Industrial PhD student – Multi-trailer Motion Estimation

WHO ARE WE?
We at Volvo Group are constantly moving and changing to be one step ahead in this technology journey. Within Volvo Group Trucks Technology, we are always adapting and pushing ourselves to be able to develop new breakthrough transport solutions. We strive to be more energy efficient, more sustainable and safer for society.
Our organization is built by engaged people and teamwork. We are a truly global company and we believe in the advantage of diversity. Together we create a workplace that brings the best out of everyone and this is where you fit right in.


Within the Technology Stream Vehicle Motion and Energy Management, we develop system solutions and functionalities in the area of vehicle safety, dynamics, driver assistance and motion management. Now you have the possibility to join a stimulating and dynamic global work environment, as an Industrial PhD student in the area of Multi-trailer motion estimation.


BACKGROUND
The vehicle combination trailer is in the future assumed to be its own units and is assumed to be able to carry its own energy storage with own propulsion and thus opens up for active driving and control through the utilization of auto coupling of trailers.


With demands for increased efficiency and reduced energy consumption, we move towards heavier and longer vehicle combination, so called multi-trailers. Meaning that several trailers are connected, giving more articulation points to keep track of.
Additionally, with an increasing degree of automation, the requirements also increase for the vehicle itself, at any moment, to have precise control of its various parts, e.g., relative positioning, speed and acceleration, i.e., current dynamic state of the multi-trailer combination.
This is made possible by putting a multitude of sensors on the vehicle that, at a constant rate, provide noisy observations of how the different vehicle parts move. These measurements are then refined by combining them with knowledge of how vehicles move to make an improved estimate of the vehicle's dynamic state.


However, this is a complex and challenging problem. Noise in the sensors and limitations in the models introduces misconceptions and uncertainties about the dynamic state of the vehicle. For automation of long vehicle combinations, these types of errors and uncertainties can have major consequences, even if they may seem relatively minor. It is therefore of the utmost importance to produce accurate state estimates with a reliable uncertainty description such that the system gets a good "feeling" for where each vehicle in the combination is located and the system can, like a human driver, adapt how the vehicle is controlled accordingly.


WHAT EXCITEMENT DO WE OFFER?
In this PhD project, you will study how to improve the uncertainty description of the dynamic state estimate of the multi-trailer vehicles to realize safe automated driving of long vehicle combinations in complex traffic environments. You will address this by identifying the needed sensor platform, develop novel estimation methods that place greater emphasis on reliable uncertainty description and explore opportunities to use data (machine learning) to train methods/models that can describe the complex nature of the system.
The work is conducted in cooperation with a twin industrial PhD student focusing on the vehicle control part of the problem.


The project is expected to provide knowledge to be used by the heavy vehicle industry to produce world-leading transport solutions.


Volvo Trucks is the main applicant and provides industrial delivery, where Chalmers University of Technology participates through academic supervision of the doctoral student and senior researchers. The industrial PhD period is about 4.5 years.


In this position You will become a researcher and technical expert for Volvo and, after graduating as PhD, become Volvo’s expert in developing the vehicle motion control design of commercial heavy vehicle combinations for 2030.
During the project, you will develop novel state-of-the-art state estimation methods that combine classical model-based approaches with data-driven models that address the real-world problem of automating longer vehicle combinations.
The work is expected to result in academic papers that are published at conferences and in high-impact journals as well as patentable inventions.


WHO ARE YOU?
You should preferably have more than 3 years of hands-on experience in Bayesian statistics, advanced control systems, robotics, or automotive systems and especially vehicle motion control and dynamics.
Knowledge in sensors & actuators for motion and real-time systems is required for the role. A good understanding of software development and the related environment is important in this role.


You have a deep interest to figure out how things work, both in theory but also practically in vehicles. In this You are eager to take ownership of own area and deliveries and thereby take accountability.


We believe you are creative and have the mindset to constantly learn and improve to have the best solutions for our customers.
A customer-oriented attitude is in your nature, you care about quality, allow yourself to be inspired, have a “can do” attitude and take pride in your work.


You have a positive outlook and collaborative mindset. As a person, you are a team player with a positive mind-set and you know the various different parts of application development.
Being resilient is important, able to rebounding from setbacks and adversity when facing difficult situations.


The ability to effectively build formal and informal relationship networks inside and outside the organization is a needed for the position.
You know how to communicate effectively and are able to convey a clear understanding of the unique needs to different audiences.