Z-ENG: Line association using neural network

Félév: 2024-2025 ősz

Kategória: Szoftver

Téma leírása

One of the most important engineering tasks in the development of autonomous vehicles is to create a high-quality representation of the vehicle's real-world environment, as it is necessary for the robot to be able to make ideal decisions and navigate without external assistance. Although some details of the implementation may depend on the specific functionality, many general steps can be identified when considering such a solution. Such task is the detection, tracking and fusion of surrounding objects in time and space. These objects, which in real life often have complex shapes, can be described by simple geometric shapes, avoiding unnecessary overcomplication of algorithms and helping to achieve optimal runtimes. A common such generic shape is a line connecting two points, which can represent, for example, the boundary of a parking space or even a dashed line separating lanes.

To build the environment, these lines need to be traced throughout the measurement - this involves associating objects measured in consecutive frames. In practice, this means that for a given line measured at time 't' along a certain calculated quality, it is possible to determine for each line at time 't + 1' the probability that it represents the line measured at time 't'. The algorithm may identify only one such line pair, or none if none of the association probabilities of the lines measured at time 't + 1' reaches a minimum level.

This can be implemented using classic solutions (Nearest Neighbor, Global Nearest Neighbor, etc.) or neural networks.

The student's task is to implement the association step using a neural network: determine the optimal structure of the input, search for suitable models of the network and select the ideal candidate. It is also responsibility of the student to generate the training data (training-validation-test-set), implement the selected model, train, and evaluate it focusing on accuracy and runtime (relative comparison with a classical solution) in Python.

The student will be assisted by the Continental AI Development Center staff to solve the problem.

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