Aurora Voices with Luke Starcher

^{Luke teaching a class in Germany (left) | Luke visiting the town of Saverne in France (right)}

After I returned from Germany, I worked as a vehicle operator at another self-driving vehicle company before making my way to Aurora. I decided to join Aurora because I wanted to stay in Pittsburgh, and I saw Aurora as the most promising self-driving vehicle company in the area.

What does the Capability Operations team do?

Capability Operations is a relatively new team, and our job is to supply software engineering groups with high-quality manual driving data for various capabilities. A capability could be something like nudging, which is when the Aurora Driver adjusts its trajectory to get around obstacles in the road.

How do you get good manual driving data, and how does it help improve the Aurora Driver?

First, we sync with the autonomy teams to figure out exactly what kinds of data they need. For example, this year we were asked to gather examples of nudging around oncoming vehicles breaching our lane, nudging around double-parked vehicles on the road-side, etc.

Then, we put together routes for our trained vehicle operators to drive, where they can successfully demonstrate a maneuver many times in different circumstances. Finally, we review that incoming data to ensure it meets our quality standards, tag it with the maneuver type and a time stamp, and send it along to engineering.

That driving data is fed into machine learning models that teach the Aurora Driver how to do that maneuver smoothly. This is incredibly useful because it helps the Aurora Driver make decisions that feel natural on the road. We’re building a Driver that follows road rules, while also capturing that feeling of how trained vehicle operators actually drive.

Can you walk us through an example of a log you’d send to the motion planning team?

Below, our vehicle operators manually performed a smooth unprotected left turn. This example helped teach the Aurora Driver how to find an appropriate gap in oncoming traffic. It also demonstrated a situation when it was appropriate to pull up past the stop line at a traffic light.

^{An example of a manual driving clip that Luke’s team vetted and sent onward to be incorporated into motion planning machine learning models. Here, Aurora’s vehicle operators perform a smooth unprotected left turn.}

Tell us something about yourself that would surprise us.

^{Delicate Cashmere’s logo}

What made you decide to start your own record label?

My grandparents taught me how to play the guitar when I was really young, so music has been a huge focus throughout my whole life. When I was younger, I couldn’t always pay for recording studios, so I started building my own.

Now, I know so many people in Pittsburgh who are talented, and their music is usually overlooked. Most of the time, people play this game of “if I can just get this record label to hear me, my music will be put out.” That’s a big cornerstone to hit if you’re an artist. I’ve always wanted to do that, and I started believing that it was possible to do it myself.

^{Luke working in his music studio (left) | Luke launched Delicate Cashmere in February 2020 with a sponsored event to showcase local Pittsburgh artists (center) | Luke playing a live gig at Piano Day Pittsburgh 2019—photo credit Joey Kennedy (right)}

What is your label producing, and where can we find the music?

The label will likely always include some form of electronic music, whether that essence is buried deep in a post-rock funk band, or featured front and center for a wonky instrumental hip hop album.

I’m kind of old-fashioned in the sense that I like vinyl records, so my label presses as much vinyl as possible. Eventually, I’ll sell them in record stores, but for now, I encourage people to reach out over social media. It’s very home-grown.