I used to work on Mars rovers and now I’m developing self-driving cars. Here’s how I transitioned from NASA’s JPL to Amazon’s Zoox.

• Olivier Toupet started his career working on autonomous helicopters.

• The former supervisor at NASA’s Jet Propulsion Laboratory now works at AV startup Zoox.

• Here’s reporter Alexa St. His story as told to John.

This as-described article is based on a conversation with Olivier Toupet, 42, chief software engineer who works on the planning and control team at Amazon-owned autonomous vehicle startup Zoox. Toupet is located in San Diego County, California. He started his career as an aerospace engineer and holds a master’s degree in aerospace science from MIT and a master’s degree in aeronautical engineering from ISAE-SUPAERO in France. Interview edited for length and clarity.

France is where I grew up and went to school for aerospace engineering.

My main passion is really aviation and airplanes. I got my private pilot’s license. That school was one of the best space schools in France and they have partnerships with the best schools in the USA, so I decided to do a double degree at MIT.

I have always been very interested in the USA. I came to a school in Philadelphia for a full month in high school. I was excited to come again, this time for MA.

I was lucky enough to find a French professor doing research on aerobatic helicopters.

This was in the early 2000s. These were small scale helicopters that were fully autonomous and flying through the sky, performing the craziest aerobatic stunts. It’s very interesting in terms of orbital planning and control.

I’ve always loved math and I was pretty good at it. That’s how I got into controls, motion planning, drones, and autonomous vehicles.

Working in the aerospace industry as a foreigner is difficult.

There are many restrictions. However, I was lucky enough that my advisor had a small venture to actually commercialize some of his helicopters. The co-CEO was also an MIT research engineer. In November 2006, I was hired by a company called Aurora Flight Sciences.

For the first six years of my career, I was working directly with many faculty members at MIT and doing really exciting research projects about multi-vehicle autonomy, namely drones, land vehicles, watercraft, and even space with NASA.

The story continues

As you can imagine, it’s very exciting intellectually, but sometimes you have small prototype developments, lots of small projects that you feasibility, and it doesn’t become a real product.

It left me a bit lacking in terms of having a greater impact and developing truly real products.

I moved to California right after we got married in 2011 and worked on self-flying cars at a company now called Wisk.Aero.

I need to work on some pretty tough problems. This was actually developing a real airplane from the ground up. So it was a bit of a fantasy, a group of friends at a startup developing an airplane.

A small world in robotics. In fact, I did not apply to any company. Among all the jobs I had to go out, there were friends who reached out to me to work with them at that company.

It was still a little early for self-flying cars in 2011. I think they’re starting to gain more momentum now, but still probably ten years from now.

Another friend of mine reached out and said I should join them. I decided to move to Los Angeles and work for NASA. After all the attempts, I thought why not work for a big company and if there could be a better big company than NASA.

I am really interested in space and aerospace engineering but my main passion was more airplanes.

I was the supervisor of the Robotic Air Mobility group at the NASA Jet Propulsion Laboratory.

It’s a unique place in that it’s been called the FFRDC: Federal Funded Research and Development Center. It’s at the intersection of industry and academia in the sense that you have some really cool research projects, but you also have some really cool NASA flight missions where you can really instill some of these robotic technologies.

For example, I developed self-driving for the Perseverance rover so it can now self-drive beyond the horizon on Mars. I received a medal from NASA for my traction control work for the Curiosity rover, which basically helps reduce damage to the wheels. (Toupet received another NASA medal for software. Perseverance explorer.)

I need to use the Opportunity, Curiosity and Perseverance rovers and also fly the Ingenuity helicopter on Mars.

I had a good friend who left JPL to work at Zoox.

I joined Zoox as a consultant in March 2015, and it was ideal for me because I needed to do great things for NASA at a fairly slow pace – these space programs take many years to mature – but at the same time, most weekends here in the Bay Area much faster I would be working. It was the best of both worlds, and that went on for seven years.

Zoox was acquired by Amazon. It was perfect timing.

Here’s one reason why being a consultant has worked so well for me: When you think about it, someone might see it as a few hours on the weekends or something. How can you be productive? The reason it works so well is because there is so much technical expertise that I can take advantage of and help me develop much faster than someone who needs to reinvent how to do things from scratch.

I joined full time in November 2021.

Connections are very important.

All those strange coincidences in my life finally came to an abrupt end. I don’t know if I’m doing anything special other than following what I’m really excited about. The most important to me are the people you work with. If you look at my career, even though I really like airplanes, I’ve been to space and I’ve been to AV, and it’s not necessarily because I’m so excited about AV or space, but because of the people I have to work with. with.

There are other AV companies but I would never consider working for anyone else because to me the people at Zoox are like family.

The leaders of the company, the CTO (Jesse Levinson) and CEO (Aicha Evans), are people I look up to and admire. They’re not just people who pay me every month.

The AV domain is the next frontier of robotics.

I have worked on many autonomous vehicles, but always to a fairly small extent. What we’re trying to do here in the AV field is extremely multidisciplinary. The entire robotics stack. You are perceiving, you are planning, you are estimating, you are simulating. Zoox also makes the vehicle, that is, all the hardware. It redesigns the entire robotaxis from the ground up.

If we can develop technology that can react faster than humans, that doesn’t get drunk, doesn’t get tired, and doesn’t fall asleep behind the wheel, that’s a great result of the robotic expertise I’ve developed.

The gain is proportional to the risk you take. If you always try to do something easy, your successes are not so great. I think self-driving car technology has some challenges, but we’ll get there. That’s a limit we’ll reach soon, and I think it’s definitely worth the struggle and hard work.

Read the original article on Business Insider