Reproduce “Benchmarking Interaction-Oriented Aerial Mobility across Heterogeneous 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
Zhibo Duan, Hanlin Kong, Tianran Ma, Yuze Wu, Yuxuan Xu, Kenghou Hoi, Changheng Xie, Xin Zhou and 3 more
CrossFly benchmarks UAV flight across indoor, outdoor, and connected indoor–outdoor scenes, evaluating arrival at an interaction site and whether the terminal position is suitable for interaction. Its dataset contains 15,263 trajectories in 23 reconstructed scenes. A distance-and-yaw readiness measure complements navigation success. On unseen indoor–outdoor episodes, CrossFly-Agent achieves 9.7% success, the best result among agents, but performance remains low.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.