专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US09364128B2 Robot cleaner and controlling method of the same 有权
标题翻译：机器人清洁与控制方法相同
公开(公告)号：US09364128B2
公开(公告)日：2016-06-14
申请号：US13809534
申请日：2011-07-05
申请人： Yiebin Kim , Seung min Baek , Yoojin Choi , Vadim Lutsiv , Victor Redkov , Alexey Potapov , Seongsoo Lee
发明人： Yiebin Kim , Seung min Baek , Yoojin Choi , Vadim Lutsiv , Victor Redkov , Alexey Potapov , Seongsoo Lee
IPC分类号： A47L11/20 , G05D1/02 , B25J13/08
CPC分类号： A47L11/20 , A47L2201/04 , B25J13/08 , G05D1/0246 , G05D1/0253 , G05D1/0274 , G05D2201/0203 , Y10S901/01 , Y10S901/09 , Y10S901/47
摘要： Disclosed are a robot cleaner and a method for controlling the same. The robot cleaner is capable of recognizing a position thereof by extracting one or more feature points having 2D coordinates information with respect to each of a plurality of images, by matching the feature points with each other, and then by creating a matching point having 3D coordinates information. Matching points having 3D coordinates information are created to recognize a position of the robot cleaner, and the recognized position is verified based on a moving distance measured by using a sensor. This may allow a position of the robot cleaner to be precisely recognized, and allow the robot cleaner to perform a cleaning operation or a running operation by interworking the precisely recognized position with a map.
摘要翻译：公开了一种机器人清洁器及其控制方法。机器人清洁器能够通过相对于多个图像中的每一个提取具有2D坐标信息的一个或多个特征点来识别其位置，通过使特征点彼此匹配，然后通过创建具有3D坐标的匹配点信息。创建具有3D坐标信息的匹配点以识别机器人清洁器的位置，并且基于通过使用传感器测量的移动距离来验证识别的位置。这可以允许机器人清洁器的位置被精确地识别，并且允许机器人清洁器通过将精确识别的位置与地图相互作用来执行清洁操作或运行操作。

2. 发明授权

US08503760B2 System and method for real-time object recognition and pose estimation using in-situ monitoring 有权
标题翻译：使用现场监测的实时物体识别和姿态估计的系统和方法
公开(公告)号：US08503760B2
公开(公告)日：2013-08-06
申请号：US12032427
申请日：2008-02-15
申请人： Sukhan Lee , Seung-Min Baek , Jeihun Lee , Jangwon Lee
发明人： Sukhan Lee , Seung-Min Baek , Jeihun Lee , Jangwon Lee
IPC分类号： G06K9/00
CPC分类号： G06K9/00201 , G06K9/6292 , G06T7/35 , G06T7/73 , G06T7/77 , G06T2207/10028
摘要： Provided are a system and method for real-time object recognition and pose estimation using in-situ monitoring. The method includes the steps of: a) receiving 2D and 3D image information, extracting evidences from the received 2D and 3D image information, recognizing an object by comparing the evidences with model, and expressing locations and poses by probabilistic particles; b) probabilistically fusing various locations and poses and finally determining a location and a pose by filtering inaccurate information; c) generating ROI by receiving 2D and 3D image information and the location and pose from the step b) and collecting and calculating environmental information; d) selecting an evidence or a set of evidences probabilistically by receiving the information from the step c) and proposing a cognitive action of a robot for collecting additional evidence; and e) repeating the steps a) and b) and the steps c) and d) in parallel until a result of object recognition and pose estimation is probabilistically satisfied.
摘要翻译：提供了使用现场监测的实时对象识别和姿态估计的系统和方法。该方法包括以下步骤：a）接收2D和3D图像信息，从接收到的2D和3D图像信息中提取证据，通过将证据与模型进行比较来识别对象，并通过概率粒子表示位置和姿态; b）概率地融合各种位置和姿势，并最终通过过滤不准确的信息来确定位置和姿势; c）通过从步骤b）接收2D和3D图像信息以及位置和姿势来生成ROI并收集和计算环境信息; d）通过接收步骤c）中的信息并提出机器人的收集附加证据的认知行动来概率地选择证据或一组证据; 和e）并行地重复步骤a）和b）和步骤c）和d），直到概率地满足对象识别和姿态估计的结果。

