外观
论文arXiv 2606.055062 个月前
通过 Privileged-Sensor 引导的对比学习实现 PointGoal Navigation 的鲁棒场景迁移
原文链接：Robust Scene Transfer for PointGoal Navigation via Privileged-Sensor–Guided Contrastive Learning（arXiv 2606.05506 · 发布日期：2026-08-28）
Robust Scene Transfer for PointGoal Navigation via Privileged-Sensor–Guided Contrastive Learning
提出由 LiDAR 特权传感器引导的自适应对比学习框架，在高保真仿真中提升 PointGoal 导航的跨场景迁移。
核心要点
- 动机是让视觉表征捕获导航相关结构，而非依赖特定场景外观。
- 训练时用 LiDAR 引导几何相似度与自适应温度缩放，编码器预训练后冻结供强化学习使用。
- 引入表征预训练与策略学习间的跨阶段域不匹配，以抑制环境特定捷径。
- 高保真仿真实验显示可改善室内外场景迁移，并优于大型预训练视觉模型和标准对比基线。
验证范围与局限：验证范围为高保真仿真中的多样室内和室外 PointGoal 导航场景。
英文摘要 (Abstract)
We propose a sensor-guided adaptive contrastive learning framework for visual representation learning in PointGoal navigation. During training, privileged LiDAR sensing guides the contrastive objective through a geometry-aware similarity metric and adaptive temperature scaling, encouraging visual embeddings to capture navigation-relevant structure rather than scene-specific appearance. The resulting encoder is pretrained independently, frozen, and used as the perceptual backbone for reinforcement learning, decoupling representation learning from policy optimization. We further introduce a cross-stage domain mismatch between representation pretraining and policy learning to suppress environment-specific shortcuts and promote reliance on task-relevant features. Extensive experiments in high-fidelity simulation demonstrate that our approach significantly improves policy-level scene transfer across diverse indoor and outdoor environments. At deployment, the agent relies only on monocular RGB observations together with standard task-related inputs such as goal position and proprioceptive signals, without access to LiDAR or other privileged sensors. Our method outperforms large pretrained vision models and standard contrastive baselines under severe appearance and semantic shifts. We also release a multimodal dataset to support future research on privileged-guided visual representation learning for navigation. The code is available at:
作者：Amirhossein Zhalehmehrabi, Tiziano Tezze, Alberto Castellini, Alessandro Farinelli
来源
本页事实对应的公开页面，以原文为准。