Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


High performance path planning using GPUs for autonomous racing



Alexander Liniger, Sandro Merkli

In recent work we developed a control method for autonomous racing of two cars, the method is based on two steps, first both cars generate a set of possible trajectories and in a second step the collision between the two set of trajectories are determined. Using this information the two players then decide how to drive. As the set of possible trajectories grows exponentially in the horizon, and the collision checks are combinatorial in the number of trajectories the problem can only be solve for short horizons. The goal of this project is to investigate if parallel computation can help to speed up the computation and therefore allow for longer horizons.

The student should have good programming skills and knowledge in parallel computation with GPUs using Cuda or similar languages.

Weitere Informationen


John Lygeros

Art der Arbeit:
Anzahl StudentInnen:
Status: done
Semester: Summer 2017