← 研踪 PaperTrailarXiv:2606.05015 · v2
Flying on Imagination: DreamerV3-Style World Models under Environment Distribution Shift for Quadrotor Navigation
首次提交 2026-06-03 23:38
版本更新 2026-11-16 03:44
雷达观测 2026-11-17 17:12
摘要
DreamerV3-style reconstructive world models offer a route to vision-based navigation for aerial robots through learned latent dynamics. Yet their behavior under shifts in the training environment and their ability to support navigation using imagined observations, predictions generated by rolling the latent dynamics forward without new sensory input, remain insufficiently characterized. We study four training-environment regimes for depth-based quadrotor navigation, spanning a fixed layout, a finite set of layouts, low-discrepancy continuous obstacle sampling, and i.i.d. uniform sampling. We cross-evaluate reconstruction before and after Reinforcement Learning fine-tuning, separately evaluate the resulting policies in simulation, and transfer them to a real quadrotor without real-world fine-tuning. We demonstrate onboard flight driven by imagined state and depth: a 24.7m mission in which 66% of flight time and 76% of traveled distance occur during repeated 5s sensor-free imagination windows, with prediction quality degrading over each open-loop interval and recovering after sensory re-grounding. Additionally, in closed-loop hardware transfer, all policies succeed in a setting close to the simulated geometry, whereas the policy trained from a single fixed layout fails under a corridor-topology and obstacle-type shift, while the other three succeed.
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v2 · 2026-11-16 03:44 · 最新观测版本
Flying on Imagination: DreamerV3-Style World Models under Environment Distribution Shift for Quadrotor Navigation
DreamerV3-style reconstructive world models offer a route to vision-based navigation for aerial robots through learned latent dynamics. Yet their behavior under shifts in the training environment and their ability to support navigation using imagined observations, predictions generated by rolling the latent dynamics forward without new sensory input, remain insufficiently characterized. We study four training-environment regimes for depth-based quadrotor navigation, spanning a fixed layout, a finite set of layouts, low-discrepancy continuous obstacle sampling, and i.i.d. uniform sampling. We cross-evaluate reconstruction before and after Reinforcement Learning fine-tuning, separately evaluate the resulting policies in simulation, and transfer them to a real quadrotor without real-world fine-tuning. We demonstrate onboard flight driven by imagined state and depth: a 24.7m mission in which 66% of flight time and 76% of traveled distance occur during repeated 5s sensor-free imagination windows, with prediction quality degrading over each open-loop interval and recovering after sensory re-grounding. Additionally, in closed-loop hardware transfer, all policies succeed in a setting close to the simulated geometry, whereas the policy trained from a single fixed layout fails under a corridor-topology and obstacle-type shift, while the other three succeed.
查看此版本解读 →查看此版本原文 ↗