检索结果-内蒙古大学图书馆

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Peng, Yuanzhe Han, Weichao Ou, Yongsheng Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728163215

Semantic segmentation as a pixel-wise segmentation task provides rich object information, which is an important research topic in robotic perception. It has been widely applied in many fields, such as autonomous driving and robot navigation. In the application of understanding road scene, the semantic segmentation model should accurately describe the appearance and shape of different categories of objects. In addition, the semantic segmentation model need to understand the spatial relationships between different categories. In order to improve the performance of semantic segmentation model for road scene, we present a model based on encoder-decoder structure with dilated convolution. We apply this model on the Cityscapes dataset and compare it with other classical models. To assess performance, we rely on the standard Jaccard Index IoU (Intersection over Union) and mIoU (mean Intersection over Union). The experimental results verify that this model can effectively improve the performance of semantic segmentation and meet the requirements for road scene. © 2019 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A Grasping CNN with Image Segmentation for Mobile Manipulating Robot

A Grasping CNN with Image Segmentation for Mobile Manipulati...

引用

IEEE International Conference on robotics and Biomimetics

作者： Yingying Yu Zhiqiang Cao Shuang Liang Zhicheng Liu Junzhi Yu Xuechao Chen State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Intelligent Robots and Systems Intelligent Robotics Institute BIT Beijing China

This paper presents a grasping convolutional neural network with image segmentation for mobile manipulating robot. The proposed method is cascaded by a feature pyramid network FPN and a grasping network DrGNet. The FPN network combined with point cloud clustering is used to obtain the mask of the target object. Then, the grayscale map and the depth map corresponding to the target object are combined and sent to the DrGNet network for providing multi-scale images. On this basis, depthwise separable convolution is used for encoding. The results of encoders are refined according to the light-weight RefineNet as well as sSE, which can achieve a better grasp detection. The proposed method is verified by the experiments on mobile manipulating robot.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Binocular depth estimation using convolutional neural network with siamese branches

Binocular depth estimation using convolutional neural networ...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Liu, Guodong Jiang, Guolai Xiong, Rong Ou, Yongsheng Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen518055 China University of Chinese Academy of Sciences Beijing100049 China Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergic Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China

ISBN: (纸本)9781728163215

Binocular depth estimation is a hot research topic in computer vision. Traditional methods need high precision camera calibration and key point matching, but the results are not ideal. In this paper, we introduce an approach of binocular depth estimation method based on deep learning. A new convolutional neural network is designed, which consists of two sub-networks. The first sub-network is a deep network with Siamese branches and 3D convolutional layer, it learns parallax and global information and generates a global depth estimation result in low resolution. The second is a fully convolutional deep network, which reconstructions the depth map to original resolution. The two sub-networks are connected by a pool pyramid. Experiments are taken on the Middlebury Stereo Dataset show that the proposed method can generate much more accurate depth image than traditional methods. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Haptic and visual enhance-based motor imagery BCI for rehabilitation lower-limb exoskeleton

Haptic and visual enhance-based motor imagery BCI for rehabi...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Duan, Shengcai Wang, Can Li, Mengyao Long, Xingguo Wu, Xinyu Feng, Wei Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology China University of Chinese Academy of Sciences China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

The motor imagery (MI) based on electroencephalogram (EEG) via non-invasive Brain Computer Interface (BCI) is a promising interactive method to provide effective communication between the disabled and rehabilitation robotic device. Interactive efficiency of MI-based BCI largely relies on the performance of subject's motor imagery. In this work, we proposed a simple and effective paradigm based on visual and haptic modalities for a high-quality initialized and calibrated MI-BCI model. Five healthy male subjects participated in motor imagery experiments with two paradigms. The proposed paradigm utilized mixed cues based on the visual and haptic modalities where the haptic cues were provided by the mini vibration motors, and a traditional paradigm utilized the ordinary arrow visual cues. The analysis of the topographic maps was conducted to illustrate the differences of the EEG in both paradigms. The average classification accuracy of motor imagery in the proposed paradigm improved about 14% compared to the traditional paradigm. Furthermore, a subject completed the qualitative verification experiment of the trained model on a rehabilitation lower-limb exoskeleton which proved the feasibility of the proposed paradigm. © 2019 IEEE.

