外观
论文arXiv 2610.1236820 天前
LiteNWM：用于野外板载视觉导航的高效潜在世界模型
原文链接：LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild（arXiv 2610.12368 · 发布日期：2026-10-08）
LiteNWM: Efficient Latent World Models for Onboard Visual Navigation in the Wild
LiteNWM通过共享视觉编码和潜在多时域预测选择轨迹，在离线数据集与未见室内外真机导航中验证。
核心要点
- 直接视觉导航策略虽能高效生成轨迹，但不显式评估未来后果；视觉 rollout 评估多候选代价高。
- LiteNWM在候选间共享视觉编码，联合预测动作条件未来表示，并用学习评分器选择轨迹。
- 在RECON、SCAND、SACSoN离线评估中，较NoMaD+NWM-XL降低17.56%轨迹误差并加速128.00倍。
- 同一评估器可从NoMaD迁移到MBRA而无需重训；真机未见室内外环境中成功率由43.3%升至83.3%。
验证范围与局限：验证范围包括RECON、SCAND、SACSoN离线评估，以及未见室内外环境中的真机导航实验。
英文摘要 (Abstract)
Direct visual navigation policies generate trajectories efficiently but do not explicitly evaluate their future consequences. Generative navigation world models provide this foresight through visual rollouts, which are costly when evaluating multiple candidates. We present LiteNWM, a latent navigation world model that shares visual encoding across candidates and jointly predicts their action-conditioned future representations at multiple horizons, while a learned scorer uses these predictions to select trajectories. In offline evaluations on RECON, SCAND, and SACSoN, LiteNWM reduces macro-averaged trajectory error by 17.56% relative to NoMaD+NWM-XL and achieves a 128.00-fold end-to-end speedup on an RTX 5090. The same evaluator transfers from NoMaD to MBRA without proposer-specific retraining, reducing MBRA's macro-averaged trajectory error by 16.2%. In real-robot experiments in unseen indoor and outdoor environments, LiteNWM improves navigation success from 43.3% to 83.3% relative to NoMaD. These results demonstrate that LiteNWM can be deployed for future-aware planning and closed-loop navigation on a physical robot.
作者：Linkai Liu, Yuntian Zhang, Zhenshan Bing, Chen Chen, Lingjuan Lyu, Shangguang Wang, Mengwei Xu, Cai Dongqi
来源
本页事实对应的公开页面，以原文为准。