Z-ENG: Pathfinding and planning of self-driving vehicles using known algorithms

Félév: 2024-2025 ősz

Kategória: Nincs megadva

Téma leírása

One of the key challenges in the dynamically growing field of self-driving cars is the selection and application of optimal pathfinding algorithms for vehicles. Autonomous vehicles must efficiently navigate through varied and often unpredictable environmental challenges, thereby planning safe and efficient routes to reach their destination.

The pathfinding problem requires knowledge of a static and dynamic environmental model, in which a route can be computed based on a partially or fully known map given the vehicle's kinematic properties and a predefined objective function.

The aim of the project is to develop and implement a pathfinding and planning system based on A* (A-star), RRT (Rapidly-exploring Random Tree) or other popular algorithms. The student will be tasked with developing an efficient and reliable route planning system for a given autonomous vehicle, taking into account various environmental factors and obstacles. The expected outcome is the implementation and evaluation of a software that allows autonomous vehicles to adaptively and flexibly select the optimal route to navigate efficiently and safely in diverse traffic environments. The work includes a literature survey exploring state-of-the-art pathfinding methods, a qualitative and quantitative comparison of methods, and an insight into algorithms used in real-world automotive applications such as automatic parking or collision avoidance // safe corridor for high-speed manoeuvres.

To solve this task, the student will receive assistance from the employees of the Continental AI Development Center.

If you are interested in the topic, be sure to contact Dávid Sik by email before applying, indicating the selected topic, training level, major and the planned project subject.

Külső partner: Continental Autonomous Mobility Hungary

Maximális létszám: 1 fő