Reproduce “UAV-Flow++: A Unified Suite for Benchmarking and Learning Language-Guided UAV Flight” 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
Donglin Yang, Xiangyu Wang, Yantong Zhong, Wenhao Zheng, Zihan Ding, Yue Liao, Hongsheng Li, Ke Xu and 1 more
The authors train FlowVLA to turn short, object-relative flight instructions, camera images, and UAV state into continuous drone maneuvers. They combine selected real-flight demonstrations with simulated demonstrations, then apply TGRPO post-training in closed-loop simulation. On 273 held-out episodes, success rises from 75.58% to 93.16%, in the same campus scene used for simulated demonstrations.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.