The Department of Robotics, Perception, and Learning at KTH Royal Institute of Technology in Stockholm, Sweden, is offering two fully funded PhD positions in the field of robot learning for manipulation. The research will focus on leveraging recent advances in Vision-Language-Action (VLA) models to address tabletop and mobile manipulation tasks, with an emphasis on using whole-body motion to enhance perception and control. The positions are part of Professor Danica Kragic Jensfelt’s group, a leading research team in robotics, computer vision, and machine learning.

Applicants should have a strong background in robotics and machine learning, with demonstrated experience in at least two of the following areas: deep learning, reinforcement learning, robot perception, navigation, or manipulation. The research environment at KTH is highly interdisciplinary, combining aspects of computer science, electrical engineering, and mechanical engineering to advance the state of the art in robotic systems for industry, healthcare, and service applications.

Eligibility requirements include a second cycle degree (such as a master's) or equivalent, with at least 240 higher education credits (including 60 at the second-cycle level), and proficiency in English equivalent to English B/6. The selection process values goal orientation, independence, collaboration skills, and analytical ability. The positions are full-time, with a monthly salary according to KTH’s doctoral student salary agreement, and include employee benefits and a creative, dynamic work environment.

Applications must be submitted through the KTH application portal and should include a CV, application letter, diplomas, transcripts, proof of English proficiency, and representative publications or technical reports. The deadline for applications is March 5, 2025. For more information, visit the department’s website or contact Professor Danica Kragic Jensfelt at [email protected].

Research keywords: robot learning, manipulation, robotics, machine learning, vision-language-action models, deep learning, reinforcement learning, robot perception, navigation, whole-body motion, mobile manipulation.