SkipWorld：基于蒸馏世界模型的隐式跳跃规划用于高效视觉导航
SkipWorld: Latent Skip Planning with Distilled World Models for Efficient Visual Navigation
AI总结：
SkipWorld是一种高效视觉导航的隐式跳跃规划框架，通过Latent AutoRoll、SkipDistill和Skip-then-Refine Planning三个组件，在保证轨迹评估准确性的同时降低计算成本，在多个数据集上较NWM取得更优性能。
摘要：
基于世界模型的视觉导航可通过预测候选轨迹下的未来状态实现动作规划，但长时序回推仍具挑战性：模型常以真实视觉历史训练，却在闭环预测中部署，且逐步回推评估大量候选的计算成本高昂。本文提出SkipWorld，一种用于高效视觉导航的隐式跳跃规划框架，包含三个组件：（i）Latent AutoRoll，训练世界模型在隐空间递归回推未来状态，减少训练与闭环推理的不匹配；（ii）SkipDistill，将隐式自回归模型蒸馏为直接预测长步长未来隐状态的跳跃世界模型；（iii）Skip-then-Refine Planning，一种双模型粗到细规划器，先用跳跃模型过滤候选轨迹，再用更强的自回归模型对选中候选重排序。该设计在保留轨迹评估准确性的同时减少冗余回推计算。在RECON、HuRoN、SCAND和TartanDrive数据集上的实验表明，与NWM相比，SkipWorld将平均ATE降低4.2%、RPE降低2.7%，规划时间减少62.4%，速度提升2.7倍。
英文摘要：
World-model-based visual navigation enables action planning by predicting future states under candidate trajectories. However, long-horizon rollout remains challenging: models are often trained with ground-truth visual histories but deployed in closed-loop prediction, and evaluating many candidates with step-by-step rollout is computationally expensive. We propose SkipWorld, a latent skip planning framework for efficient visual navigation. SkipWorld introduces three components: (i) Latent AutoRoll, which trains a world model to recursively roll out future states in latent space, reducing the mismatch between training and closed-loop inference; (ii) SkipDistill, which distills the latent autoregressive model into a skip world model that directly predicts long-stride future latent states; and (iii) Skip-then-Refine Planning, a dual-model coarse-to-fine planner that first filters candidate trajectories with the skip model and then reranks selected candidates with the stronger autoregressive model. This design preserves accurate trajectory evaluation while reducing redundant rollout computation. Experiments on RECON, HuRoN, SCAND, and TartanDrive show that, compared with NWM, SkipWorld reduces the average ATE by 4.2% and RPE by 2.7%, while decreasing planning time by 62.4% with a 2.7-fold speedup.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
