Publisher
source

KTH Royal Institute of Technology

Top university

Doctoral student in perception for dynamic scene understanding KTH Royal Institute of Technology in Sweden

Degree Level

PhD

Field of study

Computer Science

Funding

Full funding available

Deadline

December 31, 2026
Country flag

Country

Sweden

University

KTH Royal Institute of Technology

Social connections

How do I apply for this?

Sign in for free to reveal details, requirements, and source links.

Apply for this position

Keywords

Computer Science
Computer Vision
Self-supervised Learning
Robotics
Autonomous System
Machine learning

About this position

This doctoral position at KTH Royal Institute of Technology focuses on perception for dynamic scene understanding, specifically targeting generalizable 3D dynamic scene analysis for autonomous systems. The research centers on scene flow estimation, aiming to overcome current limitations in generalization across sensor configurations and environments, and to integrate motion estimation with downstream safety requirements for autonomous planning. The project will develop a self-supervised, multi-modal model that fuses LiDAR geometry and camera semantics, enabling motion representations that generalize zero-shot to unseen real-world scenarios and align with safety and efficiency needs beyond standard geometric metrics.

The starting point for the research is the department's state-of-the-art work on self-supervised scene flow, accessible at OpenSceneFlow. The position is based in the Department of Robotics, Perception and Learning and is fully funded by the Wallenberg AI, Autonomous Systems and Software Program (WASP), with additional connection to the WASP graduate school (WASP Graduate School). The project is supervised by Dr. Patric Jensfelt, a leading researcher in robotics and perception.

Eligibility requires a second cycle degree (such as a master's) or equivalent, or completion of at least 240 higher education credits (with at least 60 at second-cycle level), or substantially equivalent knowledge. English proficiency equivalent to English B/6 is mandatory. Candidates should demonstrate strong programming skills and experience with machine learning methods, preferably in computer vision. Selection will emphasize independence, collaboration, professionalism, analytical skills, and proficiency in English. Applications must include certified copies of diplomas and grades, proof of language requirements, CV, application letter (max 1 page), and a list of publications or technical reports.

The position offers a monthly salary according to KTH’s doctoral student salary agreement and is a full-time, temporary contract. Employment is initially for one year, renewable for up to four years total. The doctoral student will benefit from a creative and dynamic research environment, attractive employee benefits, and access to the doctoral student network at KTH. The first day of employment is September 1, or as agreed, but no later than January 7. The application deadline is May 15, 2026.

To apply, submit your application through KTH's recruitment system (application link) and ensure all required documents are included. For further information about the WASP program, visit WASP Sweden. KTH is committed to equality, diversity, and quality in education and research, offering a supportive environment for doctoral students.

Funding details

Full funding including tuition fees and living expenses is available for this position. The scholarship covers all educational costs and provides a monthly stipend.

How to apply

Please submit your application including a cover letter, CV, academic transcripts, and contact information for two references. Applications should be sent via the online portal before the deadline.

More information can be found here

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?