Jia-Bin Huang (@jbhuang0604)
2025-05-13 | โค๏ธ 165 | ๐ 29
Exploration is key for robots to generalize, especially in open-ended environments with vague goals and sparse rewards.
BUT, how do we go beyond random poking? Wouldnโt it be great to have a robot that explores an environment just like a kid?
Introducing Imagine, Verify, Execute (IVE)!
IVE leverages Vision-Language models to โข extract semantic scene graphs, โข imagine novel scenes, โข predict their physical plausibility, and โข generate executable sequences.
IVE is a memory-guided agentic exploration framework that operates fully automatically, enabling more diverse and meaningful exploration.
๋ฏธ๋์ด
๐ Related
Auto-generated - needs manual review
Tags
domain-robotics domain-ai-ml domain-dev-tools domain-visionos