外观
论文arXiv 2610.1647816 天前
面向纯仿真 Sim-to-Real 深度强化学习的 XAI 引导傅里叶域泛化
原文链接：XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning（arXiv 2610.16478 · 发布日期：2026-10-12）
XAI-Guided Fourier Domain Generalisation for Pure-Simulation Sim-to-Real Deep Reinforcement Learning
针对仿真训练视觉自动驾驶策略真实部署退化，XFD以XAI归因引导傅里叶域泛化，并在仿真与零样本真实部署中验证。
核心要点
- 现有图像迁移需目标域数据，域随机化扰动缺乏策略相关指导。
- XFD从仿真观测提取归因图，转为策略条件的傅里叶域干预。
- 方法扰动外观敏感频谱成分，同时保留任务定义的空间结构。
- 实验显示其行驶距离和奖励优于标准策略与随机域随机化基线。
验证范围与局限：验证范围为仿真和零样本真实世界部署，尤其包含未见地图与杂乱背景场景。
英文摘要 (Abstract)
Deep reinforcement learning has shown strong potential for vision-based autonomous driving, but policies trained in simulation often suffer severe performance degradation when deployed in the real world. Existing sim-to-real methods commonly address this gap through image-transfer-based domain adaptation or policy-agnostic domain randomisation. However, the former requires laborious acquisition of target-domain data and is often limited to the deployment domain, whereas the latter introduces unguided perturbations that may not reflect the underlying sim-to-real discrepancy, leading to suboptimal transfer performance. To overcome these limitations, we propose XFD, an explainable artificial intelligence (XAI)-guided Fourier domain generalisation framework for pure-simulation sim-to-real reinforcement learning. The proposed framework extracts explainability attribution maps from simulated observations, and converts these attributions into policy-conditioned Fourier-domain interventions. By perturbing appearance-sensitive spectral components while preserving task-defining spatial structures, XFD constructs robustness-enhancing visual domains entirely within simulation. Subsequently, the proposed robust policy optimisation guides the policy towards attending to task-critical features while suppressing sensitivity to irrelevant visual information. Extensive experiments in simulation and zero-shot real-world deployment demonstrate that XFD consistently improves traveled distance and reward over standard policy and randomly domain-randomised baseline, especially on unseen maps with cluttered backgrounds. Attribution-based analysis further proves that the proposed policy preserves more consistent task-relevant visual evidence across simulation and real-world observations.
作者：Wei Yao, Chuyao Wang, Ziwei Wang, Nabil Aouf
来源
本页事实对应的公开页面，以原文为准。