Robotics_Qi

> My system info: > > Ubuntu 18.0.4 (5.4.0-109-generic) ROS melodic NVIDIA GTX 950M (Compute capability (version) 5.0) Maxwell Cuda 11.1.74 gcc 7.5.0 cmake version 3.10.2 ros-melodic-pcl-ros 1.7.4 eigen 3.3.4...

> hi @Gatsby23 I solved changing the nvcc compiler flag in CMakeLists.txt, I opened a pullrequest for this #92 I changed like this. But I get this problem: ''' nvcc...

> that's strange, what's your cuda version? try `nvcc --version` maybe this option does not apply to all cuda versions, mine now is 11.6.2, I updated it Sorry for that,...

不好意思，这里为了理解的更清楚点，就直接中文给您回复了： 关于这里IMU的测量和外参的转换，我还是有点不理解：为什么在imu_handler当中会把IMU的测量值转换到lidar坐标系下，但是在预积分的时候，IMU还需要在自身的坐标系下进行积分呢？我的理解是：整体在状态估计的时候应该是以Lidar作为body系主体，依次向下进行状态递推的

> imuConverter那个函数只是把imu测量值转换到了一个和lidar坐标系只有平移而没有旋转关系的坐标系b*。那预积分其实都是在b*下进行的，那肯定是要加上平移关系才能转换到lidar坐标系下（imu2Lidar里只有平移）。 OK，我大致明白了，我仔细看下源码，后面再和您详细交流下

> Hi, > > I tried infering labels using the pretrained model, and it worked great without uncertainty > > > Network seq 00 scan 000000.label in 0.7649648189544678 sec >...

> 演示视频可以很明显看出初始化时，飞机在高空静止，累积了足够数据生成平面后再开始运动。 但是实际情况下飞机会一直运动，没法控制初始化的实践，测试了一些数据发现算法在运动场景下的初始化确实不太鲁棒=-= 应该是动态初始化估计重力方向和IMU部分内参，你可以把程序当中这部分写死来看看效果

There seems some problem with picture 1. 

Have same problem too, have you download the pretrained model?

Wonderful work!. Is there some reference paper about this nerf-based localization methods?