访问计数 185422 (自2016年5月)
Videos
0?1470885445
发布时间:05/19/2017 08:11
更新时间:12/22/2017 17:28

This video is about the experimental results of the following paper: Xieyuanli Chen, Huimin Lu, Junhao Xiao, Hui Zhang, Pan Wang. Robust relocalization based on active loop closure for real-time monocular SLAM. Proceedings of the 11th International Conference on Computer Vision Systems (ICVS), 2017.


Abstract. Remarkable performance has been achieved using the state-of-the-art monocular Simultaneous Localization and Mapping (SLAM) algorithms. However, tracking failure is still a challenging problem during the monocular SLAM process, and it seems to be even inevitable when carrying out long-term SLAM in large-scale environments. In this paper, we propose an active loop closure based relocalization system, which enables the monocular SLAM to detect and recover from tracking failures automatically even in previously unvisited areas where no keyframe exists. We test our system by extensive experiments including using the most popular KITTI dataset, and our own dataset acquired by a hand-held camera in outdoor large-scale and indoor small-scale real-world environments where man-made shakes and interruptions were added. The experimental results show that the least recovery time (within 5ms) and the longest success distance (up to 46m) were achieved comparing to other relocalization systems. Furthermore, our system is more robust than others, as it can be used in different kinds of situations, i.e., tracking failures caused by the blur, sudden motion and occlusion. Besides robots or autonomous vehicles, our system can also be employed in other applications, like mobile phones, drones, etc.

回复 ︿
用户头像
登录后可添加回复
0?1470885445
发布时间:06/29/2017 00:31
更新时间:09/22/2017 23:44

This video is about the experimental results of the following paper: Xieyuanli Chen, Hui Zhang, Huimin Lu, Junhao Xiao, Qihang Qiu and Yi Li. Robust SLAM system based on monocular vision and LiDAR for robotic urban search and rescue. Proceedings of the 15th IEEE International Symposium on Safety, Security, and Rescue Robotics 2017 (SSRR 2017), Shanghai, 2017


Abstract. In this paper, we propose a monocular SLAM system for robotic urban search and rescue (USAR). Based on it, most USAR tasks (e.g. localization, mapping, exploration and object recognition) can be fulfilled by rescue robots with only a single camera. The proposed system can be a promising basis to implement fully autonomous rescue robots. However, the feature-based map built by the monocular SLAM is difficult for the operator to understand and use. We therefore combine the monocular SLAM with a 2D LiDAR SLAM to realize a 2D mapping and 6D localization SLAM system which can not only obtain a real scale of the environment and make the map more friendly to users, but also solve the problem that the robot pose cannot be tracked by the 2D LiDAR SLAM when the robot climbing stairs and ramps. We test our system using a real rescue robot in simulated disaster environments. The experimental results show that good performance can be achieved using the proposed system in the USAR. The system has also been successfully applied in the RoboCup Rescue Robot League (RRL) competitions, where our rescue robot team entered the top 5 and won the Best in Class Small Robot Mobility in 2016 RoboCup RRL Leipzig Germany, and the champions of 2016 and 2017 RoboCup China Open RRL.



回复 ︿
用户头像
登录后可添加回复
0?1470885445
发布时间:09/14/2017 20:29
更新时间:09/14/2017 20:29
This video shows a track-wheel hybrid robot, named Kylin, which is designed to integrate the advantages of both wheeled locomotion and tracked locomotion. To save the research and development time, the robot is built upon our tracked robot named NuBot, by integrating modular components for wheeled locomotion without changing the main body of NuBot. Kylin can run 3.7 m/s on the ground, climb up 45 degree slops and 0.5 m steps. It has been employed in UGVC 2016, and won the vice-champion.
( 26.4 MB) 肖军浩, 09/14/2017 20:31
回复 ︿
用户头像
登录后可添加回复
0?1470885445
发布时间:03/26/2017 17:49
更新时间:06/23/2017 23:36
视频中展示的是基于三维建图和虚拟现实技术的新型人机交互系统,便于审稿专家对系统进行全面了解和评价。
回复 ︿
用户头像
登录后可添加回复
0?1470885445
罗莎 TO  NuBot Research Team | Videos
发布时间:04/14/2017 13:19
更新时间:04/14/2017 13:19
In this video, a ball, a robot and a piece of orange luggage are fixed at posi-tions (0, 144), (0, 7) and (0, -144) respectively. Then another robot with a Kinect sensor rotates around these objects following a circular trajectory centered at (0, 0) with the radius of 300cm. The robot moves at the speed of 3m/s and its heading points towards the origin all the time during the dynamic test. We marked the detected ball with grey sphere and obstacle with red/white cube in the video, and there have some disfluency because of the visualization of point cloud in TX1. From the video we can conclude that our algorithm can  detect the ball and obstacles accurately.
( 15.9 MB) 罗莎, 04/14/2017 13:19
回复 ︿
用户头像
登录后可添加回复
0?1470885445
发布时间:06/26/2016 18:13
更新时间:10/06/2016 13:03

Title

Real-time Object Segmentation for Soccer Robots Based on Depth Images

Author

Qiu Cheng, Shuijun Yu, Qinghua Yu and Junhao Xiao


Abstract

Object detection and localization is a paramount important and challenging task in RoboCup MSL (Middle Size League). It has a strong constraint on real-time, as both the robot and obstacles (also robots) are moving quickly. In this paper, a real-time object segmentation approach is proposed, based on a RGB-D camera in which only the range information has been used. The method has four main steps, e.g., point cloud filtering, background points removing, clustering and object localization. Experimental results show that the proposed algorithm can effectively detect and segment objects in 3D space in real-time.

Video:

The video can be found here if the below link does not work.



回复 ︿
用户头像
登录后可添加回复
0?1470885445
发布时间:01/05/2016 11:33
更新时间:06/06/2016 15:04

The qualification video for RoboCup 2016 Leipzeig, Germany can be found here


回复 ︿
用户头像
登录后可添加回复