Master Thesis Project(s) within Autonomous Driving and Active Safety
Thesis Worker at Volvo CarsLooking for a master piece for your master thesis project? Together, we will work towards making the future Autonomous and Connected with human centric technology. Autonomous cars will reshape traveling and our future lifestyle - would you like to be a part of our team influencing this change?
We are looking for driven and motivated students interested in pursuing their master thesis within the development of self-driving cars during the spring term 2021.
The strategy of Volvo Cars is to emphasize the lifestyle of freedom to move with Autonomous Drive by making transportation personal, sustainable and safe. At the department of Safe Vehicle Automation, we embrace this paradigm shift in the automotive industry, which is moving towards the deployment of autonomous vehicles at a very fast pace. Our approach to Autonomous Driving at Volvo Cars is unique by focusing on the people and their safety and not just the technology, while at the same time working towards the vision of providing 1 week quality time per year through a new Volvo Car by 2025.
Within our team of over 400 engineers at Safe Vehicle Automation, we are offering a broad range of master thesis projects. Since our core value is everything we do starts with people, we are also open to consider your ideas and proposals.
Who are you?We are looking for candidates with excellent academic records who are open, innovative, driven and team-players. Because of the interdisciplinary nature of our work, we are extending our search to a broad range of competences. If you think that you have what it takes to help us in our journey to deliver a safe, human-centric, autonomous drive technology, read below on what we do & the various areas we can offer the thesis work in! Following are the various areas/domains we offer thesis work in. There are several thesis projects in each area. Please specify in your application cover letter, the domain(s) of your interest.
Domain 1: Data Driven Development of Autonomous Drive
The thesis projects in this area deal with exploring the capabilities of Machine Learning and Artificial Intelligence for the development and verification of Self Driving Cars. There is considerable amount of work ongoing in the field of Data Analytics to ensure the use of extensive data to make the vehicle performance better. The projects here will focus on generating trained models for annotation, driving behaviors, object classification, image manipulation & formulation etc. using various machine learning techniques. Keywords: Computer Vision, Active Learning, Annotation, Data Driven, Neural Networks, Big Data
Domain 2: Data Driven Verification & Validation of Autonomous Drive
For vehicles to reach high levels of automation, data driven development and verification is a huge challenge and necessity. The initial step towards ensuring this is to carry out a well quantified and good quality data collection using test fleet vehicles. For driver assistance systems, the traditional methods of validation and verification involved driving test kilometers on test grounds and public roads. However, for higher levels of automation, the amount of test driving to prove safety of AD becomes unfeasible – instead, scenario-centric simulation-based testing is envisioned to replace the unachievable goal of test driving billions of kilometers for validation purposes. The thesis projects in this area will deal with developing methods to identify and classify traffic scenarios from driving data using various design of experiments and optimization; applying statistical methods to estimate the exposure rate to rare critical scenarios never seen in test driving; automated classification of annotated data and research methods on how to facilitate good data collection. Keywords: Scenarios, Coverage, Validation, Corner Cases, Edge Cases, States, Transitions, extreme value theory, Optimization, Parameter Space, Data sets
Domain 3: Modelling and Simulation for Development and Verification of Autonomous Drive
This area deals with fundamentals of vehicle localization, prediction, path planning and control. This includes the development and implementation of advanced features and functions for Driver Assistance, Collision Avoidance, Connected Safety and Autonomous Drive. Some examples are Pilot Assist and Animal Detection. The projects in this area will deal with developing driver models; controllers for path prediction and algorithms for path following and traffic generation. Keywords: Collision Avoidance, Optimization, Latency, Self-Driving Cars, Future Mobility
Before a new function is deployed on a production vehicle, it must be tested virtually in simulation environments. The existing methods used for testing Active Safety functions are not sufficient for the testing of future AD cars. Therefore, we are constantly developing new simulation platforms to ensure both high quantity and quality of virtual verification. The projects in this area focus on research tailored to verification of existing models, generation of synthetic data sets and development of mixed reality environments. Keywords: Simulators, Traffic Simulation, Computer Vision, Cluster, Target Platforms, IPC, SDK, Synthetic Data, Rendering, Mixed Reality, Augmented Reality
Domain 4: Sensors & Sensor Fusion Development and Verification
The safety of our cars relies heavily on the performance of multiple sensors such as Radars, Cameras, LIDAR and Ultrasonic Sensors, whose readings are fused in real time to yield the holistic representation of the surrounding of autonomous vehicle validation of the performance of single sensors and the sensor fusion is done by comparing their outputs to high-accuracy data from a reference sensor system. The thesis projects in this area will deal with deploying novel methods to improve the quality of reference sensor data in order to generate more accurate representation of surroundings detection of the objects and scenes that confuse the sensor system (“anomalies”), as well as development of modular and sensor agnostic sensor-fusion systems. Keywords: Sensors, Sensor Fusion, SLAM, Reference Sensor, Ground Truth
Application and contactDoes this sound like your next challenge? Below are some practicalities you need to be aware of:
- Proposed thesis work period: 18th January 2021 to 25th of June 2021 (dates can be flexible with +/- 7 days)
- Academic credits: equivalent to 30 ECTS
- Number of students: 1-2 students per project (2 preferred)
Welcome with your application by submitting your resume, cover letter (including which area you would like to work and why) and grades/transcripts via the link below no later than 22nd November 2020. We will be continuously reviewing the applications and selecting the candidates, so apply as early as you can! Note that we do not accept any applications via e-mail. If you have any questions regarding the position you are welcome to contact Siddhant Gupta (email@example.com). For questions about the recruitment process, please contact Andreas Antefelt (firstname.lastname@example.org).
Who are we?Everything we do starts with people. Our purpose is to provide freedom to move, in a personal, sustainable and safe way. We are committed to simplifying our customers’ lives by offering better technology solutions that improve their impact on the world and bringing the most advanced mobility innovations to protect them, their loved ones and the people around them.
Volvo Cars’ continued success is the result of a collaborative, diverse, and inclusive working environment. The people of Volvo Cars are committed to making a difference in our world. Today, we are one of the most well-known and respected car brands, with over 40,000 employees across the globe. We believe in bringing out the best in each other and harnessing the true power of people. At Volvo Cars your career is designed around your talents and aspirations so you can reach your full potential. Join us on a journey of a lifetime as we create safety, autonomous driving and electrification technologies of tomorrow. Gothenburg, Sweden