Λεπτομέρειες βιβλιογραφικής εγγραφής
| Τίτλος: |
A Lightweight Vision-Language-Action Policy with Progress-Aware Hybrid Execution for UAV Waypoint Navigation in AirSim. |
| Συγγραφείς: |
Xu, Yiqing1 (AUTHOR) yiqingxu@niit.edu.cn, Lin, Haifeng2 (AUTHOR), Yang, Yujin3 (AUTHOR), Xia, Ji'An1,4 (AUTHOR), Han, Zidong1,4 (AUTHOR) |
| Πηγή: |
Sensors (14248220). Jul2026, Vol. 26 Issue 14, p4655. 31p. |
| Θεματικοί όροι: |
*Flight simulators, *Flight control systems, *Aeronautical navigation, *Robot control systems |
| Περίληψη: |
Offline action prediction does not by itself guarantee reliable closed-loop flight for unmanned aerial vehicle (UAV) vision-language-action (VLA) models. We study a controlled AirSim Blocks waypoint task using 100 expert episodes and 3385 RGB-D, instruction, state, and action records. Checkpoints are selected only on val-seen data, after which val-unseen is evaluated once. A 132,840-parameter policy reaches 0.9278 ± 0.0019 final-test action accuracy across three training seeds, yet raw VLA control fails in closed loop. We therefore embed its action proposals in progress-aware hybrid execution with explicit recovery and near-goal precision. The strongest checkpoint reaches 59/60 goals, but crossing three independently trained checkpoints with three target seeds yields a more conservative 147/180 successes (81.7%) with zero recorded collisions and marked checkpoint sensitivity. Substantial overrides and fallback-tagged steps further show that the reported closed-loop outcomes are properties of the hybrid system, not of the learned policy alone. These findings are restricted to the controlled AirSim Blocks benchmark and do not demonstrate real-UAV deployment, sim-to-real transfer, or field robustness. [ABSTRACT FROM AUTHOR] |
| Βάση Δεδομένων: |
Academic Search Index |