Getting to Know Wayfinder’s Head of Machine Learning, Husam Abu-Haimed
What were you working on before you joined Acubed?
Early in my career, I focused on Electronic Design Automation (EDA) at NVIDIA, Cadence and Synopsys. With a growing interest in artificial intelligence and machine learning, I started working in ad targeting for Google. But I was far more interested in autonomous vehicles, which drove my moves to Cruise and XPENG, where I built AI and ML models for autonomous driving.
Why did you join the Acubed Wayfinder team?
I was working in the automotive industry, and aerospace wasn’t on my radar then. It wasn’t until I was approached by a recruiter that I learned about Acubed. I was very interested when I heard more about the work Wayfinder was doing and the opportunity to work on autonomous flight systems. When dealing with cars, the biggest challenge is people, whether they’re other drivers or pedestrians crossing the street. With aerospace, the focus is entirely on safety, which requires higher accuracy within the algorithms. It means holding ourselves to a higher standard to meet those safety needs.
What are you working on now, and how does it show up in your day-to-day work?
AI is an exciting industry, especially as it’s applied in aerospace; it moves fast and is constantly evolving. During my day, I meet with our team to discuss issues we’re working on, and I write a lot of code. I also read a lot of recent research papers to stay up-to-date on the industry. And those research papers act as a catalyst to help our team test new ideas and improve our performance.
Some of my current activity is around the following:
- Perception: Developing AI models that analyze images taken by cameras on our planes that perform tasks including detecting the runway as the plane approaches the airport and detecting obstacles on the runway. This detection must happen in real time and meet the highest level of accuracy.
- Localization: Developing models that rely only on cameras and inertia sensors to estimate the current 3D position of the plane relative to the runway with very high accuracy.
- Safety Standards: Everything we build needs to meet the aviation industry’s safety standards. I developed a new framework for quantifying and measuring the robustness and safety of ML models. I’m working with the European Union Aviation Safety Agency (EASA) and, soon, with the Federal Aviation Administration (FAA) on using this framework to certify our models.
Our recent achievements include:
- Safety and Certification: We developed a new framework for assessing the safety and robustness of ML models that we expect to improve the certification process significantly. Our framework received support from parties within and outside of Airbus.
- Perception: Our detection models achieved very high levels of accuracy while being an order of magnitude smaller and faster than standard detection models in the industry.
What is the biggest professional challenge you’ve encountered so far?
Collecting data is the biggest challenge I’ve faced since transitioning to aerospace. With a car, it’s easy to hop in and go for a drive and collect data, but capturing data from an airplane requires a lot more work and coordination. Also, we need to collect data in all weather conditions, including degraded conditions like clouds, rain, storms, etc., which we sometimes have to chase in California and in other parts of the country.
What advice do you have for someone interested in joining Acubed?
Acubed is just the right mix of a well-established company with a startup culture—that’s what I like the most about it. As part of Airbus, one of the world's most well-known and innovative companies, we’re able to work on the most cutting-edge technology, especially in AI and software engineering in aerospace.
With regard to Wayfinder specifically, the people I get to work with are very smart; they have high standards and are really good at what they do. I find that a powerful and exciting environment to be a part of. Be ready to work with very smart people.
What is one thing you like to do outside of work?
If I’m not at work, I’m likely reading at a coffee shop. My work is my passion, and I’m always trying to learn more and stay up-to-date in the field.
If you’re interested in joining our team and building the future of flight, do reach out via our open roles here.