关键词： Brain computer interface

来源：评论

学校读者我要写书评

暂无评论

GC-IGTG: A rehabilitation gait trajectory generation algorithm for lower extremity exoskeleton

GC-IGTG: A rehabilitation gait trajectory generation algorit...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： He, Yong Wu, Xinyu Ma, Yue Cao, Wujing Li, Nan Li, Jinke Feng, Wei Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Shenzhen518055 China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

It is important to offer a natural and personalized rehabilitation gait trajectory, especially in the early stages of walking rehabilitation, for the patients with lower limb disability. Lower extremity exoskeleton has been proven to be efficient to provide highly repeatable and accurate rehabilitation exercise, but most existing exoskeletons' gait trajectories won't vary with the users. This paper proposes an algorithm, named as gait cell based individualized gait trajectory generation (GC-IGTG), for the purpose of offering a natural and personalized gait trajectory reference for the lower extremity exoskeleton based on the body parameters of the patients. The GC-IGTG is based on extreme learning machine and AutoEncoder, which makes it achieve fast training speed and suitable for small sample training conditions. The gait cell concept is proposed to improve the efficiency and safety of the algorithm. The experimental results indicate that the generated trajectories with GC-IGTG are almost identical to the original ones. © 2019 IEEE.

关键词： Patient rehabilitation

来源：评论

学校读者我要写书评

暂无评论

Fuzzy Adaptive Control-based Real-time Obstacle Avoidance under Uncertain Perturbations

Fuzzy Adaptive Control-based Real-time Obstacle Avoidance un...

引用

International Conference on advanced robotics and Mechatronics (ICARM)

作者： Yingbai Hu Guang Chen Longbin Zhang Hang Su Mengyao Li Yunus Schmirander Hu Cao Alois Knoll Chair of Robotics Artificial Intelligence and Realtime Systems Technical University of Munich Munich Germany College of Automotive Engineering Tongji University Shanghai China KTH MoveAbility Lab KTH Royal Institute of Technology Stockholm Sweden Politecnico di Milano Milano Italy Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (数字)9781728164793

ISBN: (纸本)9781728164809

Dynamic Movement Primitives (DMPs) framework is a powerful approach to imitate motor skills, which has outstanding characteristics, such as convergence to the goal position and good imitation performance. Considering complex motion scenes of manipulators, such as changing the goal position or adding obstacles, the original DMPs framework is not sufficient for the requirements. In this paper, we propose a learning control-based hierarchical control strategy to adapt to new goal positions and avoid obstacles: the high-level learning scheme is targeted at imitating the motor skill and generating the optimization trajectory for obstacle avoidance; the lower-level control scheme focuses on the safety and stability of the robot's movement with unknown disturbances. Firstly, the enhanced DMPs framework is presented to imitate the trajectory from human demonstrations, where the novel DMPs can adapt to new goal position with the changing goal, and avoid single or multiple obstacles. Then, the fuzzy adaptive control method is employed to control redundant manipulators, where the fuzzy logic system (FLS) is incorporated to approximate an unknown nonlinear function term of the unknown disturbance. Finally, the effectiveness of the proposed learning-control strategy is demonstrated with simulation results. The results show that the developed hierarchical strategy has good performance for new goal adaptation and obstacle avoidance.

关键词： Collision avoidance Trajectory Manipulator dynamics Nonlinear dynamical systems Adaptive control

来源：评论

学校读者我要写书评

暂无评论

Real-world Robot Reaching Skill Learning Based on Deep Reinforcement Learning

Real-world Robot Reaching Skill Learning Based on Deep Reinf...

引用

第32届中国控制与决策会议

作者： Naijun Liu Tao Lu Yinghao Cai Rui Wang Shuo Wang State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced TechnologyChinese Academy of Sciences Center for Excellence in Brain Science and Intelligence Technology of the Chinese Academy of Sciences

Traditional programming method can achieve certain manipulation tasks with the assumption that robot environment is known and ***,with robots gradually applied in more domains,robots often encounter working scenes which are complicated,unpredictable,and *** overcome the limitation of traditional programming method,in this paper,we apply deep reinforcement learning(DRL) method to train robot agent to obtain skill *** policy trained with DRL on real-world robot is time-consuming and costly,we propose a novel and simple learning paradigm with the aim of training physical robot ***,our method train a virtual agent in an simulated environment to reach random target position from random initial ***,virtual agent trajectory sequence obtained with the trained policy,is transformed to real-world robot command with coordinate transformation to control robot performing reaching *** show that the proposed method can obtain self-adaptive reaching policy with low training cost,which is of great benefits for developing intelligent and robust robot manipulation skill system.

关键词： Robot reaching skill learning deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic obstacle tracking based on high-definition map in urban scene

Dynamic obstacle tracking based on high-definition map in ur...

