2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)最新文献_第6页

Distributed Human 3D Pose Estimation and Action Recognition* 分布式人体三维姿态估计和动作识别*

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961741

Guoliang Liu, Tiantian Liu, G. Tian, Ze Ji

引用次数: 2

Obstacle Avoidance Using Stereo Vision and Deep Reinforcement Learning in an Animal-like Robot 基于立体视觉和深度强化学习的类动物机器人避障研究

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961639

Fuhai Ling, Alejandro Jiménez-Rodríguez, T. Prescott

引用次数: 2

Online memory learning for active object recognition 动态目标识别的在线记忆学习

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961612

Dengsheng Chen, Yuanlong Yu, Zhiyong Huang

{"title":"Online memory learning for active object recognition","authors":"Dengsheng Chen, Yuanlong Yu, Zhiyong Huang","doi":"10.1109/ROBIO49542.2019.8961612","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961612","url":null,"abstract":"Traditional CNN-based recognition algorithms are trained for limited labeled data, which may not perform well in a different environment due to the lack of adaptivity of the CNN networks. So the traditional CNN-based recognition algorithms can not play a good role in robot applications because the robots have to work in different environments. However, the robot can continuously perceive new images during its mission. These images contain lots of environment-related features but lack of labels. So the robots must learn the environment-related features adaptively with unlabeled data to further improve the performance of CNN-based recognition algorithms. We call this ability as active object recognition (OBR). In this paper, we designed a dynamic memory structure (DMS) which can adaptively learn the environment-related features online and embedded DMS into a VGG-16 network to implement active object recognition. We also evaluate our dynamic memory network of CIFAR-10 and CIFAR-100 classification dataset. The results show that by learning environment-related features, dynamic memory network achieves a better performance on classification accuracy. More importantly, the network can have the ability to improve itself while many times testing.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123218099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dual Closed-loop Impedance Control for Wheeled Mobile Manipulator in Trajectory Tracking 轮式移动机械臂轨迹跟踪的双闭环阻抗控制

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961872

Q. Tang, Pengjie Xu, Fangchao Yu, Jingtao Zhang, Zhipeng Xu

引用次数: 0

Design, Control and Analysis of a Dual-arm Continuum Flexible Robot System 双臂连续柔性机器人系统的设计、控制与分析

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961525

Chenxi Wang, Zhi Li, Yunfan Ren, Yuwen Deng, Shuang Song

引用次数: 1

Normalized Neural Network for Energy Efficient Bipedal Walking Using Nonlinear Inverted Pendulum Model 基于非线性倒立摆模型的节能双足行走归一化神经网络

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961646

Ruobing Wang, Samuel J. Hudson, Y. Li, Hongtao Wu, Chengxu Zhou

引用次数: 2

Wind Power Curve Data Cleaning Algorithm via Image Thresholding∗ 基于图像阈值分割的风电曲线数据清洗算法

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961448

Yahao Su, Fan Chen, Guoyuan Liang, Xinyu Wu, Yong Gan

{"title":"Wind Power Curve Data Cleaning Algorithm via Image Thresholding∗","authors":"Yahao Su, Fan Chen, Guoyuan Liang, Xinyu Wu, Yong Gan","doi":"10.1109/ROBIO49542.2019.8961448","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961448","url":null,"abstract":"Wind turbine data from the Supervisory Control And Data Acquisition (SCADA) system is very important for wind turbine conditional monitoring, wind power prediction and wind turbine performance evaluation. However, the SCADA data usually contains lots of abnormal data. This paper presents an image-based algorithm for abnormal data cleaning of wind power curve (WPC) data via image thresholding. The basic idea is to build a gray-level representation of the original binary image of WPC which is able to preserve the normal part as much as possible. Therefore, the cleaning operation is then turned into a problem of image segmentation. The proposed algorithm includes the following steps: First, the scatter data is converted into a binary image. Then the median of four distances are computed from each pixel in the image to the nearest connected domain boundary along four directions, and a gray level image is generated to strengthen the normal part, in the meantime, weaken the abnormal part. For all possible threshold t, the optimal to which makes the smallest Hu moment based dissimilarity of the segmented normal part with a reference WPC template, is finally determined. The proposed algorithm is compared with some data-based algorithms as well as an image-based mathematical morphology operation (MMO) algorithm. Experiments carried out on WPC data of 17 wind turbines from a wind farm verified the effectiveness and accuracy of the proposed method.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124732281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 10

