30 credits - Estimation and Tracking of Vulnerable Road Users Using Collaborative Perception

A thesis project at Scania is an excellent way of making contacts for your future working life. Many of our current employees started their career with a thesis project.

Background:
In complex urban scenarios, the on-board sensors of Connected and Autonomous Vehicle (CAV) typically provide a limited understanding of their surroundings due to the occlusions created by other vehicles, limited sensor range and other obstacles. These areas are typically are densely populated with vulnerable road users, such as pedestrians, cyclists, and motorcyclists. A potential solution is to share sensor data from other external sensors, such as road side units or other connect vehicles, through vehicular communication.

Accurately estimating the state and tracking the movements of these vulnerable road users, with safety guarantees, is a critical requirement for autonomous vehicles. Achieving this capability, enhances safety, improves situational awareness, and enables effective navigation in dynamic environments. However, integrating data from multiple sensors introduces challenges in maintaining accurate estimation and tracking. To provide safety guarantees for vulnerable road users, the objective is to use deterministic methods for estimation and tracking. 

As a master thesis student, you can interact and learn from engineers working with various fields of autonomous systems.

Target:
The target is to design a framework that effectively and reliably can predict the most likely object association and object discrimination of other pedestrians in simple traffic situations. This framework should be able to support decision making on board autonomous vehicles.

Assignment:
The assignment is divided into these sub-tasks: 
1. Investigate deterministic methods for estimation and tracking of road users.
2. Analyze the factors that contribute to uncertainties in collaborative perception. 
3. Design and implement a framework that can adapt to dynamically changing scenarios.
4. Test the work in simulation and/or in real experiments using research and prototype vehicles.

Education:
Master (civilingenjör) in computer science, robotics, engineering physics, electrical engineering, or applied mathematics, preferably with specialization in applied estimation, control theory, optimal control or optimization. Knowledge of reachability analysis, system modeling and programming are a plus.

Number of students: 1-2
Start date: January 2025  
Estimated time needed: 20 weeks
 
Contact persons and supervisors:
Vandana Narri, Industrial PhD student in Situational Awareness for Autonomous Vehicle,
vandana.narri@scania.com , 08 – 553 822 97

Application:
Enclose CV, cover letter and transcript of records.

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