Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Handovers in HRC (MT)
The goal of this thesis is to implement a method that allows for efficient handovers between the collaborative robots and humans. To this end you should leverage state-of-the-art computer vision and AI methods to generate a model of the human’s hand. Then we need to create an algorithm that determines the optimal approach to the hand. Finally, we need to account for interaction object geometries. This is the pipeline in a static case: However, when the user is moving, we also do not know, where the handover will take place. Thus, this thesis could take one of two main directions:
Keywords: Human-Robot collaboration, human-robot handover, control systems. computer vision
We expand the possibilities of human robot collaboration by leveraging state-of-the art control frameworks and computer vision.
We expand the possibilities of human robot collaboration by leveraging state-of-the art control frameworks and computer vision.
(1) Focus on hand modelling with high-quality handover generation
(2) Focus on handover timing with timing based on human intent. This might be modelled through a mix of task models and sensory metrics, such as gaze and skeleton tracking.
(1) Focus on hand modelling with high-quality handover generation (2) Focus on handover timing with timing based on human intent. This might be modelled through a mix of task models and sensory metrics, such as gaze and skeleton tracking.
• Some prior knowledge in AI&Modelling, basics of computer vision • Some prior knowledge of C++ for control • For (2): willing to learn unity for hololens development
Not specified
Not specified
send your CV and transcript to Lucas Gimeno
gimenol@ethz.ch
send your CV and transcript to Lucas Gimeno gimenol@ethz.ch
