Shaohua Wan

AeroDPO: Unleashing Lightweight UAV Navigation with High-Fidelity Perception and Automated Preference Optimization

This paper proposes AeroDPO, a zero-cost automated Direct Preference Optimization pipeline driven by deterministic physical simulation state rollback and boosts success rates to 49.16% on unmapped scenarios while drastically suppressing collision rates, establishing a new SOTA for autonomous aerial agents.