30 hp - Master's Thesis: Data-driven Multi Modal Object Tracking

Are you passionate about the cutting-edge technology driving the future of automotive safety and autonomy? Do you have a keen interest in LiDAR, camera, and radar sensors and their role in advancing vehicle perception systems? If so, we invite you to embark on an exciting research journey with us by pursuing your Master's thesis in the field of perception.  

Background:

At Scania, we believe that autonomy is the future of logistics, and we are committed to being at the forefront of this transformation. 

The application of autonomous technology for autonomous hub-to-hub transport is steadily gaining pace. With the permission of the Swedish transport authority, Scania is trialing autonomous trucks in open-road conditions in Sweden. The customer advantages are clear, as the use of autonomous hub-to-hub truck solutions can provide significant benefits for logistics companies, resulting in greater efficiency, lower costs, improved safety and tracking, and reduced environmental impact. 

Target/scope: 

The primary target of this Master's thesis is to develop, analyse and evaluate a Multi Object Tracking solution system utilizing multimodal sensors like LiDAR, camera & radar for automotive applications. The research aims to address critical challenges in the field of autonomous driving and contribute to the enhancement of vehicle perception and safety.  

Objectives: 

1. Literature Review: Conduct an extensive review of existing methodologies and technologies in multimodal multi-object tracking. This includes exploring various sensor modalities, data fusion techniques, and state-of-the-art algorithms for object detection and tracking. 

1. Module Implementation: Develop and implement a tracking module that leverages the insights gained from the literature review. The module will integrate multi-view detection and tracking strategies, focusing on enhancing robustness and accuracy in diverse environments. 

1. Evaluation: Test the implemented module on multiple public datasets to evaluate its performance against existing benchmarks.  

Join us in pushing the boundaries of automotive technology, improving safety, and paving the way for the future of autonomous driving. 

Applicant Requirements: 

• Enrollment in a Master's program in fields such as Robotics, Computer Science, Electrical Engineering, Machine Learning or Automotive Engineering. 

• Strong programming skills (e.g., Python, PyTorch, C++) and a background in computer vision or robotics are advantageous. 

• Enthusiasm for research and the drive to tackle complex challenges in autonomous vehicle technology. 

Education/line/direction: 

Number of students: 1 
Start date for the Thesis project: Jan 2025
Estimated timescale: 5 months 

Contact person and Supervisors: 

Sina Sharif Mansouri, Perception Technical Leader at EEARP, sina.sharif.mansouri@scania.com

Alejandro Sarmiento, Perception Development Engineer at EEARP, alejandro.sarmiento.gonzalez@scania.com

Application: 

Your application should contain CV, motivation letter and copies of grades 

A background check might be conducted for this position. We are conducting interviews continuously and may close the recruitment earlier than the date specified.