3. 发明申请

US20090190798A1 SYSTEM AND METHOD FOR REAL-TIME OBJECT RECOGNITION AND POSE ESTIMATION USING IN-SITU MONITORING 有权
标题翻译：用于现场监测的实时对象识别和位置估计的系统和方法
公开(公告)号：US20090190798A1
公开(公告)日：2009-07-30
申请号：US12032427
申请日：2008-02-15
申请人： Sukhan LEE , Seung-Min BAEK , Jeihun LEE , Jangwon LEE
发明人： Sukhan LEE , Seung-Min BAEK , Jeihun LEE , Jangwon LEE
IPC分类号： G06K9/00
CPC分类号： G06K9/00201 , G06K9/6292 , G06T7/35 , G06T7/73 , G06T7/77 , G06T2207/10028
摘要： Provided are a system and method for real-time object recognition and pose estimation using in-situ monitoring. The method includes the steps of: a) receiving 2D and 3D image information, extracting evidences from the received 2D and 3D image information, recognizing an object by comparing the evidences with model, and expressing locations and poses by probabilistic particles; b) probabilistically fusing various locations and poses and finally determining a location and a pose by filtering inaccurate information; c) generating ROI by receiving 2D and 3D image information and the location and pose from the step b) and collecting and calculating environmental information; d) selecting an evidence or a set of evidences probabilistically by receiving the information from the step c) and proposing a cognitive action of a robot for collecting additional evidence; and e) repeating the steps a) and b) and the steps c) and d) in parallel until a result of object recognition and pose estimation is probabilistically satisfied.
摘要翻译：提供了使用现场监测的实时对象识别和姿态估计的系统和方法。该方法包括以下步骤：a）接收2D和3D图像信息，从接收到的2D和3D图像信息中提取证据，通过将证据与模型进行比较来识别对象，并通过概率粒子表示位置和姿态; b）概率地融合各种位置和姿势，并最终通过过滤不准确的信息来确定位置和姿势; c）通过从步骤b）接收2D和3D图像信息以及位置和姿势来生成ROI并收集和计算环境信息; d）通过接收步骤c）中的信息并提出机器人的收集附加证据的认知行动来概率地选择证据或一组证据; 和e）并行地重复步骤a）和b）和步骤c）和d），直到概率地满足对象识别和姿态估计的结果。

4. 发明授权

US08954191B2 Mobile robot and controlling method of the same 有权
标题翻译：移动机器人及其控制方法相同
公开(公告)号：US08954191B2
公开(公告)日：2015-02-10
申请号：US12718380
申请日：2010-03-05
申请人： Dong Hoon Yi , Young Gie Kim , Jeong Suk Yoon , Seong Soo Lee , Jei Hun Lee , Seung Min Baek , Yoo Jin Choi , Sang Ik Na , Su Uk Choe , Yie Bin Kim
发明人： Dong Hoon Yi , Young Gie Kim , Jeong Suk Yoon , Seong Soo Lee , Jei Hun Lee , Seung Min Baek , Yoo Jin Choi , Sang Ik Na , Su Uk Choe , Yie Bin Kim
IPC分类号： G05B19/04 , G05B19/18 , G05D1/02
CPC分类号： G05D1/0274 , G05D1/0246 , G05D1/0255 , G05D2201/0203
摘要： Disclosed is a mobile robot and a controlling method of the same. An entire movement region is divided into a plurality of regions, and a partial map is gradually made by using feature points of a plurality of images of the divided regions. Then, the map is compensated into a closed curved line, thereby making an entire map. Furthermore, when the mobile robot is positioned at a boundary of neighboring regions of the cleaning region, the boundary where a closed curved line is formed, the mobile robot compensates for its position based on a matching result between feature points included in the map, and feature points extracted from images captured during a cleaning process.
摘要翻译：公开了一种移动机器人及其控制方法。整个移动区域被划分为多个区域，并且通过使用分割区域的多个图像的特征点逐渐地进行部分地图。然后，将地图补偿为闭合的曲线，从而制作整个地图。此外，当移动机器人位于清洁区域的相邻区域的边界处，形成闭合曲线的边界时，移动机器人基于地图中包括的特征点之间的匹配结果来补偿其位置，以及从清洁过程中捕获的图像中提取特征点。

