为了保证机器人能够在人类的生活环境中安全地工作,应该选择最稳定的运动轨迹.提出了一种能够评价不同的运动步态之间稳定性好坏的稳定性评价准则.将零力矩点(ZMP,Zero Moment Point)与机器人支撑区域的形心之间的距离定义为不稳定度,...为了保证机器人能够在人类的生活环境中安全地工作,应该选择最稳定的运动轨迹.提出了一种能够评价不同的运动步态之间稳定性好坏的稳定性评价准则.将零力矩点(ZMP,Zero Moment Point)与机器人支撑区域的形心之间的距离定义为不稳定度,分析了仿人型机器人行走过程中几种典型步态的不稳定度,同时提出了基于不稳定度的仿人型机器人步态规划的方法.当采用多种运动步态都能完成同一种任务时,用所提出的不稳定度评价方法可以在不同步长的步态中选择出稳定性最好的运动步态来执行.仿真及实验结果验证了该方法的有效性.展开更多
随着机器人技术的发展,仿人机器人在多个领域展现出应用潜力和价值。针对仿人机器人,基于机器视觉进行自主抓取研究,旨在提高仿人机器人在自然环境中的抓取适应能力和动作仿人性。在机器视觉方面,硬件采用Realsense-D435深度摄像头,利用...随着机器人技术的发展,仿人机器人在多个领域展现出应用潜力和价值。针对仿人机器人,基于机器视觉进行自主抓取研究,旨在提高仿人机器人在自然环境中的抓取适应能力和动作仿人性。在机器视觉方面,硬件采用Realsense-D435深度摄像头,利用YOLO(You Only Look Once)物体检测模型实现目标物体的识别、空间定位、深度图裁切和目标点云生成,并根据目标点云与标准点云的配准算法(ICP)获取物体的姿态,通过D-H法对机器人头部进行建模,将物体的位置和姿态由相机坐标系转换为机器人坐标系。在运动规划上,参照人手臂的抓取规律,将抓取过程分为9个基础动作:初始位、移动至预抓取位、抓取物体、提起物体、搬运物体、移动至放置位、放置物体、退出位和回到初始位,针对不同物体确定对应抓取姿态,以提高抓取成功率,根据视觉获取的抓取点和放置点,自主计算余下的关键点,并以空间弧形作为抓取轨迹,通过Matlab仿真,验证抓取过程机械臂末端运动轨迹和关节轨迹的合理性。最后进行物体抓取实验,结果表明,仿人机器人在自然环境中能够快速准确地识别和定位不同物体,并能成功进行抓取和搬运,成功率均在80%以上,并且能够兼顾动作的仿人性,验证了所提出方案的有效性。本研究可促进仿人机器人在人类日常生活中的应用和普及。展开更多
The motion planning for obstacle negotiation by humanoid robot BHR-2 through stepping over or stepping on/off the wide and flat obstacle at known locations is presented. In the trajectory generation method, first the ...The motion planning for obstacle negotiation by humanoid robot BHR-2 through stepping over or stepping on/off the wide and flat obstacle at known locations is presented. In the trajectory generation method, first the constraints of the foot motion parameters which include obstacle dimensions and the distance of obstacle from the humanoid robot is formulated. By varying the values of the constraint parameters, different types of foot motion for different obstacles can be produced. In this method, first the foot trajectory is generated, and then the waist trajectory is computed by using cubic spline interpolation without first calculating the zero moment point （ZMP） trajectory . The dynamic stability during the execution of stepping over and stepping on/off trajectories are ensured by incorporating the ZMP criterion. The effectiveness of the proposed method is confirmed by simulations and experiments on humanoid robot BHR-2.展开更多
According to the features of movements of humanoid robot, a control system for humanoid robot walking on uneven terrain is present. Constraints of stepping over stairs are analyzed and the trajectories of feet are cal...According to the features of movements of humanoid robot, a control system for humanoid robot walking on uneven terrain is present. Constraints of stepping over stairs are analyzed and the trajectories of feet are calculated by intelligent computing methods. To overcome the shortcomings resulted from directly controlling the robot by neural network （NN） and fuzzy logic controller （FLC）, a revised particle swarm optimization （PSO） algorithm is proposed to train the weights of NN and rules of FLC. Simulations and experiments on different control methods are achieved for a detailed comparison. The results show that using the proposed methods can obtain better control effect.展开更多
文章主要阐述了基于人体运动相似性的仿人机器人动作规划系统的基本组成。首先,定义了异构形态下的相似性运动特点;其次,以卡耐基梅隆大学和哈尔滨工业大学的人体运动捕获系统为例,分析了人体运动捕获系统的特点;再次,分析了仿人机器人...文章主要阐述了基于人体运动相似性的仿人机器人动作规划系统的基本组成。首先,定义了异构形态下的相似性运动特点;其次,以卡耐基梅隆大学和哈尔滨工业大学的人体运动捕获系统为例,分析了人体运动捕获系统的特点;再次,分析了仿人机器人运动稳定性ZMP(Zero moment point)约束;最后阐述了仿人机器人实验平台。展开更多
文摘为了保证机器人能够在人类的生活环境中安全地工作,应该选择最稳定的运动轨迹.提出了一种能够评价不同的运动步态之间稳定性好坏的稳定性评价准则.将零力矩点(ZMP,Zero Moment Point)与机器人支撑区域的形心之间的距离定义为不稳定度,分析了仿人型机器人行走过程中几种典型步态的不稳定度,同时提出了基于不稳定度的仿人型机器人步态规划的方法.当采用多种运动步态都能完成同一种任务时,用所提出的不稳定度评价方法可以在不同步长的步态中选择出稳定性最好的运动步态来执行.仿真及实验结果验证了该方法的有效性.
