Master thesis proposals - external

Ericsson Research Looking for a thesis project during Spring, starting in January 2025? Did you know Ericsson Research develops research on themes related to robotics and AI? Take a look at the current projects we have open:

Trajectory Tracking over Lossy Networks: Looking to push the boundaries of mobile robot control in real-world applications? Join us for an exciting MSc Thesis project at the Decision & Control unit at Ericsson Research. As mobile robots become increasingly common in industrial and public sectors, ensuring their safe and efficient operation is important.

In this project, we aim to develop a trajectory tracking controller for mobile robots that utilizes modern communication networks to leverage external processing power, such as cloud or edge servers, for executing complex control algorithms.

When transmitting control signals and measurements over the network between mobile robot and remote controller, the remote controller needs to account for potential network issues, such as packet loss , for a safe and efficient tracking of a trajectory.

If you have a passion for control theory, programming skills, and a desire to drive innovation in mobile robot control, we encourage you to join our team and contribute to cutting-edge research that builds upon the foundation of previously published work from Ericsson Research. Prior knowledge of model predictive control is beneficial, but not necessary. Apply now and be part of shaping the future of mobile robot control!

Requirements

All the projects require some common skills:¶
* Strong ability to formulate problems and solve them, independently and in groups.
* Programming skills, preferably in Python or C/C++.
* Strong communication skills in written and spoken English.
Contact

David Umsonst - david.umsonst@ericsson.com

AI Decision Making for Networked Robotics: The Cyber-Physical Systems team at Ericsson Research is looking for students to work on a Master's Thesis project on AI Decision Making for Networked Robots. The project will take place between January 2025 and June 2025.¶

The suitable candidate has an interest and experience in areas related to Machine Learning and Robotics, such as machine learning, optimization, control theory, and path planning. This is an opportunity for you to work on an international and diverse team that values a speak-up and inclusive environment. We believe in the power of diversity and encourage applicants from diverse backgrounds to bring their unique perspectives and experiences to our team.¶

With the advances of 5G and 6G technologies, the industry has been pushing the boundaries of control of mobile robots over a network connection. The purpose of this project is to investigate new machine learning algorithms that can provide fast and reliable cellular network information to mobile robots. The main goal is to develop new representation and reinforcement learning algorithms that can enable mobile robots to construct optimal path planning algorithms when operating in a changing environment.¶

Requirements¶


* Interest and experience in areas related to Machine Learning, Optimization, and Robotics;
* Ability to formulate problems and solve them independently and in groups;
* Experience in Python (PyTorch is a bonus);
* Fluent in written and spoken English.
Contact¶

Christos Mavridis - mavridis@kth.se¶

Fernando Barbosa - fernando.dos.santos.barbosa@ericsson.com¶

¶

ABB Corporate Research Center ABB Corporate Research Center is offering a position for generating behavior tree policies for robots by combining planning and learning together with a user interface for human input and feedback. Please apply by 18th of December!

https://careers.abb/global/en/job/89031397/Thesis-Work-for-Behavior-Tree-Policy-Editor

Marcus Wallenberg Laboratory for Sound and Vibration Research A project in applying LLMs to literature search:

LLM_Project_MWL

ABB Robotics ABB Robotics are offering two positions in the motion control group for spring 2024 for exploring the intersection of AI/ML and robotics. Please apply by 13th of November!

https://careers.abb/global/en/job/89028627/Thesis-Work-Robotics-R-D-Motion-Control-generative-AI

https://careers.abb/global/en/job/88926384/Thesis-Work-Robotics-R-D-Motion-Control-machine-learning

Silo AI Silo AI is Europe's largest private AI lab. We partner with industry leaders to build smart devices, autonomous vehicles, Industry 4.0, and smart cities. Silo AI recently launched SiloGen, which is now part of a groundbreaking consortium aimed at building the world's largest open-source Large Language Model. With SiloGen, our specialized arm in generative AI, we are redefining the future of AI and ensuring European digital sovereignty.

