您的位置: 专家智库 > >

国家自然科学基金(61175107)

作品数:7 被引量:40H指数:3
相关作者:郭伟李满天蔡鹤皋谭宏伟于海涛更多>>
相关机构:哈尔滨工业大学解放军信息工程大学双钱集团(江苏)轮胎有限公司更多>>
发文基金:国家自然科学基金国家高技术研究发展计划更多>>
相关领域:自动化与计算机技术电子电信更多>>

文献类型

  • 7篇中文期刊文章

领域

  • 6篇自动化与计算...
  • 1篇电子电信

主题

  • 3篇机器人
  • 2篇四足机器人
  • 1篇动力学仿真
  • 1篇音素
  • 1篇音素识别
  • 1篇运动控制
  • 1篇神经网
  • 1篇神经网络
  • 1篇识别方法
  • 1篇双足机器人
  • 1篇气动
  • 1篇气动肌腱
  • 1篇扰动观测器
  • 1篇拮抗
  • 1篇网络
  • 1篇开源
  • 1篇可信网络
  • 1篇机器人仿真
  • 1篇观测器
  • 1篇仿真

机构

  • 4篇哈尔滨工业大...
  • 1篇解放军信息工...
  • 1篇双钱集团(江...

作者

  • 3篇郭伟
  • 2篇李满天
  • 1篇于海涛
  • 1篇余溢
  • 1篇谭宏伟
  • 1篇查富生
  • 1篇陈琦
  • 1篇张文林
  • 1篇李弼程
  • 1篇王鹏飞
  • 1篇刘国才
  • 1篇牛铜
  • 1篇蔡鹤皋
  • 1篇李爱镇
  • 1篇段飞

传媒

  • 3篇机械与电子
  • 1篇机械工程学报
  • 1篇信息工程大学...
  • 1篇Chines...
  • 1篇Chines...

