A profile series that introduces our team and showcases what we’re working on.
My name is Tara Stentz, and I am a Software Engineer on the Prediction Team! I graduated in 2018 from Carnegie Mellon University with a degree in Electrical and Computer Engineering and a minor in Computer Science. For the summer of 2017, I was looking for an internship that had the feel of a smaller company, even if it was housed within a bigger organization. I was also hoping to get experience in software development, robotics, and machine learning. Uber ATG was the perfect fit! My team made sure I felt my contributions were valuable even though I was “just an intern,” and I enjoyed being immersed in this fast-paced, deeply innovative field.
I started as a full-time employee in September of 2018. I have enjoyed my time here even more because I’ve gotten to work on some really exciting projects.
Now
The Prediction Team is involved in the “brain” of the self-driving car, and we are responsible for determining what the dynamic objects in a scene, like other vehicles, might do next. This is a very hard problem to solve because, to ensure the safety of our vehicles, we must anticipate harmful events before they occur — on time and every time.
I really enjoy working on the Prediction Team because we’re in the middle of the autonomy pipeline. It’s fun to work with teams both upstream, like Perception (what the car sees), and downstream, like Motion Planning (what the car does next).
Next
Evaluating the effectiveness of our Prediction system is a huge challenge. The hard part is defining what it means to have a “good” Prediction system, then designing a metric or set of metrics so we can measure it. However, it’s a very important part of the work we do. We have to understand how and where our predictions could perform better so we can continue to improve them.
Future
I truly think this technology will make the world a safer place. Way too many people are killed each year in accidents caused by human error. In addition, I’m excited about the potential for positive environmental impact. If we had a fleet of self-driving cars operating on the streets, think of all the parking lots we could turn into parks!
And as a final funny story, I once went to an elementary school to talk about self-driving, and it made me so excited to hear the students’ ideas about a world with only self-driving vehicles. One of my favorite suggestions from the group was to make an ice cream parlor within a self-driving car. Sign me up for that!