文摘随着机器人技术的发展,仿人机器人在多个领域展现出应用潜力和价值。针对仿人机器人,基于机器视觉进行自主抓取研究,旨在提高仿人机器人在自然环境中的抓取适应能力和动作仿人性。在机器视觉方面,硬件采用Realsense-D435深度摄像头,利用YOLO(You Only Look Once)物体检测模型实现目标物体的识别、空间定位、深度图裁切和目标点云生成,并根据目标点云与标准点云的配准算法(ICP)获取物体的姿态,通过D-H法对机器人头部进行建模,将物体的位置和姿态由相机坐标系转换为机器人坐标系。在运动规划上,参照人手臂的抓取规律,将抓取过程分为9个基础动作:初始位、移动至预抓取位、抓取物体、提起物体、搬运物体、移动至放置位、放置物体、退出位和回到初始位,针对不同物体确定对应抓取姿态,以提高抓取成功率,根据视觉获取的抓取点和放置点,自主计算余下的关键点,并以空间弧形作为抓取轨迹,通过Matlab仿真,验证抓取过程机械臂末端运动轨迹和关节轨迹的合理性。最后进行物体抓取实验,结果表明,仿人机器人在自然环境中能够快速准确地识别和定位不同物体,并能成功进行抓取和搬运,成功率均在80%以上,并且能够兼顾动作的仿人性,验证了所提出方案的有效性。本研究可促进仿人机器人在人类日常生活中的应用和普及。
基金Sponsored by the National"863"Program Project (1020021300704)
文摘The motion planning for obstacle negotiation by humanoid robot BHR-2 through stepping over or stepping on/off the wide and flat obstacle at known locations is presented. In the trajectory generation method, first the constraints of the foot motion parameters which include obstacle dimensions and the distance of obstacle from the humanoid robot is formulated. By varying the values of the constraint parameters, different types of foot motion for different obstacles can be produced. In this method, first the foot trajectory is generated, and then the waist trajectory is computed by using cubic spline interpolation without first calculating the zero moment point （ZMP） trajectory . The dynamic stability during the execution of stepping over and stepping on/off trajectories are ensured by incorporating the ZMP criterion. The effectiveness of the proposed method is confirmed by simulations and experiments on humanoid robot BHR-2.
基金This material is based upon work funded by State Key Laboratory of Robotics and System （HIT） Foundation of China under Grant No. SKLRS-2012-MS-06, China Postdoctoral Science Foundation under Grant No. 2013M531022, Research project of laboratory work in universities of Zhejiang Province under Grant No. ZD201504, Educational technology research program of Zhejiang Province under Grant No. JA027.
文摘According to the features of movements of humanoid robot, a control system for humanoid robot walking on uneven terrain is present. Constraints of stepping over stairs are analyzed and the trajectories of feet are calculated by intelligent computing methods. To overcome the shortcomings resulted from directly controlling the robot by neural network （NN） and fuzzy logic controller （FLC）, a revised particle swarm optimization （PSO） algorithm is proposed to train the weights of NN and rules of FLC. Simulations and experiments on different control methods are achieved for a detailed comparison. The results show that using the proposed methods can obtain better control effect.
文摘文章主要阐述了基于人体运动相似性的仿人机器人动作规划系统的基本组成。首先,定义了异构形态下的相似性运动特点;其次,以卡耐基梅隆大学和哈尔滨工业大学的人体运动捕获系统为例,分析了人体运动捕获系统的特点;再次,分析了仿人机器人运动稳定性ZMP(Zero moment point)约束;最后阐述了仿人机器人实验平台。