5. 发明申请

US20120008513A1 METHOD AND APPARATUS FOR DETECTING TARGET FLOW IN WIRELESS COMMUNICATION SYSTEM 审中-公开
标题翻译：在无线通信系统中检测目标流的方法和装置
公开(公告)号：US20120008513A1
公开(公告)日：2012-01-12
申请号：US13178820
申请日：2011-07-08
申请人： Seung Min BAEK , Sang Ig RHO , Ho Cheol LEE , Jong Hun KIM , Jae Jin KIM
发明人： Seung Min BAEK , Sang Ig RHO , Ho Cheol LEE , Jong Hun KIM , Jae Jin KIM
IPC分类号： H04W24/00 , H04L12/26
CPC分类号： H04L43/028 , H04L43/026
摘要： An apparatus and method for detecting a target flow in a wireless communication system are provided. The target flow detection method includes receiving a packet, determining a behavior state of the packet, comparing the behavior state with a plurality of stored behavior signatures, retrieving, when the behavior state matches one of the stored behavior signatures, a target flow corresponding to the behavior signature, and instructing a packet processor to process the target flow.
摘要翻译：提供一种用于在无线通信系统中检测目标流的装置和方法。目标流检测方法包括接收分组，确定分组的行为状态，将行为状态与多个存储的行为签名进行比较，当行为状态与所存储的行为签名中的一个匹配时，检索对应于行为签名，并指示数据包处理器处理目标流。

6. 发明申请

US20060259845A1 Method and apparatus for acknowledging a bitwise data chunk in wireline and wireless communication systems 审中-公开
标题翻译：用于在有线和无线通信系统中确认按位数据块的方法和装置
公开(公告)号：US20060259845A1
公开(公告)日：2006-11-16
申请号：US11410286
申请日：2006-04-25
申请人： Seung-Min Baek
发明人： Seung-Min Baek
IPC分类号： H04L1/18 , G08C25/02
CPC分类号： H04L1/1809
摘要： A method and apparatus for acknowledging a bitwise data chunk in wireline and wireless communication systems. Data of at least one chunk is received from a sending node. Bitwise acknowledgement (ACK) information for each chunk is generated after a cumulative ACK. A predetermined message is transmitted in which the information is recorded, in a word having predetermined bits, in reverse order from a least significant bit. Lost chunk data is again received. The method and apparatus are useful in a wireless environment in which loss occurs frequently and can improve communication performance by applying an intuitive Selective Acknowledgement (SACK) format and a Selective Bitwise Chunk Acknowledgement (SBCA) for efficient bit use. The method and apparatus can securely transfer a signal of a public telephone network on a network through a multi-homing function and a multi-streaming function.
摘要翻译：一种用于在有线和无线通信系统中确认按位数据块的方法和装置。从发送节点接收至少一个块的数据。在累积ACK之后生成每个块的按位确认（ACK）信息。以与最低有效位相反的顺序，在具有预定位的字中发送其中信息被记录的预定消息。再次收到丢失的块数据。该方法和装置在其中经常发生损耗并且可以通过应用直观的选择性确认（SACK）格式和选择性逐位块确认（SBCA）来提高通信性能的无线环境中有用，用于有效的位使用。该方法和装置可以通过多归属功能和多流功能安全地传送网络上的公用电话网络的信号。

