摘要:由于摄像机和光探测与测距(LiDAR)传感器提供了有关环境的补充信息,因此将LiDAR测量的距离指定给图像中检测到的视觉特征,有助于移动机器人定位融合其信息。然而,现有方法忽略了融合信息的不确定性,或以乐观的方式对其建模(例如,未考虑外部校准误差)。由于传感器融合过程中误差的实际分布通常是未知的,我们假设只知道误差的
《Interval-Based Visual-LiDAR Sensor Fusion》(RAL2021 ) Motivation 将激光和视觉的深度信息进行融合是一个主流的方案,但是,现有的方法忽略的融合信息的不确定性,大部分的融合方案是直接将根据算法算出的最可靠的激光点和特征点进行关联,然后将激光的深度赋值给视觉的特征点(VLOAM,LIMO均如此),但是这样并不符合实...
Figure 26 demonstrates the comparison between conventional LiDAR-based detection and the proposed prediction-based detection algorithm. While the conventional method activates collision detection whenever obstacles enter the predetermined sensor range, our proposed method predicts the trajectory of moving obstacle...
Figure 26 demonstrates the comparison between conventional LiDAR-based detection and the proposed prediction-based detection algorithm. While the conventional method activates collision detection whenever obstacles enter the predetermined sensor range, our proposed method predicts the trajectory of moving obstacle...