基于Kinect和ODE的人体运动建模与仿真

Modeling and Simulation of Human Motion Based on Kinect and ODE

运动数据捕获与物理仿真再现相结合,为人体运动特性的研究及仿人机器人的研制提供了一个重要技术途径。论文基于Kinect体感设备及ODE物理引擎,设计并实现了人体运动数据捕获、数据转化、动作建模及仿人机器人动作再现的系列方法。首先,建立转化模型,完成从Kinect关节点位置数据向肢体姿态数据的转化,并存储于BVH文件中,为数据分析和数据驱动提供支撑。其次,基于ODE建立一个全尺寸虚拟仿人机器人,为人体动作的仿真再现及控制算法提供验证平台。第三,完成关节位姿数据向驱动扭矩的实时计算及控制,采用PD控制算法控制各关节的扭矩输入。第四,贯穿完成Kinect数据采集、离线BVH转换、仿人机器人姿态计算、关节扭矩计算、仿真驱动等,实现虚拟仿人机器人对人体动作的精确再现。最后,将该方法应用于轻型仿人机器人手臂样机的研制过程。实践表明,该系列方法能够比较精确地实现仿人机器人对人体动作(挥手、行走、站立等)的学习和再现,可用于仿人机器人研制中的动作学习、规划、仿生控制等环节。

The combination of motion capture and physical simulation provides an important technical approach for the research of human motion characteristic and the development of humanoid robot.Based on Kinect and ODE,a series of methods of human motion data capture,modeling,transformation and action reproduction on humanoid robot is proposed in this paper.First,a model is established to complete the transformation from Kinect joint position to limb orientation,which is stored in BVH file for further data analysis and driver.Second,a full-scale virtual humanoid robot is built based on ODE,which provides a verification platform for the simulation.Third,the real-time calculation and control of joint pose data to drive torque is realized,and the joint torque is controlled by PD algorithm.Fourth,by going through Kinect data acquisition,off-line BVH conversion,position and pose calculation,joint torque calculation,simulation and drive,the virtual humanoid robot achieves an accurate reproduction of human body action.Finally,the system is applied to the development of a prototype of a lightweight humanoid robot arm.The practice shows that this series of methods can accurately realize the learning and reproduction of human body movements(wave,walk,stand,etc.)by the humanoid robot,and can be used in the process of learning,planning and bionic control in the development of humanoid robot.