2016 IEEE International Conference on Information and Automation (ICIA)最新文献_第9页

Robust autopilots based on the fuzzy model reference learning control 基于模糊模型参考学习控制的鲁棒自动驾驶仪

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831976

Lintao Zheng, Guodong Xu

引用次数: 0

Real-time rendering of large-scale terrain based on OpenCL 基于OpenCL的大规模地形实时渲染

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7832007

Xiangkun Guo, Jishen Liu

引用次数: 0

Transleg: A wire-driven leg-wheel robot with a compliant spine 跨腿机器人:一种由线驱动的腿轮机器人，具有柔顺的脊柱

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831789

Zhong Wei, G. Song, Ying Zhang, Huiyu Sun, Guifang Qiao

{"title":"Transleg: A wire-driven leg-wheel robot with a compliant spine","authors":"Zhong Wei, G. Song, Ying Zhang, Huiyu Sun, Guifang Qiao","doi":"10.1109/ICINFA.2016.7831789","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831789","url":null,"abstract":"A novel leg-wheel robot, Transleg, is proposed in this paper. Differing from the existing leg-wheel robots, Transleg is driven by wire, so the transmission mechanism is simple and the weight is reduced. Transleg adopts a transformable leg-wheel mechanism which has two degrees of freedom in the legged mode and one degree of freedom in the wheeled mode. The motions in and switching between the two modes are achieved by the same actuators. That is to say only two actuators are needed in one leg-wheel mechanism. The spine contributes significantly to the motion of the quadrupeds, so a compliant spine mechanism is designed for Transleg, which is actuated by two actuators and can bend in yaw and pitch directions. The leg-wheel and spine mechanisms and their kinematic analysis are described in this paper. To verify the feasibility of the leg-wheel mechanisms, the motions of Transleg without spine bending in legged and wheeled modes and switching between the two modes are simulated. Experiments on the motion of the prototype of the leg-wheel and spine mechanisms are also performed to validate the effectiveness of the two proposed mechanisms.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128737286","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

Design and path planning of Massagebot: One massaging robot climbing along the acupuncture points 按摩机器人的设计与路径规划:一个按摩机器人沿着穴位爬行

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831959

Hongli Chen, Xinyu Wu, Wei Feng, Tiantian Xu, Yong He

引用次数: 5

Visualization automatic programming system of bending machine based on machine vision 基于机器视觉的折弯机可视化自动编程系统

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831897

Wenqiang Wu, Jialiang Xie, Guanghuan Chen, Hebang Lin, Lingqian Kong, Chunliang Zhang

引用次数: 2

Opposition learning adaptive cross-generation differential evolution algorithm based multi-objective optimization of rolling schedule for tandem cold rolling 基于对立学习自适应跨代差分进化算法的冷连轧轧制规程多目标优化

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831843

Li Yong, Fangfang Lei, Wang Yu

引用次数: 2

The residual vibration impact on the multiple target positioning time for array operation 残余振动对阵列多目标定位时间的影响

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831796

Zhijun Yang, Youdun Bai, Xin Chen, Y. Guan, Wenxian Feng

{"title":"The residual vibration impact on the multiple target positioning time for array operation","authors":"Zhijun Yang, Youdun Bai, Xin Chen, Y. Guan, Wenxian Feng","doi":"10.1109/ICINFA.2016.7831796","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831796","url":null,"abstract":"Array processing, such as micro structure punching, wire bonding of LED array or integrated circuit, laser drilling, is widely used in electronic/optics manufacturing. In the processing, high speed positioning can cause strong excitation on the machine structure, which results in severe structure vibration and long settling time. Especially in multiple target positioning process, vibration exists in the whole procedure, so that the positioning means that the vibration amplitude is smaller than a given accuracy instead of completely still. According to vibration theory, new excitation will enhance or weaken the residual vibration with different phase, therefore, it is important to know what the impact of residual vibration on the continuous positioning. In this paper, the dynamic response of multiple target positioning is analyzed with flexible multibody dynamics. The optimal design of motion profile for a single positioning is performed and the positioning time is reduced by 10%. The impact of residual vibration is studied by choosing different start time, and the positioning time under corresponding residual vibration (amplitude and phase) is calculated. It is found that when the residual vibration is negative to the motion direction, the positing time is decreased, and vice versa. It is also found that the positioning time saving is much greater than the start time delay at the first few cycles. Up to 10% throughput can be improved by choosing a suitable start time for array processing. Analytic and experimental results match well. Our finding is important for improving the throughput of massive production of arrays processing in information technology.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121087980","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

Superpixel-based optimal seamline detection via graph cuts for panoramic images 基于超像素的全景图像最佳缝线检测

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7832053

Li Li, Jian Yao, Renping Xie, Menghan Xia, Binbin Xiang

引用次数: 7

Dynamic matching model of ultrasonic transducer based on digital inductance 基于数字电感的超声换能器动态匹配模型

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831895

Zhili Long, Yuxiang He, Zuohua Li, Jianjun Zou, Zhenzhong Sun

引用次数: 5

Convolutional neural network bottleneck features for bi-directional generalized variable parameter HMMs 双向广义变参数hmm的卷积神经网络瓶颈特征

2016 IEEE International Conference on Information and Automation (ICIA) Pub Date : 2016-08-01 DOI: 10.1109/ICINFA.2016.7831988

Rongfeng Su, Xunying Liu, Lan Wang

{"title":"Convolutional neural network bottleneck features for bi-directional generalized variable parameter HMMs","authors":"Rongfeng Su, Xunying Liu, Lan Wang","doi":"10.1109/ICINFA.2016.7831988","DOIUrl":"https://doi.org/10.1109/ICINFA.2016.7831988","url":null,"abstract":"Recently, convolutional neural networks (CNNs) have been applied successfully to acoustic modelling in speech recognition. As the bottleneck features from CNNs contain inherently discriminative and rich context information, the standard approach is to augment the conventional acoustic features with the CNN bottleneck features in a tandem framework. To better capture the highly complex relationship between them, a novel bidirectional generalized variable parameter HMM (GVP-HMM) based approach is proposed in this paper. In this approach, the trajectories of continuous acoustic features space HMM parameters, as well as the model space linear transforms against CNN bottleneck features are modelled by polynomial functions. The optimal GVP-HMM model structure for each direction, which is determined by the locally varying polynomial parameters and degrees, can be automatically learnt using model selection techniques. The proposed bi-directional GVP-HMM based approach gave a word error rate of 12.22% on the Aurora 4 task. In particular, a significant error rate reduction of 18.09% relative was obtained over the baseline tandem HMM system using CNN bottleneck features on the secondary microphone channel condition.","PeriodicalId":389619,"journal":{"name":"2016 IEEE International Conference on Information and Automation (ICIA)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127710278","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: 3