用视觉坐标回归与可信学习，让无人机在无GPS环境更准飞行
SCREP: Scene Coordinate Regression and Evidential Learning-based Perception-Aware Trajectory Generation
- 基于可信学习的视觉坐标回归，直接预测像素3D位置
- 实测轨迹误差降低至少4.9%（平移）和30.8%（旋转）
- 适合对定位精度要求高的无人机室内自主飞行场景
在无GPS的室内环境中实现自主飞行，需确保不同任务下视觉定位误差始终受控。基于地图的视觉定位方法（如特征匹配）需高计算量的地图重建，且在大环境中有存储扩展性问题。场景坐标回归（SCR）提供一种高效的学习型替代方案，可直接预测每个像素的3D坐标，支持绝对位姿估计，适用于机载机器人应用。本文提出一种感知意识轨迹规划器，将基于可信学习的SCR位姿估计算法与滚动时域优化器结合。优化器引导机载相机朝向低不确定性的可靠场景坐标，而固定滞后平滑器则融合低频的SCR位姿估计与高频惯性测量单元（IMU）数据，生成高质量、高频的位姿估计。仿真结果表明，本方法相比基线，平移和旋转均方根误差（RMSE）分别降低至少4.9%和30.8%。软硬件联合实验验证了该规划器在接近真实部署条件下的可行性。
原文摘要 · Abstract (English)
Autonomous flight in GPS-denied indoor spaces requires trajectories that keep visual-localization error tightly bounded across varied missions. Map-based visual localization methods such as feature matching require computationally intensive map reconstruction and have feature-storage scalability issues, especially for large environments. Scene coordinate regression (SCR) provides an efficient learning-based alternative that directly predicts3D coordinates for every pixel, enabling absolute pose estimation with significant potential for onboard roboticsapplications. We present a perception-aware trajectory planner that couples an evidential learning-based SCR poseestimator with a receding-horizon trajectory optimizer. The optimizer steers the onboard camera toward reliablescene coordinates with low uncertainty, while a fixed-lag smoother fuses the low-rate SCR pose estimates with high-rate IMU data to provide a high-quality, high-rate pose estimate. In simulation, our planner reduces translationand rotation RMSE by at least 4.9% and 30.8% relative to baselines, respectively. Hardware-in-the-loop experiments validate the feasibility of our proposed trajectory planner under close-to-real deployment conditions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。