摘要
为提高未知环境下移动机器人遍历路径规划的效率,提出了一种可动态调节启发式规则的滚动路径规划算法。该算法以生物激励神经网络为环境模型,通过在线识别环境信息特征,动态调用静态搜索算法和环绕障碍搜索算法,有效减少了路径的转弯次数。引入虚拟障碍和直接填充算法,解决了U型障碍区域的连续遍历问题。最后通过仿真实验表明了该方法在未知复杂环境下的有效性。
A new complete coverage path planning algorithm based on rolling path planning and dynamic heuristic searching is proposed to improve efficiency of path planning for mobile robot in unknown environments. The biological inspired neural network is used to model the environment of mobile robot. After the characteristic of local environment around the robot is identified on line, the dynamic heuristic planning method combing static searching and following the boundary of obstacle is applied and generated path is much shorter and less turning. Using virtual obstacle and directly filling algorithm, the continuously covered area in U shape obstacle is obtained in unknown environments. The effectiveness of the proposed algorithm is validated by simulation in unknown complicated environments.
出处
《计算机工程与设计》
CSCD
北大核心
2010年第1期172-174,202,共4页
Computer Engineering and Design
基金
广东省科技计划基金项目(2007B010200040)
广东省产学研合作基金项目(2007B090400056)
关键词
遍历路径规划
动态启发式规则
滚动窗口
直接填充
神经网络
complete coverage path planning
dynamic heuristic planning
rolling window
directly filling
neural network