Mater Thesis: Modelling combinational behavior of a truck and surround

Background of thesis project


Driving automation has a significant potential in improving the traffic safety by reducing the human errors. Volvo Group highly focus on the development of Advanced Driver Assistance System and Autonomous Trucks. Identifying various traffic driving scenarios that the trucks are exposed to and training the autonomous system to take safest and efficient actions in those scenarios are crucial and are many research ongoing in this field.
In this project, we aim to analyze the combinational behavior of a truck and surrounding vehicle and develop an autonomous driving controller which assists the truck to drive in a way that makes surrounding vehicles feel safe. For instance, a passenger car driver may not feel safe and try to change lane or slow down when the lateral gap with a truck in the next lane is too small.

Description of thesis work
The purpose of this thesis can be summarized as. Analyze the dataset containing images from surroundings of a long truck (See Fig 2) and extract the various states of truck and surrounding vehicles.
Model the behavior of surrounding vehicles based on that of the truck using supervised learning algorithms and/or reinforcement learning.
Develop a prototype of the driving controller.



This project will use advanced machine learning methods to solve problems within autonomous driving. The work will include programming, machine learning, control theory, numerical optimization and vehicle simulation. The work will be carried out at Volvo Group Trucks Technology, Sweden. The thesis is recommended for one or two students with a strong background in machine learning and Python/C++ with a good mathematical background.


Thesis Level: Master

Language: English


Starting date: January 2023


Number of students: 1 or 2


Tutor
Leo Laine – Volvo GTT
tel: +46 31 323 53 11
mail: leo.laine@volvo.com


Deepthi – Volvo GTT
tel: +46 72 847 67 65
mail: deepthi.pathare@volvo.com
https://youtu.be/aUNiVxmiJDE