Reproduce “Intent Prediction-Driven Model Predictive Control for UAV Planning and Navigation in Dynamic 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

Zhefan Xu, Hanyu Jin, Xinming Han, Haoyu Shen, Kenji Shimada

The authors present a UAV system that plans around dynamic obstacles by considering several short-term behaviors rather than one predicted path. It assigns heuristic probabilities to four intents and uses model predictive control to select an avoidance trajectory. In high-density simulation, it recorded 14 collision events across 20 runs, versus 69 for ViGO; these results are limited to simulated settings.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.