Problem statement
In this Master Thesis in Software Engineering we will focus on developing a Proof of Concept for an AI-driven navigation system for autonomous drone flight at low altitude. One of the major challenges in this domain is achieving safe and reliable navigation under constraints such as unreliable or absent GPS signals dynamic obstacles limited onboard computational resources and restricted visibility.
To operate effectively in such environments we must rely on onboard sensors such as cameras IMU and LiDAR and combine them through sensor fusion computer vision and intelligent motion planning. In addition satellite map data can be integrated as a complementary prior to increasing environmental awareness and provide geographic context when GPS information is weak or missing.
Furthermore traditional rule-based navigation algorithms often fail under these conditions making it necessary to explore a new AI-driven approach that can adapt in real time while ensuring safety energy efficiency and robustness during low-altitude operations.
Proposed solution
The proposed solution is to develop an AI-driven navigation system as a Proof of Concept (POC) that enables a drone to operate safely at low altitude even when GPS signals are unreliable or absent.
The system will combine:
- Deep learning-based motion planning allowing the drone to adapt its trajectory in real time
- Computer vision methods for detecting obstacles and understanding the surrounding environment
- Sensor fusion integrating data from IMU camera satellite map data and optionally LiDAR to maintain accurate localization without GPS
- Simulation based validation where all algorithms will be trained and tested in environments such as AirSim PX4 or Gazebo before any real-world deployment
Qualifications :
- An student in Information Technology Computer Science Electronics Mathematics or Physics.
- Have relevant coursework or knowledge in data science control systems and AI.
- Experienced with or have at least basic programming knowledge in Python C or similar languages.
- Self-driven able to take initiative and move the project forward independently.
A person with team spirit social skills and genuine curiosity for robotics AI and autonomous systems.
Additional Information :
Supervisors: Ibrahim Yilmaz
We encourage to have a team of 2 master thesis students working on the thesis.
Please note: Only applications from students located in the area of Lund are accepted.
Remote Work :
No
Employment Type :
Full-time
Problem statementIn this Master Thesis in Software Engineering we will focus on developing a Proof of Concept for an AI-driven navigation system for autonomous drone flight at low altitude. One of the major challenges in this domain is achieving safe and reliable navigation under constraints such as...
Problem statement
In this Master Thesis in Software Engineering we will focus on developing a Proof of Concept for an AI-driven navigation system for autonomous drone flight at low altitude. One of the major challenges in this domain is achieving safe and reliable navigation under constraints such as unreliable or absent GPS signals dynamic obstacles limited onboard computational resources and restricted visibility.
To operate effectively in such environments we must rely on onboard sensors such as cameras IMU and LiDAR and combine them through sensor fusion computer vision and intelligent motion planning. In addition satellite map data can be integrated as a complementary prior to increasing environmental awareness and provide geographic context when GPS information is weak or missing.
Furthermore traditional rule-based navigation algorithms often fail under these conditions making it necessary to explore a new AI-driven approach that can adapt in real time while ensuring safety energy efficiency and robustness during low-altitude operations.
Proposed solution
The proposed solution is to develop an AI-driven navigation system as a Proof of Concept (POC) that enables a drone to operate safely at low altitude even when GPS signals are unreliable or absent.
The system will combine:
- Deep learning-based motion planning allowing the drone to adapt its trajectory in real time
- Computer vision methods for detecting obstacles and understanding the surrounding environment
- Sensor fusion integrating data from IMU camera satellite map data and optionally LiDAR to maintain accurate localization without GPS
- Simulation based validation where all algorithms will be trained and tested in environments such as AirSim PX4 or Gazebo before any real-world deployment
Qualifications :
- An student in Information Technology Computer Science Electronics Mathematics or Physics.
- Have relevant coursework or knowledge in data science control systems and AI.
- Experienced with or have at least basic programming knowledge in Python C or similar languages.
- Self-driven able to take initiative and move the project forward independently.
A person with team spirit social skills and genuine curiosity for robotics AI and autonomous systems.
Additional Information :
Supervisors: Ibrahim Yilmaz
We encourage to have a team of 2 master thesis students working on the thesis.
Please note: Only applications from students located in the area of Lund are accepted.
Remote Work :
No
Employment Type :
Full-time
View more
View less