2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)最新文献_第8页

CSDM: Fusion of orthographic contour signature and distribution matrix for 3D object global representation and object recognition 面向三维目标全局表示和目标识别的正射影轮廓特征与分布矩阵融合

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324778

Mingliang Fu, Haitao Luo, Weijia Zhou

引用次数: 0

Experimental study on an automatic drilling strategy for lunar regolith coring 月壤岩心自动钻孔策略的实验研究

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324611

Jieneng Liang, L. Ding, Shengyuan Jiang, Yong Pang, Z. Deng, Junyue Tang

引用次数: 2

FEM-based training of artificial neural networks for modular soft robots 基于有限元法的模块化软体机器人人工神经网络训练

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324448

G. Runge, M. Wiese, A. Raatz

引用次数: 33

Improving robustness of monocular VT&R system with multiple hypothesis 提高多假设单目VT&R系统的鲁棒性

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324443

Xubin Lin, Weinan Chen, Li He, Y. Guan, Guanfeng Liu

引用次数: 1

Estimation of upper limb muscle stiffness based on artificial neural network 基于人工神经网络的上肢肌肉刚度估计

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324724

Ze Cui, Wangyang Han, Dong-Hai Qian, Yumei Wang, Guowen Qiu, Danjie Zhu

引用次数: 2

Basic research of upper limb work support system “My cybernic robot arm” for hemiplegic persons 偏瘫患者上肢工作支撑系统“我的机器人手臂”的基础研究

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324526

Hiroaki Toyama, H. Kawamoto, Y. Sankai

{"title":"Basic research of upper limb work support system “My cybernic robot arm” for hemiplegic persons","authors":"Hiroaki Toyama, H. Kawamoto, Y. Sankai","doi":"10.1109/ROBIO.2017.8324526","DOIUrl":"https://doi.org/10.1109/ROBIO.2017.8324526","url":null,"abstract":"Hemiplegic persons have difficulties in handling many kinds of tasks in daily life because they must perform the tasks by only the unaffected arm and hand. In order to realize upper limb work support for hemiplegic persons, a robot arm that has ability to grip various daily necessities and cooperate with the nonparalyzed side in same work space is required. The purposes of this study is to develop a novel assistance system “My Cybernic Robot Arm” that has measurement function and adjustment function of grip force, and to confirm the basic performance of the system through the benchmark experiments. The system is composed of a robot arm and hand, a sensing unit and a control unit. The system has grip force adjustment function and learning function of grip force by grip force teaching playback. The robot arm has six degrees of freedom and was designed with minimum size to cover an area of the table tasks so as not to narrow the work area of the nonparalyzed side. The sensing unit can measure the grip force and centroid position of grip force calculated by using a capacitance feature. In addition, developed sensing unit is small enough to be embedded in the fingertip of robot hand. We conducted verification of the sensing unit accuracy and grip force teaching and reproduction as basic experiments to confirm the basic performance of the system. The results showed that the system could measure grip force and load center of gravity position. In addition, it was confirmed that the system could learn the appropriate grip force and adjust the grip force by grip force teaching playback. In conclusion, the system has basic performance because it can grip the object with appropriate grip force. This system is expected to support upper limb work of hemiplegic persons such as desk work in everyday life, and improve QOL (Quality of life) and encourage independence.","PeriodicalId":197159,"journal":{"name":"2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121215477","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

Painlevé paradox during passive dynamic walking of biped robots 双足机器人被动动态行走过程中的疼痛水平悖论

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324590

Ye Kuang, Yunian Shen, Wei Wang, Sai Zhang

{"title":"Painlevé paradox during passive dynamic walking of biped robots","authors":"Ye Kuang, Yunian Shen, Wei Wang, Sai Zhang","doi":"10.1109/ROBIO.2017.8324590","DOIUrl":"https://doi.org/10.1109/ROBIO.2017.8324590","url":null,"abstract":"An analytical method is proposed to study the walking stability problem and Painlevé paradox during the passive walking of bipedal robots. The whole walking process can be seen as the repetition of the four states, i.e. left single-leg support state, double-legs support state, right single-leg support state and double-legs support state. Based on the multiple states, the hybrid rigid body frictional model is established. The contact constraint is treated by completely inelastic collision hypothesis, and the initial conditions are calculated by conservation of angular momentum. Dynamic equations for the four system states are derived by using Lagrange equation. The relationship between the ratio ft/fn and time t under initial condition of the stable walking is obtained, and by using this relationship, region of friction coefficient for the stable walking state is obtained. The possible singular phenomenon — Painlevé paradox problem is analyzed. The critical value of the coefficient of friction for Painlevé paradox is specified. In addition, the analytical results of robot's dynamic responses are compared with the finite element numerical simulation. It shows that the results from the flexible body model are totally different from solutions calculated by the rigid body model. The critical value of coefficient of friction is smaller than those of the rigid body model.","PeriodicalId":197159,"journal":{"name":"2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"30 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124895838","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

Generalization of task model using compliant movement primitives in a bimanual setting 基于柔性运动原语的任务模型泛化

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324707

Aleksandar Batinica, B. Nemec, J. Santos-Victor, A. Gams, M. Raković

{"title":"Generalization of task model using compliant movement primitives in a bimanual setting","authors":"Aleksandar Batinica, B. Nemec, J. Santos-Victor, A. Gams, M. Raković","doi":"10.1109/ROBIO.2017.8324707","DOIUrl":"https://doi.org/10.1109/ROBIO.2017.8324707","url":null,"abstract":"Compliant Movement Primitives (CMPs) showed good performance for a desirable behavior of robots to maintain low trajectory error while being compliant without knowing the dynamic model of the task. This framework uses the integral representation of reference trajectories in a feedback loop together with driving joint torques that represent the feed-forward control term. To achieve CMPs generalization, refer-ence trajectories (represented in the form of task space position trajectories) are encoded as Dynamic Movement Primitives (DMPs) while the feed-forward torques are learned through the Gaussian Process Regression (GPR) and are represented as a combination of radial basis functions. This paper extends the existing framework through the generalization of CMPs in bimanual settings that can concurrently achieve low trajectory errors in relative task space and compliant behavior in absolute task space. To achieve this behavior of the bimanual robotic system, the control terms derived from CMP framework are extended with the symmetric control approach. We show how the task-specific bimanual task dynamics can be learned and generalized to different task parameters that influence the task space trajectory and to a different load. Real-world results on a bimanual Kuka LWR-4 robots configuration confirms the usability of the extended framework.","PeriodicalId":197159,"journal":{"name":"2017 IEEE International Conference on Robotics and Biomimetics (ROBIO)","volume":"427 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116568607","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

Sloth and slow loris inspired behavioral controller for a robotic agent 树懒和懒猴启发了机器人代理的行为控制器

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324693

Lakshmi Velayudhan, R. Arkin

引用次数: 4

Force tracking impedance control with moving target 运动目标力跟踪阻抗控制

2017 IEEE International Conference on Robotics and Biomimetics (ROBIO) Pub Date : 2017-12-01 DOI: 10.1109/ROBIO.2017.8324608

Houde Liu, Weifeng Lu, Xiaojun Zhu, Xueqian Wang, Bin Liang

引用次数: 4