Reproduce “AirPlayground: Benchmarking Aerial Navigation across Diverse Reconstructed Environments” 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
Rangya Zhang, Yujing Shang, Zhuoyuan Yu, Mingsheng Li, Qingsong Yan, Chao Yan, Yuhang Zhang, Mir Feroskhan
AirPlayground pairs reconstructed scenes with expert demonstrations and shared interfaces for closed-loop aerial-navigation evaluation. It contains 94,000 demonstrations across 94 scenes, recorded as synchronized RGB–state–action data at 50 Hz. In an ACT scaling study on five fixed seen and five unseen scenes, training on 70 rather than 5 scenes raised median success from 30.6% to 41.2% on seen scenes and from 16.8% to 29.4% on unseen scenes.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.