This spring we offer two exciting Master projects on Generative AI. Please follow the instructions in the descriptions below on how to apply. Welcome with your application!

Adaptive Generative Agents in Dynamic Environments

Stable Diffusion for Spatio-Temporal Consistent Generations

Hitachi Energy The electrical power system is evolving due to e.g. an increasing amount of renewables and distributed power generation. FACTS (Flexible AC Transmission Systems) devices can assist with this evolution by improving the power quality and reducing the risk of system disconnections.

In this master thesis proposal, we want to investigate the application of machine learning to a FACTS device. The device itself is based on a power electronic converter and has its own local controller. The performance, in terms of efficiency and stability, is dependent on modelling assumptions which may to a certain extent deviate from reality. Here, the objective would be to improve the performance of the FACTS device, by application and integration of a suitable machine learning method into the control. The master thesis is planned to start in January 2023.

Contact: Jonathan Hanning, jonathan.hanning@hitachienergy.com

For more details, see: https://www.hitachienergy.com/career/jobs/details/SE53908798_E1

Ocean Infinity Ocean Infinity has a number of proposals for thesis projects. These involve problems within underwater perception, sonar and robotics. For example:

* Target Identification and classification from sidescan sonar data.
* MultiBeam Echo Sounder (MBES) image alignment and outlier rejection.
* Localization of AUV swarm (SLAM loop closing)
Please contact John Folkessn johnf@kth.se for more information.

Arriver Sweden Knowledge Distillation for Autonomous Driving

Description

CNN-based association for Multiple Object Tracking

Description

Univrses Cross-city domain shift is the cause of a 25-30% metrics drop of normal Deep Learning predictors. Change of weather and lighting conditions might even result in more disruptive effects. Therefore, to provide a robust and accurate output, the predictor would need to be trained on every possible deployment condition, e.g. multiple cites, districts, seasons, kinds of weather, cameras pose and intrinsics. This largely reduces the scalability of AI solutions both in terms of costs and deployment time. Recent Unsupervised Domain Adaptation (UDA) methods proved to be very effective in mitigating (or even solving) these shortcomings.

Contact: Pier Luigi Dovesi <pier.luigi@univrses.com>Application link, full description and details: https://career.univrses.com/jobs/1401972-master-thesis-project-unsupervised-domain-adaptation

SkyCraft AB Master projects in CV and ML on powerline detection

Description

Viscando AB Projects within deep learning, signal processing and modelling for traffic and autonomous vehicle safety

Description

Babyshop Group Leveraging transfer learning for multi-label attribute prediction in fashion images, using deep learning

At Babyshop Group, there exist tens of thousands of images of children’s apparel. Currently, new items are labeled by hand, where each item has multiple attributes, eg. color, category, pattern, neckline, and style, etc. Since the workload of this manual task is immense, a need for a support system is high. In literature, a multitude of previous work has been done in regards to multi-label attribute prediction on fashion clothing, most notably DeepFashion and iMaterialist Fashion. Here, deep learning models have been trained on hundreds of thousands of labeled images to predict corresponding attributes, which has proven highly successful. However, almost all of these images are of adult fashion, with very little emphasis on childrens’ fashion. The question then arises, is it possible to combine the pre-trained models from previously mentioned multi-label attribution prediction models that are trained on almost exclusively adults’ fashion, together with the learnings from transfer-learning frameworks - in order to successfully perform multi-label attribution prediction on childrens’ fashion?

Required qualifications: MSc studies in Computer Science, Machine Learning, Computer Engineering, Mathematics, Physics, or related field; Good understanding of machine learning frameworks such as Keras, TensorFlow, PyTorch, Scikit-Learn, and/or Spark; Proficiency in Python and Git; Knowledge about data wrangling and data munging, using SQL, Pandas, and Numpy.

Web version of the proposal with instructions on how to apply.

Time frame: from early January to mid-June.

Contact: Marcus Svensson (marcus.svensson@babyshop.se), Data Scientist at Babyshop Group