Navigation is about knowing where you are and where you are going. For autonomous vehicles, this is achieved through Simultaneous Localization and Mapping (SLAM), which allows a system to map its surroundings while estimating its own position at the same time. At Sensrad, we address this challenge with a fully radar-based SLAM solution.
In Lewis Carroll’s Alice’s Adventures in Wonderland, there is a well-known exchange:
“One day Alice came to a fork in the road and saw a Cheshire Cat in a tree.
‘Which road do I take?’ she asked.
‘Where do you want to go?’ was his response.
‘I don’t know,’ Alice answered.
‘Then,’ said the Cat, ‘it doesn’t matter.”
While the scene touches on a timeless human question about purpose, every autonomous vehicle must confront a more practical version of the same dilemma: Where am I, and where am I going?
At Sensrad, we work to answer these questions by introducing our new Simultaneous Localization and Mapping (SLAM) solution. SLAM is a widely used technique in autonomous vehicles and robotics, enabling a system to map its surroundings and estimate its own position within that map at the same time.
In the video below, we demonstrate the solution in action. It is a fully radar-based approach that combines the point cloud from Hugin D1 with key components from our perception stack, Oden. As shown, the map is built incrementally as the vehicle explores new areas. When the vehicle returns to the starting point, you can first observe that the odometry has accumulated drift, meaning the estimated pose is no longer perfectly aligned with the original start position. The SLAM algorithm then detects a loop closure, allowing it to correct the accumulated drift and re-align the trajectory so the system again recognizes that it has returned to the same physical location. The system continues to search for loop closures continuously to ensure the robot maintains a robust understanding of where it is over time.
So, if you have an autonomous vehicle that does not have the answers to life’s big questions, contact Sensrad for more information.
