Reproduce “3D Generation for Embodied AI and Robotic Simulation: A Survey” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Tianwei Ye, Yifan Mao, Minwen Liao, Jian Liu, Chunchao Guo, Dazhao Du, Quanxin Shou, Fangqi Zhu and 1 more
The authors survey how 3D generation can support embodied AI by creating simulation-ready objects, composing interactive environments, and bridging simulation with real-world learning. They define readiness through valid geometry, physical parameters, executable kinematics, and simulator-compatible formats. The survey finds a shift toward simulation readiness, while annotation scarcity and the sim-to-real gap remain unresolved.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.