MSc Thesis: Affordance-Aware Multi-Fingered Manipulation via LLM

07.07.2025, Abschlussarbeiten, Bachelor- und Masterarbeiten

Your Tasks
  • Review state-of-the-art in LLM-based robotic manipulation
  • Implement and evaluate semantic grasp reasoning modules
  • Design and run experiments on a robotic hand platform, with an existing dexterous hand
  • Evaluation of the capabilities and limits of such tools

Your Qualifications
  • Enrolled in a Master’s program (STEM or related fields)
  • Passionate about machine learning and robotics
  • excellent in python (experience with PyTorch or JAX is a bonus)
  • Self-motivated working

Relevant publication:
Mirjalili, Reihaneh, et al. "Lan-grasp: Using large language models for semantic object grasping." arXiv preprint arXiv:2310.05239 (2023)

Kontakt: cristina.piazza@tum.de