摘要
提出了一种新颖、有效地基于立体视觉的移动机器人动态避障方法。首先提取出可疑障碍物区域,然后引入最大包围盒得到障碍物投影到水平路面的二维尺寸,接着利用几何知识获取障碍物相对机器人的运动速度和可能发生碰撞的方位。最后使用基于速度改变最小原则和速度改变最佳原则来完成机器人的动态避障。仿真结果表明该方法能够使移动机器人在具有静态和动态障碍物的复杂环境中安全避障。
A novel and effective obstacle avoidance method for a vision-based mobile robot is developed. First, doubtful obstacle regions are identified, and then a maximal encasing box is introduced to obtain the planar shape of the obstacle. After that, geometrical knowledge is used to analyze the orientation of collision and relative velocity between obstacles and the robot. Finally, the least velocity change principle and its optimal principle are used to realize the robot＇s obstacle avoidance. Simulation results show that the method can help the robot reach its target safely in complex environments where stationary and movement obstacles exist.
出处
《机械科学与技术》
CSCD
北大核心
2006年第6期631-634,共4页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(50275078)资助
