基于区域空间知识模型的在线快速路径规划
Online fast path-planning based on regionalized spatial knowledge model

人类在其导航过程中运用了区域化的空间知识模型并采取了“由精到粗”的寻路策略. 受此启发本文首先 提出一种区域化的空间知识模型. 在该模型中, 多个小尺度的区域组合在一起形成上一层级的区域, 构成一种层次 化的空间表示结构. 在此基础上提出一种基于该空间知识模型的在线路径规划算法FTC–A*(fine-to-coarse A*). FTC–A*能够根据环境信息的远近采取不同的规划策略. 在机器人所在的区域中, 进行路径的精细规划, 而对远处 空间进行粗糙规划. 该策略利用环境描述的区域化特性, 降低了搜索空间的大小, 从而显著地降低了规划时间和内 存负载, 减少了机器人的运动响应延迟. 本算法能适应环境规模巨大以及目标点经常改变的应用场合. 通过 在MobileSim平台的仿真实验以及与A*和HA*算法的对比分析, 验证了该方法的可行性与有效性.
Human beings use the regionalized spatial knowledge and adopt the ”fine-to-coarse” way-finding strategy in the process of navigation. Inspired by this, we put forward a regionalized spatial knowledge model. In this model, small scale regions are grouped together to form the bigger regions at the next hierarchy level which leads to a hierarchical spatial representation structure. Based on the spatial knowledge model, we develop a kind of online route-planning algorithm FTC– A*(fine-to-coarse A*) which can take different planning strategies according to the distance of environmental information. In the area where the robot stays, a fine route-planning will be conducted while for the distant space a coarse planning will be done. Taking advantage of regionalization feature of environment description, this strategy can shrink the search space; thus, remarkably reducing the planning time and the memory loading as well as lowering the motion response lags of the robot. The algorithm FTC–A* can be applied to occasions with huge number of environments or target-points change frequently Through the simulation experiment on MobileSim platform and the contrastive analysis of algorithms A* and HA*, we find the proposed method is feasible and effective.