引用

2019 IEEE International Conference on robotics and Biomimetics, ROBIO 2019

作者： Li, Yuxiao Wang, Can Su, Zhilong Duan, Shengcai Wu, Xinyu Chinese Academy of Sciences Guangdong Provincial Key Lab of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Shenzhen518055 China CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institutes of Advanced Technology Shenzhen518055 China Shenzhen College of Advanced Technology University of Chinese Academy of Sciences Beijing100049 China Department of Mechanical and Automation Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)9781728163215

The application of High-Definition map can realize centimeter-level position in urban scenes, the development of deep learning has made great breakthrough in the point cloud dynamic obstacle recognition. All these technologies make obstacle detection and tracking based on High-Definition map effectively realize in the modern smart city scene. It is different from the previous obstacle detection and tracking methods based purely on vision the using of High-Definition map can provide high-precision positioning and reduce the difficulty of point cloud classification. The using of lidar also solves the problem of up-to-scale in dynamic detection. In this paper, we put forward a new Multi-camera Lidar Point Cloud Map, we complete the map at normal speed on the highway and get a satisfactory result. At the same time, we also find a robust combination of traditional kalman filter, Hungary algorithm and current deep learning to solve dynamic obstacle tracking and detection. The experimental results show that our system can effectively complete the special problem of generating map and target tracking on urban scene. © 2019 IEEE.

关键词： Optical radar

来源：评论

学校读者我要写书评

暂无评论

A registration-aided domain adaptation network for 3D Point cloud based place recognition

arXiv

引用

arXiv 2020年

作者： Qiao, Zhijian Hu, Hanjiang Shi, Weiang Chen, Siyuan Liu, Zhe Wang, Hesheng Department of Automation Insititue of Medical Robotics Key Laboratory of System Control and Information Processing of Ministry of Education Key Laboratory of Marine Intelligent Equipment and System of Ministry of Education Shanghai Jiao Tong University Shanghai200240 China Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing Institute of Technology China Department of Mechanical Engineering Carnegie Mellon University United States Department of Computer Science and Technology University of Cambridge United Kingdom

In the field of large-scale SLAM for autonomous driving and mobile robotics, 3D point cloud based place recognition has aroused significant research interest due to its robustness to changing environments with drastic daytime and weather variance. However, it is time-consuming and effort-costly to obtain high-quality point cloud data for place recognition model training and ground truth for registration in the real world. To this end, a novel registration-aided 3D domain adaptation network for point cloud based place recognition is proposed. A structure-aware registration network is introduced to help to learn features with geometric information and a 6-DoFs pose between two point clouds with partial overlap can be estimated. The model is trained through a synthetic virtual LiDAR dataset through GTA-V with diverse weather and daytime conditions and domain adaptation is implemented to the real-world domain by aligning the global features. Our results outperform state-of-the-art 3D place recognition baselines or achieve comparable on the real-world Oxford RobotCar dataset with the visualization of registration on the virtual dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Three dimensional computer graphics

来源：评论

学校读者我要写书评

暂无评论

LED Visible Light Localization Based on Illuminance Analysis

LED Visible Light Localization Based on Illuminance Analysis

引用

IEEE International Conference on Real-time Computing and robotics (RCAR)

作者： Chenting Gu Xiaofeng Liu Yongsheng Ou Chao Liu Hao Tao Tianyun Shi HoHai University Nanjing China Chinese Academy of Sciences Shenzhen Institutes of Advanced Technology Shenzhen China Key Laboratory of Special Robots Changzhou China Changzhou Key Laboratory of Robots and Intelligent Technology Changzhou China College of IoT Engineering Hohai University Changzhou China Key Laboratory of Human-Machine-Intelligence Synergic Systems Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China Guangdong Provincial Key Laboratory of Robotics and Intelligent System Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences Shenzhen China China Ship Development and Design Center Wuhan Tian-yun Shi China Academy of Railway Sciences Corporation Limited Beijing China

ISBN: (数字)9781728172934

ISBN: (纸本)9781728172941

LED based positioning technology has recently become a popular choice due to the low cost, convenience for maintenance and strong adaptability to the environment. In this paper, we introduce an illuminance-distance analysis method with a rolling shutter camera, for a low-cost indoor positioning system to improve robustness in the case of insufficient LEDs. Firstly, the binary threshold method is used to decode the light signals. Then the gray value information of image is extracted to analyze the depth of LEDs, using the illuminance attenuation theorem. It provides potential solution to the position of devices with the camera by combining depth information, image and camera intrinsic. Our proposed method reduced the minimum number of LEDs observed by the camera from three to two, using only the camera. We evaluated the proposed method with real scene data and demonstrated the effectiveness of illumination-distance model based localization.

关键词： Light emitting diodes Cameras Receivers Light sources Robots Mathematical model Image sensors

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：