自定义博客皮肤VIP专享

*博客头图:

格式为PNG、JPG,宽度*高度大于1920*100像素,不超过2MB,主视觉建议放在右侧,请参照线上博客头图

请上传大于1920*100像素的图片!

博客底图:

图片格式为PNG、JPG,不超过1MB,可上下左右平铺至整个背景

栏目图:

图片格式为PNG、JPG,图片宽度*高度为300*38像素,不超过0.5MB

主标题颜色:

RGB颜色,例如:#AFAFAF

Hover:

RGB颜色,例如:#AFAFAF

副标题颜色:

RGB颜色,例如:#AFAFAF

自定义博客皮肤

-+
  • 博客(274)
  • 收藏
  • 关注

转载 泡泡一分钟:Learning Motion Planning Policies in Uncertain Environments through Repeated Task Executions...

张宁 Learning Motion Planning Policies in Uncertain Environments through Repeated Task Executions通过重复任务执行学习不确定环境中的运动规划策略链接:https://pan.baidu.com/s/1TlSJn0fXuKEwZ9vts4xA6g 提取码:jwsd 复制这段内容后打开百度网盘手...

2019-09-14 15:16:00 330

转载 泡泡一分钟:Efficient Trajectory Planning for High Speed Flight in Unknown Environments

张宁 Efficient Trajectory Planning for High Speed Flight in Unknown Environments高效飞行在未知环境中的有效轨迹规划链接:https://pan.baidu.com/s/1l0HtSOU-6QSojq7ELrmLIA 提取码:ayc1Markus Ryll, John Ware, John Carter...

2019-09-06 22:28:00 428

转载 运行okvis-mono

./build/okvis_app_synchronous config/config_fpga_p2_euroc1.yaml ../mav0转载于:https://www.cnblogs.com/feifanrensheng/p/11461152.html

2019-09-04 19:31:00 413

转载 Robotics Education and Research at Scale - A Remotely Accessible Robotics Development Platform

张宁 Robotics Education and Research at Scale - A Remotely Accessible Robotics Development Platform链接:https://pan.baidu.com/s/1_hXP4dg5qZNHh6T9zKzyCw 提取码:3giyThis paper introduces the KUKA Robo...

2019-08-29 10:49:00 173

转载 泡泡一分钟:Teaching Robots to Draw

Teaching Robots to Draw教会机器人画画https://h2r.cs.brown.edu/wp-content/uploads/kotani19.pdfAtsunobu Kotani and Stefanie TellexIn this paper, we introduce an approach which enables manipulator ro...

2019-08-25 15:43:00 109

转载 Gan-based zero-shot learning 论文整理

1 Feature Generating Networks for Zero-Shot LearningSuffering from the extreme training data imbalance between seen and unseen classes, most ofexisting state-of-the- art approaches fail to achi...

2019-08-23 20:55:00 478

转载 泡泡一分钟:BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous Driving

BLVD: Building A Large-scale 5D Semantics Benchmark for Autonomous DrivingBLVD:构建自主驾驶的大规模5D语义基准Jianru Xue, Jianwu Fang, Tao Li, Bohua Zhang, Pu Zhang, Zhen Ye and Jian DouAbstract—In autono...

2019-08-17 13:47:00 243

转载 泡泡一分钟:GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and Mapping

张宁 GEN-SLAM - Generative Modeling for Monocular Simultaneous Localization and MappingGEN-SLAM - 单目同时定位和建图的生成模型https://arxiv.org/abs/1902.02086Punarjay Chakravarty, Praveen Narayanan and Tom...

2019-08-10 23:05:00 181

转载 泡泡一分钟:Fast and Robust Initialization for Visual-Inertial SLAM

张宁 Fast and Robust Initialization for Visual-Inertial SLAM链接:https://pan.baidu.com/s/1cdkuHdkSi9x7l-96zMbX7g 提取码:b3ffCarlos Campos, Jos´e M.M. Montiel and Juan D. Tard´osVisual-inertial SLAM...

2019-08-04 22:00:00 248

转载 泡泡一分钟:FMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAM...