7. 发明申请

US20060190217A1 PARTICLE SAMPLING METHOD AND SENSOR FUSION AND FILTERING METHOD 有权
标题翻译：颗粒采样方法和传感器融合和滤波方法
公开(公告)号：US20060190217A1
公开(公告)日：2006-08-24
申请号：US11276127
申请日：2006-02-15
申请人： Suk-Han LEE , Seong-Soo LEE , Jang-Yong LEE , Seung-Min BAEK
发明人： Suk-Han LEE , Seong-Soo LEE , Jang-Yong LEE , Seung-Min BAEK
IPC分类号： G06F17/18
CPC分类号： G05B13/04 , G05B17/02
摘要： Disclosed is a technique for obtaining an_estimate and variance of each variable based on a constraint manifold. Particles (or samples) are sampled in order to filter and fuse ambiguous data or information on at least one state variable of a system using the particles. The sampling is carried out in consideration of an influence which non-linearity of the constraint manifold of_a system model, an observation model or another system model exerts on a probability distribution of the state variable. With this construction, it is possible to reduce decrease of fusion and filtering performance, decrease a Gaussian approximation error, and detect mismatched information.
摘要翻译：公开了一种用于基于约束歧管获得每个变量的估计和方差的技术。对粒子（或样本）进行采样，以便使用粒子对系统的至少一个状态变量进行过滤和融合不明确的数据或信息。考虑到系统模型，观测模型或其他系统模型对状态变量的概率分布施加的约束歧管的非线性的影响进行抽样。利用这种结构，可以减少融合和滤波性能的降低，降低高斯近似误差，并检测不匹配的信息。

8. 发明申请

US20130116826A1 ROBOT CLEANER AND CONTROLLING METHOD OF THE SAME 有权
标题翻译：机器清洁器及其控制方法
公开(公告)号：US20130116826A1
公开(公告)日：2013-05-09
申请号：US13809534
申请日：2011-07-05
申请人： Yiebin Kim , Seung min Baek , Yoojin Choi , Vadim Lutsiv , Victor Redkov , Alexey Potapov , Seongsoo Lee
发明人： Yiebin Kim , Seung min Baek , Yoojin Choi , Vadim Lutsiv , Victor Redkov , Alexey Potapov , Seongsoo Lee
IPC分类号： A47L11/20 , B25J13/08
CPC分类号： A47L11/20 , A47L2201/04 , B25J13/08 , G05D1/0246 , G05D1/0253 , G05D1/0274 , G05D2201/0203 , Y10S901/01 , Y10S901/09 , Y10S901/47
摘要： Disclosed are a robot cleaner and a method for controlling the same. The robot cleaner is capable of recognizing a position thereof by extracting one or more feature points having 2D coordinates information with respect to each of a plurality of images, by matching the feature points with each other, and then by creating a matching point having 3D coordinates information. Matching points having 3D coordinates information are created to recognize a position of the robot cleaner, and the recognized position is verified based on a moving distance measured by using a sensor. This may allow a position of the robot cleaner to be precisely recognized, and allow the robot cleaner to perform a cleaning operation or a running operation by interworking the precisely recognized position with a map.
摘要翻译：公开了一种机器人清洁器及其控制方法。机器人清洁器能够通过相对于多个图像中的每一个提取具有2D坐标信息的一个或多个特征点来识别其位置，通过使特征点彼此匹配，然后通过创建具有3D坐标的匹配点信息。创建具有3D坐标信息的匹配点以识别机器人清洁器的位置，并且基于通过使用传感器测量的移动距离来验证识别的位置。这可以允许机器人清洁器的位置被精确地识别，并且允许机器人清洁器通过将精确识别的位置与地图相互作用来执行清洁操作或运行操作。