OGBPS: Orientation And Gradient Based Path Smoothing Algorithm For Various Robot Path Planners OGBPS:基于方向和梯度的各种机器人路径平滑算法

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961626

Xiaotong Wang, Biao Hu, Meng Zhou

{"title":"OGBPS: Orientation And Gradient Based Path Smoothing Algorithm For Various Robot Path Planners","authors":"Xiaotong Wang, Biao Hu, Meng Zhou","doi":"10.1109/ROBIO49542.2019.8961626","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961626","url":null,"abstract":"It is significant to plan a smooth trajectory for high-speed wheeled mobile robots working in a cluttered environment. The trajectory generated by most of the previously proposed path planners is not smooth enough for robot motion, especially under kino-dynamic constraints. An improved smoothing algorithm is proposed in this work as a solution for most of the previously proposed path planners to deal with the rugged paths, which may cause abrupt and angular turns of robots. The improved solution we proposed could be applied to many mainstream path planners (like Theta*, A*, RRT, RRT*, RRT#, SORRT*, PRM) as a post-smoothing algorithm, which is called orientation and gradient-based path smoothing (OGBPS). The OGBPS algorithm is derived from both orientation-angle-based and gradient-based path deformations to obtain a high-quality path. The objective of path deformations in this work is to improve path smoothness, lower maximum curvature and path length. Sufficient simulation experiments are well conducted to demonstrate the effectiveness of our approach. It is verified that the proposed algorithm can improve the quality of the previous path while respecting the kino-dynamic constraints through experiments. The simulation results indicate the advantages (smaller maximum curvature and smaller path length) of the proposed algorithm compared with several state-of-the-art smoothing algorithms.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129697938","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Deep Learning Training with Simulated Approximate Multipliers 模拟近似乘数的深度学习训练

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/ROBIO49542.2019.8961780

Issam Hammad, K. El-Sankary, J. Gu

{"title":"Deep Learning Training with Simulated Approximate Multipliers","authors":"Issam Hammad, K. El-Sankary, J. Gu","doi":"10.1109/ROBIO49542.2019.8961780","DOIUrl":"https://doi.org/10.1109/ROBIO49542.2019.8961780","url":null,"abstract":"This paper presents by simulation how approximate multipliers can be utilized to enhance the training performance of convolutional neural networks (CNNs). Approximate multipliers have significantly better performance in terms of speed, power, and area compared to exact multipliers. However, approximate multipliers have an inaccuracy which is defined in terms of the Mean Relative Error (MRE). To assess the applicability of approximate multipliers in enhancing CNN training performance, a simulation for the impact of approximate multipliers error on CNN training is presented. The paper demonstrates that using approximate multipliers for CNN training can significantly enhance the performance in terms of speed, power, and area at the cost of a small negative impact on the achieved accuracy. Additionally, the paper proposes a hybrid training method which mitigates this negative impact on the accuracy. Using the proposed hybrid method, the training can start using approximate multipliers then switches to exact multipliers for the last few epochs. Using this method, the performance benefits of approximate multipliers in terms of speed, power, and area can be attained for a large portion of the training stage. On the other hand, the negative impact on the accuracy is diminished by using the exact multipliers for the last epochs of training.","PeriodicalId":121822,"journal":{"name":"2019 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129761209","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 8

ROBIO 2019 Author Index ROBIO 2019作者索引

2019 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2019-12-01 DOI: 10.1109/robio49542.2019.8961636

引用次数: 0