behaviors. I can also provide a closer look into the future of the transportation and autonomous driving industries, and how they will continue to grow as new advancements are made and hurdles are overcome. This new type of mobility–one that is built around safety, accessibility and convenience–makes it easier to imagine a world where so many aspects of daily life improve, such as access to job opportunities and healthcare. And, with the power of autonomous driving technology, it can become a widespread reality.

View the slides for this session