9. 发明申请

US20100228394A1 MOBILE ROBOT AND CONTROLLING METHOD OF THE SAME 有权
标题翻译：移动机器人及其控制方法
公开(公告)号：US20100228394A1
公开(公告)日：2010-09-09
申请号：US12718380
申请日：2010-03-05
申请人： Dong Hoon YI , Young Gie KIM , Jeong Suk YOON , Seong Soo LEE , Jei Hun LEE , Seung Min BAEK , Yoo Jin CHOI , Sang IK NA , Su Uk CHOE , Yie Bin KIM
发明人： Dong Hoon YI , Young Gie KIM , Jeong Suk YOON , Seong Soo LEE , Jei Hun LEE , Seung Min BAEK , Yoo Jin CHOI , Sang IK NA , Su Uk CHOE , Yie Bin KIM
IPC分类号： G05D1/02 , G05B19/00 , G06F19/00
CPC分类号： G05D1/0274 , G05D1/0246 , G05D1/0255 , G05D2201/0203
摘要： Disclosed is a mobile robot and a controlling method of the same. An entire movement region is divided into a plurality of regions, and a partial map is gradually made by using feature points of a plurality of images of the divided regions. Then, the map is compensated into a closed curved line, thereby making an entire map. Furthermore, when the mobile robot is positioned at a boundary of neighboring regions of the cleaning region, the boundary where a closed curved line is formed, the mobile robot compensates for its position based on a matching result between feature points included in the map, and feature points extracted from images captured during a cleaning process.
摘要翻译：公开了一种移动机器人及其控制方法。整个移动区域被划分为多个区域，并且通过使用分割区域的多个图像的特征点逐渐地进行部分地图。然后，将地图补偿为闭合的曲线，从而制作整个地图。此外，当移动机器人位于清洁区域的相邻区域的边界处，形成闭合曲线的边界时，移动机器人基于地图中包括的特征点之间的匹配结果来补偿其位置，以及从清洁过程中捕获的图像中提取特征点。

10. 发明授权

US09060658B2 Mobile robot with single camera and method for recognizing 3D surroundings of the same 有权
标题翻译：具有单摄像头的移动机器人和识别3D环境的方法
公开(公告)号：US09060658B2
公开(公告)日：2015-06-23
申请号：US13262192
申请日：2010-03-12
申请人： Yoo-Jin Choi , Young-Gie Kim , Jeong-Suk Yoon , Seong-Soo Lee , Yie-Bin Kim , Seung-Min Baek , Sang-Ik Na , Su-Uk Choe , Dong-Hoon Yi , Jei-Hun Lee
发明人： Yoo-Jin Choi , Young-Gie Kim , Jeong-Suk Yoon , Seong-Soo Lee , Yie-Bin Kim , Seung-Min Baek , Sang-Ik Na , Su-Uk Choe , Dong-Hoon Yi , Jei-Hun Lee
IPC分类号： G06K9/00 , A47L9/00 , G01S15/93 , G05D1/02
CPC分类号： A47L9/009 , A47L2201/04 , G01S15/931 , G01S2015/938 , G05D1/0246 , G05D1/0253 , G05D1/0274 , G05D2201/0203
摘要： Disclosed are a mobile robot with a single camera capable of performing a cleaning process with respect to surroundings, and capable of more precisely making a 3D map of the surroundings including a plurality of feature points, and a method for recognizing 3D surroundings of the same. According to the method, images of the surroundings are captured, and a preset number of particles with respect to feature points of a first image are projected to a second image based on matching information of feature points extracted from the two images sequentially captured, thereby extracting 3D information of the surroundings.
摘要翻译：公开了具有能够对周围进行清洁处理的单个摄像机的移动机器人，并且能够更准确地制作包括多个特征点的周围环境的3D地图，以及用于识别其周围的3D环境的方法。根据该方法，捕获周围的图像，并且基于从顺序捕获的两个图像中提取的特征点的匹配信息，将关于第一图像的特征点的预定数量的粒子投影到第二图像，从而提取环境的3D信息。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式