FMD Stereo SLAM: Fusing MVG and Direct Formulation Towards Accurate and Fast Stereo SLAMFMD Stereo SLAM:融合MVG和直接方法,实现准确,快速的双目SLAMFulin Tang, Heping Li, Yihong WuWe propose a novel stereo vi...

2019-07-28 14:34:00 330

转载 泡泡一分钟:eRTIS - A Fully Embedded Real Time 3D Imaging Sonar Sensor for Robotic Applications...

eRTIS - A Fully Embedded Real Time 3D Imaging Sonar Sensor for Robotic ApplicationseRTIS - 用于机器人应用的全嵌入式实时3D成像声纳传感器链接:https://pan.baidu.com/s/1493U3I3mO5TVUB7ne9jjaw 提取码:ivj5Robin Kerstens,...

2019-07-20 16:39:00 98

转载 Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience

Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience模拟到实际循环闭环:使用真实世界的经验调整模拟随机化Yevgen Chebotar, Ankur Handa, Viktor Makoviychuk Miles Macklin Jan Issac1 N...

2019-07-11 09:26:00 295

转载 evo:评测slam参数设置

zn@buaa:~$ evo_ape euroc m1/state_groundtruth_estimate0/data.csv pl-svo-master2/trajout.txt -angle_deg -as --plotusage: evo_ape euroc [-h] [-r {full,trans_part,rot_part,angle_deg,angle_rad}]...

2019-07-04 22:25:00 734

转载 泡泡一分钟:Project AutoVision - Localization and 3D Scene Perception for an Autonomous Vehicle with a Mul...

Project AutoVision - Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera SystemLionel Heng, Benjamin Choihttps://arxiv.org/abs/1809.05477Abstract: Project Aut...

2019-07-03 22:33:00 153

转载 SVL-VI SLAM

3.4. Mappoints management and key frame process如果在步骤3.3中成功跟踪地图点,则缓存地图点以在下一帧中优先化。当完成当前帧的跟踪时,应该为下一帧更新帧运动速度和地图点。最后,决定当前帧是否应该作为关键帧产生,其标准指的是[11]。 如果框架作为关键帧生成,则会提取并匹配新的ORB要素,同时在此关键帧中保留成功跟踪的要素。ORB功能在关键帧...

2019-07-02 23:09:00 220

转载 泡泡一分钟:Aided Inertial Navigation: Unified Feature Representations and Observability Analysis...

http://udel.edu/~yuyang/downloads/tr_observabilityII.pdfAided Inertial Navigation: Unified Feature Representations and Observability AnalysisYulin Yang,Guoquan Huang辅助惯性导航:统一的特征表示和可观察性分析Ex...

2019-06-27 10:51:00 196

转载 泡泡一分钟:Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints...

张宁Semi-Dense Visual-Inertial Odometry and Mapping for Quadrotors with SWAP Constraints具有SWAP约束的四旋翼半密集视觉惯性里程计和建图https://ieeexplore.ieee.org/document/8463163Wenxin Liu, Giuseppe Loianno, Kar...

2019-06-17 21:20:00 134

转载 基于keras的triplet_loss

https://blog.csdn.net/yjy728/article/details/79570554https://blog.csdn.net/yjy728/article/details/79569807https://keras-cn.readthedocs.io/en/latest/getting_started/functional_API/转载于:https:...

2019-06-16 16:13:00 366

转载 泡泡一分钟:Topomap: Topological Mapping and Navigation Based on Visual SLAM Maps

Topomap: Topological Mapping and Navigation Based on Visual SLAM MapsFabian Bl¨ochliger, Marius Fehr, Marcin Dymczyk, Thomas Schneider and Roland SiegwartTopomap:基于Visual SLAM地图的拓扑映射和导航http...

2019-06-11 15:52:00 551

转载 泡泡一分钟:Robust and Fast 3D Scan Alignment Using Mutual Information

Robust and Fast 3D Scan Alignment Using Mutual Information使用互信息进行稳健快速的三维扫描对准https://arxiv.org/pdf/1709.06948.pdfNikhil Mehta, James R. McBride and Gaurav PandeyAbstract—This paper present...

