Zero-Shot Robotic Manipulation

Zero-shot robotic manipulation studies how robots can carry out new tasks and interact with unfamiliar objects or environments without task-specific demonstrations or fine-tuning. Approaches combine vision-language models and language-guided planning with geometric grounding, affordance representations, object-centric policies, and closed-loop feedback; other work learns transferable skills from human videos or scales synthetic data and simulation for sim-to-real transfer. Evaluation spans tabletop and long-horizon tasks, dexterous and contact-rich manipulation, and transfer across objects, viewpoints, robots, and real-world settings. A central challenge is turning broad semantic generalization into precise, reliable physical control, especially under occlusion, changing contact dynamics, and compounding errors during long tasks.