职位信息
Doctoral student in Multimodal AI for Human-Robot Interaction
8月31日截止
This project aims to enhance Human-Robot Interaction (HRI) through embodied AI by integrating multimodal social cues and task-related actions into foundation models, enabling more natural and human-like communication. While Large Language Models have advanced AI significantly, current systems lack understanding and generation of crucial social cues like facial expressions, gestures, and gaze direction, as well as the ability to incorporate task-specific behaviors. This project aims to bridge these gaps.
Key Objectives:
Integrate multimodal perception: Develop methods to fuse foundation models with embodied and task-specific tags.
Generate multimodal outputs: Train models to produce relevant verbal responses, non-verbal behaviors, and task-related actions.
Evaluate comprehensively: Develop novel metrics to assess integrated models in HRI scenarios.
To be admitted to postgraduate education (Chapter 7, 39 § Swedish Higher Education Ordinance), the applicant must have basic eligibility in accordance with either of the following:
passed a second cycle degree (for example a master's degree), or
completed course requirements of at least 240 higher education credits, of which at least 60 second-cycle higher education credits, or
acquired, in some other way within or outside the country, substantially equivalent knowledge
In order to succeed as a doctoral student at KTH you need to be goal oriented and persevering in your work. During the selection process, candidates will be assessed upon their ability to:
independently pursue his or her work
collaborate with others,
have a professional approach and
analyse and work with complex issues.
https://www.kth.se/lediga-jobb/739179?l=en
申请交流群
如果喜欢今天的内容，请为我点赞和在看！感谢大家的支持！