2019-06-07 17:17:00 124

转载 今日工作总结:06/03

验证预积分的效果评估相邻两图像间的imu数据预积分结果是否足够准确。因为imu的预积分是有绝对尺度的,我们只对预积分出来的旋转增量进行评估,和svo纯视觉计算的旋转增量比较,评估误差 SE3 T_cur_from_ref(new_frame_->T_f_w_ * last_frame_->T_f_w_.inverse()); std::cout<<...

2019-06-03 22:47:00 73

转载 泡泡一分钟:SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes

张宁 SceneCut: Joint Geometric and Object Segmentation for Indoor Scenes "链接:https://pan.baidu.com/s/1hpwb8IjtEpb3uTIncJbTUg 提取码:0wz1"Trung T. Pham , Thanh-Toan Do , Niko Sünderhauf , Ian...

2019-05-31 14:19:00 108

转载 使用 evo 工具评测 VI ORB SLAM2 在 EuRoC 上的结果

http://www.liuxiao.org/2017/11/%E4%BD%BF%E7%94%A8-evo-%E5%B7%A5%E5%85%B7%E8%AF%84%E6%B5%8B-vi-orb-slam2-%E5%9C%A8-euroc-%E4%B8%8A%E7%9A%84%E7%BB%93%E6%9E%9C/转载于:https://www.cnblogs.com/feifanre...

2019-05-30 10:37:00 723

转载 pip 安装指定版本

pip在安装包的时候可以不需要从网上下载,以windows的scipy为例pip install scipy==0.15.1以上表示安装0.15.1版本的scipy,这里用”==”接版本,如果权限不够则用管理员打开终端,或者pip install --user scipy==0.15.1转载于:https://www.cnblogs.com/feif...

2019-05-28 17:21:00 1298

转载 译文:A Robust and Modular Multi-Sensor Fusion ApproachApplied to MAV Navigation

A Robust and Modular Multi-Sensor Fusion ApproachApplied to MAV Navigation众所周知,将来自多个传感器的信息融合用于机器人导航导致增加的鲁棒性和准确性。然而,在现场部署之前准确校准传感器集合以及传感器中断,不同的测量速率和延迟,使得多传感器融合成为挑战。因此,为了简单起见,大多数系统都没有利用所有可用的传感器信息...

2019-05-24 15:36:00 820

转载 泡泡一分钟:Perception-aware Receding Horizon Navigation for MAVs

作为在空中抛掷四旋翼飞行器后恢复的第一步,它需要检测它使用其加速度计的发射。理想的情况下,在飞行中,加速度计理想地仅测量由于施加的转子推力引起的加速度,即。因此,当四旋翼飞行器发射时,我们可以检测到测量的加速度下降到与当前施加的推力相对应的值。B. Recovery and Initialization Steps张宁 Perception-aware Receding H...

2019-05-22 15:08:00 254

转载 泡泡一分钟: A Linear Least Square Initialization Method for 3D Pose Graph Optimization Problem...

张宁A Linear Least Square Initialization Method for 3D Pose Graph Optimization Problem"链接:https://pan.baidu.com/s/1oj_HgQtiiKExACscYuFhJQ 提取码:7xrg"三维位姿图优化问题的线性最小二乘初始化方法S. M. Nasiri, H. Moradi...

2019-05-13 21:29:00 204

转载 泡泡一分钟:LandmarkBoost: Efficient Visual Context Classifiers for Robust Localization

Marcin Dymczyk, Igor Gilitschenski, Juan Nieto, Simon Lynen, Bernhard Zeis, and Roland SiegwartLandmarkBoost: Efficient Visual Context Classifiers for Robust LocalizationLandmarkBoost:用于鲁棒定位的高效...

2019-05-10 11:29:00 134

转载 泡泡一分钟:Visual Odometry Using a Homography Formulation with Decoupled Rotation and Translation Estimat...

张宁 Visual Odometry Using a Homography Formulation with Decoupled Rotation and Translation Estimation Using Minimal Solutions "链接:https://pan.baidu.com/s/13l8ERXM9SiBqDe2r_25elw 提取码:xs4u "视觉测距法使用单...

2019-05-01 15:04:00 181

转载 泡泡一分钟:

张宁 3D Lidar-IMU Calibration Based on Upsampled Preintegrated Measurements for Motion Distortion Correction "链接:https://pan.baidu.com/s/1GhIlgccbJx5R0CjdyO8lbw 提取码:t05m "用于运动失真校正的基于超采样预积分测量的三维激光...

