Self-Driving Car Without Sensors: An Innovative Solution For a GPS-Denied Environment

Are you in need of a data science consultancy that can provide innovative solutions to unique challenges? Look no further. Our team was approached by a US Army base with a complex problem: they needed autonomous vehicles to practice shooting against moving targets, but the equipment typically used to make vehicles autonomous (such as sensors and GPS) was too expensive to be shot at. Additionally, the vehicles needed to operate in a GPS-denied environment.


  • Convert an old Humvee a Self-Driving Car
  • The vehicle needs to identify and avoid obstacles that appear in its path
  • Don’t add expensive sensors to the vehicle, which will be destroyed.
  • Let’s move all the equipment outside the vehicle
  • Operate in a GPS denied environment.
Owl Flying Towards


After consulting with other AI experts, that were more worried about what model would use rather than how it would benefit the client. They decided to stay with us, because our pragmatic approach that is 100% focused in delivering a successful project.


We were able to meet these challenging requirements in a cost-effective and reliable manner, delivering a successful project for our client. Our solution was to place radars along the path to detect the vehicle and its surroundings, rather than detecting the environment from the car. We also designed a processing pipeline to detect the vehicle with great accuracy, solving the GPS-denied environment problem. The radars also provided the necessary information to detect other moving obstacles, allowing us to avoid them.

The Results


Sub-meter Accuracy

We beat standard GPU accuracy with our system, using only the radars


Obstacle Avoidance

Our approach has proven to be reliable, and hasn't registered any crash up until this point

100% Flexible System

The system has been designed in such a way that new features can be easily integrated

Download in PDF format

Iu Ayala | CEO & Founder

Iu Ayala | CEO & Founder

I am a data scientist and robotics engineer with over 8 years of experience in delivering successful and impactful solutions using supervised and unsupervised learning, algorithm design, and programming. As the CEO of Gradient Insight, a consulting firm that helps clients make data-driven decisions through the use of AI, I have a track record of delivering customized solutions across a range of industries. I am passionate about using data and technology to solve complex problems and am always open to discussing potential collaboration opportunities. If you have a project that could benefit from my expertise, please feel free to reach out and connect on LinkedIn.

Ready to harness the power of Data Science for your business?

Contact us today to learn more about how our team can help you achieve your data-driven goals!

Other Case Studies