Last Date 30th October 2024
Subject description
Current advancements in robotics leverage extensive datasets of robot trajectories, images, and language descriptions to train machine learning models, such as transformer models, enabling robots to execute common tasks like picking and placing. However, these models are predominantly trained on everyday tasks involving common objects, with vast datasets comprising hundreds of thousands of training episodes. In this project, we want to extend the capabilities of robots to domains such as healthcare an manufacturing, where data is scarce.
The research challenges can be divided into three themes:
Extending existing models: Investigate transferability and create smaller local models to enable learning of medical and industrial applications with limited training data.
Distributed intelligence: The current machine learning models cannot be executed locally on the robot system without suitable GPU. Therefore, the intelligence in the system must be distributed in a modular architecture across a communications network.
User-friendly interaction: The robot will interact with hospital staff and patients with non-technical background, which increase the need for clear communication and intuitive interfaces.
The focus of the PhD project will be robot learning. We will explore the latest developments in Robot Transformers and Large Language Models and you will be able to test your results not only in the robot lab but also at our partners Tetra Pak and the Lund University Hospital within the competence center NextG2Com.
Description of the workplace
The Department of Computer Science, Faculty of Engineering, Lund University, is currently accepting applications for a fully funded PhD position (4 years full-time), starting at the earliest convenience. We are seeking a candidate with a keen interest in Robotics, Intelligent Autonomous Systems and Machine Learning, focusing specifically on robot task learning.
The position is at Lund University’s Department of Computer Science within the research group Robotics and Semantic Systems (RSS) . The RSS division focuses on research and teaching in AI, Machine Learning, Robotics and Robotic Learning, Human-Robot Interaction, and Natural Language Processing. Together with the Dept. of Automatic Control, the division operates RobotLab LTH , which gives access to many types of robots.
You will be working in a team with other PhD students, and visits to partner universities such as MIT or Berkeley are possible.
The PhD position is part of the competence center NextG2Com – the next generation of communication and computation infrastructure and applications – which is coordinated by Lund University in close collaboration with industry and public partners and with funding from Vinnova .
Work duties
The main duties of doctoral students are to devote themselves to their research studies which includes participating in research projects and third cycle courses. PhD students in the competence center NextG2Com will cooperate closely with our industrial partners and other PhD students within the center by participating in shared projects, meetings and activities. The work duties also include teaching and other departmental duties (no more than 20%).
In addition to these general duties, you are expected to:
Participate in graduate school activities (courses, study trips, national events and conferences, etc), which includes regular travel.
Participate in activities (data collection, demonstration, integration) in the competence center NextG2Com.
Engage in the division’s internal activities (seminar series, reading groups, etc).
Contribute to the department’s and division’s efforts in undergraduate teaching.
Admission requirements
A person meets the general admission requirements for third-cycle courses and study programmes if he or she:
has been awarded a second-cycle qualification, or
has satisfied the requirements for courses comprising at least 240 credits of which at least 60 credits were awarded in the second cycle, or
has acquired substantially equivalent knowledge in some other way in Sweden or abroad.
A person meets the specific admission requirements for third cycle studies in Computer Science if they have:
at least 60 second-cycle credits at an advanced level with relevance for the research topic, or
an MSc in Engineering in Computer Science and Engineering, Electrical Engineering, Information and Communication Technology, Engineering Physics or Engineering Mathematics.
Additional requirements:
Very good oral and written proficiency in English.
Strong analytical skills
Good mathematical skills
Top grades in Machine Learning and Computer Vision
Knowledge and experience of Python and Linux
Very good and practical knowledge in ROS
Very good and practical experience with Robotic Arms.
The ability to work both independently and in small teams
Assessment criteria
Selection for third-cycle studies is based on the student’s potential to profit from such studies. The assessment of potential is made primarily on the basis of academic results from the first and second cycle. Special attention is paid to the following:
Knowledge and skills relevant to the thesis project and the subject of study.
An assessment of ability to work independently and to formulate and tackle research problems.
Written and oral communication skills.
Other experience relevant to the third-cycle studies, e.g. professional experience.
Other assessment criteria:
Good coding and implementation skills.
Experience with Transformer models and their applications to computer vision and robotics.
Consideration will also be given to good collaborative skills, drive and independence, and how the applicant, through his or her experience and skills, is deemed to have the abilities necessary for successfully completing the third cycle programme.
Terms of employment
Only those admitted to third cycle studies may be appointed to a doctoral studentship. Third cycle studies at LTH consist of full-time studies for 4 years. A doctoral studentship is a fixed-term employment of a maximum of 5 years (including 20% departmental duties). Doctoral studentships are regulated in the Higher Education Ordinance (1993:100), chapter 5, 1-7 §§.
Instructions on how to apply
Applications shall be written in English and include a cover letter stating the reasons why you are interested in the position and in what way the research project corresponds to your interests and educational background. The application must also contain a CV, degree certificate or equivalent, and other documents you wish to be considered (grade transcripts, contact information for your references, letters of recommendation, etc.)
Reference number PA2024/3006
Contact Volker Krüger, volker.krueger@cs.lth.se
Union representative OFR/ST:Fackförbundet ST:s kansli, 046-2229362
SACO:Saco-s-rådet vid Lunds universitet, kansli@saco-s.lu.se
SEKO: Seko Civil, 046-2229366
Apply:
https://lu.varbi.com/en/what:login/jobID:761315/type:job/where:4/apply:1
Leave a Reply