2019-04-28 19:12:00 169

转载 Android手机camera和IMU的标定

https://qingsimon.github.io/post/2018-12-28-android%E6%89%8B%E6%9C%BA%E7%9B%B8camera%E5%92%8Cimu%E7%9A%84%E6%A0%87%E5%AE%9A/转载于:https://www.cnblogs.com/feifanrensheng/p/10729817.html

2019-04-18 15:19:00 1056

转载 PL-SVO公式推导及代码解析:位姿优化

通过跳过极线约束单独优化图像中每个特征的位置后,必须通过最小化3D特征与图像中相应的2D特征位置之间的重投影误差来进一步细化(3)中获得的相机姿态( 见图5)。为此,我们考虑在世界坐标系中3D特征和相机姿势Tk,w之间的重投影误差,因为它大大减少了估计轨迹的漂移。 // pose optimization SVO_START_TIMER("pose_optimizer")...

2019-04-17 22:54:00 253

转载 vins-mono:雅可比矩阵的推导

imu残差公式我们计算雅可比采用加扰动形式以下是位置增量偏差对旋转qbk的雅可比推导对应的雅可比矩阵的代码jacobian_pose_i.block<3, 3>(O_P, O_R) = Utility::skewSymmetric(Qi.inverse() * (0.5 * G * sum_dt * sum_dt + Pj - Pi - Vi...

2019-04-17 14:54:00 776

转载 PL-SVO公式推导及代码解析:地图点重投影和特征对齐

对当前帧进行地图点重投影和特征对齐 // map reprojection & feature alignment SVO_START_TIMER("reproject"); reprojector_.reprojectMap(new_frame_, overlap_kfs_); SVO_STOP_TIMER("reproject");在pro...

2019-04-16 22:53:00 447

转载 脚本:截取euroc数据集bag文件的其中一段

脚本:截取euroc数据集bag文件的其中一段功能:截取euroc数据集bag中的一段供算法测试python脚本#!/usr/bin/env python# ------------------------------------------------------------------------------# Function : restamp ros...

2019-04-15 18:48:00 316

转载 ubuntu16.04安装mrpt

源码地址https://github.com/MRPT/mrpt安装教程https://github.com/MRPT/mrpt/blob/master/README.md#32-build-from-sources转载于:https://www.cnblogs.com/feifanrensheng/p/10705742.html...

2019-04-14 16:44:00 545

转载 泡泡一分钟: Deep-LK for Efficient Adaptive Object Tracking

Deep-LK for Efficient Adaptive Object Tracking"链接:https://pan.baidu.com/s/1Hn-CVgiR7WV0jvaYBv5G_A 提取码:mp97"用于高效自适应对象跟踪的Deep-LK方法In this paper, we present a new approach for effici...

2019-04-10 19:53:00 220

转载 泡泡一分钟:Cooperative Object Transportation by Multiple Ground and Aerial Vehicles: Modeling and Plannin...

张宁 Cooperative Object Transportation by Multiple Ground and Aerial Vehicles: Modeling and Planning多地面和空中车辆的协同目标运输:建模与规划"链接:https://pan.baidu.com/s/1u00fHJMF4u9_4l7-h655og提取码:n94y"In t...

2019-04-06 21:12:00 131

转载 vins-mono中的imu参数设置

na:加速度计的测量噪声nw:陀螺仪的测量噪声nba: randow walk noise随机游走噪声nbw:randow walk noise随机游走噪声ba:加速度计的偏差bw:陀螺仪的偏差其中na,nw,nba,nbw,都是零均值高斯模型ba的导数为nba,bw的导数为nbw。获取这些参数可以通过imu_utils来获得https://githu...

2019-04-04 12:16:00 577

转载 evo: Python package for the evaluation of odometry and SLAM

https://michaelgrupp.github.io/evo/转载于:https://www.cnblogs.com/feifanrensheng/p/10650586.html

2019-04-03 18:02:00 195

空空如也

空空如也

TA创建的收藏夹 TA关注的收藏夹

TA关注的人

提示
确定要删除当前文章?
取消 删除