用于越野环境中基于图像的可承受性预测的全局可通行性先验知识提炼
Distilling Global Traversability Priors for Image-based Affordance Prediction in Off-road Environments
浏览论文内容
中文总结 AI 辅助
研究非结构化地形长距离自主导航易短视问题，利用卫星图像计算导航路径监督网络，直接从FPV图像提取远距离可通行性感知边界，提升长距离越野导航性能，减少人工干预。
中文摘要 AI 辅助
在非结构化地形中进行自主导航的标准方法在长距离场景中容易出现短视行为。使用由激光雷达或相机构建的度量地图可提供必要的局部几何和语义信息，但受到深度感应范围的严格限制。通过丢弃超出映射范围的数据，机器人会做出次优、短视的决策。为了恢复这些丢失的信息，我们专注于直接从第一人称视角（FPV）图像中提取远距离可通行性感知边界。通过利用卫星图像，我们为图像/姿态对数据集计算可行的导航路径集，并使用它们来监督我们的网络，减少对大量人工演示数据的需求。我们证明，在各种离线基准测试中，这种方法在长距离越野导航中的性能比现有方法提高了10%以上，并减少了一组实际实验中人工干预的次数。更多细节可在此https URL中找到。
英文摘要
Standard methods for autonomous navigation in unstructured terrain are prone to myopic behaviors in long-horizon scenarios. The use of metric maps built from LiDAR or cameras provides necessary local geometry and semantic information but is strictly limited by depth sensing range. By discarding data beyond the mapping horizon robots suffer from suboptimal, short-sighted decisions. To recover this lost information, we focus on extracting long-range traversability-aware frontiers directly from first-person-view (FPV) images. By leveraging satellite imagery, we compute the set of feasible navigation paths for a dataset of image/pose pairs and use them to supervise our network, reducing the need for extensive human demonstration data. We demonstrate that this approach improves performance in long-range off-road navigation over existing methods by more than 10% in various offline benchmarks and reduces the number of human interventions incurred in a set of real-world experiments. More details can be found at https://theairlab.org/ss_frontiers_iros .
发表机构
- Robotics Institute, Carnegie Mellon University（卡内基梅隆大学机器人研究所）
- Field AI（现场人工智能公司）
机构由 AI 辅助整理，请以论文原文为准。
