%0 Journal Article
%T 基于虚实交互的机器人运动场景构建方法的研究
Research on Construction Method of Robot Motion Scene Based on Virtual Reality Interaction
%A 刘雪梅
%A 周雨
%A 孟莨钦
%A 张朝兴
%A 刘忠跃
%J Artificial Intelligence and Robotics Research
%P 166-182
%@ 2326-3423
%D 2019
%I Hans Publishing
%R 10.12677/AIRR.2019.83019
%X
为应对复杂多变的环境,本文采用虚实交互技术与机器人控制技术相结合的方法,设计了一种与真实场景相匹配的机器人虚拟运动场景,实现在虚拟场景与现实场景中对机器人的运动控制,即虚实交互运动控制系统。通过Unity 3D软件搭建机器人虚拟运动场景,并在虚拟场景中设置各类障碍物,用Navgation导航网络模块计算出在避开障碍物的条件下,从起点到终点的最优路径,并利用NavMesh插件完成机器人的寻址避障运动控制。现实场景采用双足六自由度机器人,机器人将跟随虚拟场景中的机器人同步运动,并用OpenMV3摄像头识别现实场景中障碍物的图像信息,通过图像视觉处理后将障碍物的信息反馈于Socket服务器,虚拟场景从服务器中提取信息,并在虚拟场景中对应比例的重现,同时虚拟机器人进行躲避障碍物的运动控制,以此来达到虚实交互运动控制的目的。
In order to cope with the complex and ever-changing environment, this paper uses a combination of virtual and real interaction technology and robot control technology to design a virtual motion scene of the robot that matches the real scene, and realizes the motion control of the robot in the virtual scene and the real scene. That is, virtual and real interactive motion control system. The virtual motion scene of the robot is built by Unity 3D software, and various obstacles are set in the virtual scene. The Navgation navigation network module is used to calculate the optimal path from the starting point to the end point under the condition of avoiding obstacles, and the NavMesh plug-in is utilized to complete the robot’s addressing obstacle avoidance motion control. The real-istic scene adopts a two-legged six-degree-of-freedom robot. The robot will follow the robot synchronous motion in the virtual scene, and use the OpenMV3 camera to identify the image in-formation of the obstacle in the real scene. After the image visual processing, the obstacle infor-mation is fed back to the Socket server. The scene extracts information from the server and re-produces the corresponding proportion in the virtual scene. At the same time, the virtual robot performs motion control to avoid obstacles, thereby achieving the purpose of virtual and real in-teractive motion control.