年份

  • 1篇2015
  • 1篇2014
  • 3篇2013
  • 2篇2012
7 条 记 录,以下是 1-7
排序方式:
基于ODE的四足机器人仿真平台研究被引量:3
2012年
将虚拟样机搭建定义为两步运算,提出了利用ODE引擎进行机器人仿真平台设计开发的方法。设计并实现了的四足机器人仿真平台,在仿真平台上进行了四足机器人的步行仿真实验,验证了基于ODE引擎的机器人仿真平台开发方法的有效性和简便性。
李满天李爱镇郭伟
关键词:四足机器人动力学仿真
基于气动肌腱驱动的拮抗式仿生关节设计与控制被引量:21
2012年
关节是仿生机器人机械系统的基本组成元素。在面向环境交互的仿生机器人系统中,关节的质量、体积以及功/重比直接影响系统的工作性能。与传统的电气、液压驱动方式相比,采用气动肌腱的驱动方式具有质量小、体积小和高功/重比等优势,具有广阔的应用前景。从功能仿生角度出发,在分析人体肘关节骨骼结构特点和肌肉发力方式的基础上,设计一种基于气动肌腱驱动的拮抗式仿生关节。建立单根肌腱的数学模型,通过搭建气动肌腱工作特性试验平台对肌腱进行性能测试,采用最小二乘法对模型参数进行辨识。针对拮抗式仿生关节的构型进行运动学和动力学分析,提出基于肌腱模型的偏置输入气压控制方法,设计基于关节估计阻尼的扰动观测器对名义模型进行补偿,通过数值仿真对控制方法进行有效性验证。建立仿生关节运动控制试验系统,通过单关节轨迹跟踪试验验证了肌腱理论模型的正确性及控制策略的有效性。
于海涛郭伟谭宏伟李满天蔡鹤皋
关键词:气动肌腱运动控制扰动观测器
Analysis on the Performance of the SLIP Runner with Nonlinear Spring Leg被引量:7
2013年
The spring-loaded inverted pendulum(SLIP) has been widely studied in both animals and robots.Generally,the majority of the relevant theoretical studies deal with elastic leg,the linear leg length-force relationship of which is obviously conflict with the biological observations.A planar spring-mass model with a nonlinear spring leg is presented to explore the intrinsic mechanism of legged locomotion with elastic component.The leg model is formulated via decoupling the stiffness coefficient and exponent of the leg compression in order that the unified stiffness can be scaled as convex,concave as well as linear profile.The apex return map of the SLIP runner is established to investigate dynamical behavior of the fixed point.The basin of attraction and Floquet Multiplier are introduced to evaluate the self-stability and initial state sensitivity of the SLIP model with different stiffness profiles.The numerical results show that larger stiffness exponent can increase top speed of stable running and also can enlarge the size of attraction domain of the fixed point.In addition,the parameter variation is conducted to detect the effect of parameter dependency,and demonstrates that on the fixed energy level and stiffness profile,the faster running speed with larger convergence rate of the stable fixed point under small local perturbation can be achieved via decreasing the angle of attack and increasing the stiffness coefficient.The perturbation recovery test is implemented to judge the ability of the model resisting large external disturbance.The result shows that the convex stiffness performs best in enhancing the robustness of SLIP runner negotiating irregular terrain.This research sheds light on the running performance of the SLIP runner with nonlinear leg spring from a theoretical perspective,and also guides the design and control of the bio-inspired legged robot.
YU HaitaoLI MantianCAI Hegao
四足机器人在崎岖路面的路径规划研究
2013年
对于四足机器人过崎岖路面的问题,利用A*算法,以最低代价为目标函数得到较优备选路径,然后利用1个二阶系统结合4个优化指标,对备选路径进行比较,选择出1条较优路径。仿真实验结果证明了此方法的有效性。
余溢郭伟
关键词:四足机器人
Fast filtering algorithm based on vibration systems and neural information exchange and its application to micro motion robot被引量:4
2014年
This paper develops a fast filtering algorithm based on vibration systems theory and neural information exchange approach. The characters, including the derivation process and parameter analysis, are discussed and the feasibility and the effectiveness are testified by the filtering performance compared with various filtering methods, such as the fast wavelet transform algorithm, the particle filtering method and our previously developed single degree of freedom vibration system filtering algorithm, according to simulation and practical approaches. Meanwhile, the comparisons indicate that a significant advantage of the proposed fast filtering algorithm is its extremely fast filtering speed with good filtering perfi^rmance. Further, the developed fast filtering algorithm is applied to the navigation and positioning system of the micro motion robot, which is a high real-time requirement for the signals preprocessing. Then, the preprocessing data is used to estimate the heading angle error and the attitude angle error of the micro motion robot. The estimation experiments illustrate the high practicality of the proposed fast filtering algorithm.
高娃查富生宋宝玉李满天
一种基于RBM的深层神经网络音素识别方法被引量:3
2013年
为提高连续语音识别中的音素识别准确率,采用深可信网络提取语音音素后验概率进行音素识别。首先利用受限玻尔兹曼机的学习原理,对深可信网络进行逐层的预训练;然后通过增加一个"软最大化(softmax)"输出层,得到用于音素状态后验概率检测的深层神经网络,并采用后向传播算法进行网络权值的精细调整;最后以后验概率为HMM发射概率,使用Viterbi解码器进行音素识别。针对TIMIT语料库的实验结果表明,该系统的音素识别率优于GMM/HMM,MLP/HMM和TANDEM系统性能。
陈琦张文林牛铜李弼程
关键词:神经网络音素识别
双足机器人足底压力测量传感系统的研究被引量:2
2015年
研制了一款用于测量双足机器人足底压力中心位置和足底力有无的足底压力测量传感系统,该系统通过测力台验证了其检测结果的有效性,并利用传感系统,通过实验进行了身体速度计算和足着地检测的实验。
查富生刘国才王俊王鹏飞段飞
关键词:传感系统双足机器人
共1页<1>
聚类工具0