基于规则库的巡线机器人自主越障动作规划  

Rule Base Based Motion Planning Method for Inspection Robot to Cross Obstacles Autonomously

作　　者：李恩[1] 梁自泽[1] 谭民[1] 

机构地区：[1]中国科学院自动化研究所复杂系统与智能科学实验室,北京100080

出　　处：《机器人》2005年第5期400-405,共6页Robot

基　　金：国家863计划资助项目(2002AA420110-4)

摘　　要：在电力线巡检机器人的控制系统中,采用分层规划的方式,利用产生式推理从行为规划的层次上进行在线规划,生成行为序列,然后将生成的行为序列与离线规划出的知识库相结合,生成自主越障的动作序列,实现机器人越障的自动控制.本文探讨了整个越障规划的控制过程和规划方法,并通过实验验证了动作规划的可行性.Hierarchical planning structure is adopted in the control system of inspection robot for power transmission lines. A production reasoning system is used on the behavior hierarchy for on-line planning to produce the behavior sequence. Combined with the interpretation knowledge base which is produced with off-line planning method, the behavior sequence is interpreted to engender motion sequence which is used to execute the automatic control for the robot to cross obstacles. Control flow sheet of the planning process and the planning method is discussed in tiffs paper, and the feasibility of the motion planning method is validated by the experimental results.

关 键 词：巡线机器人 产生式推理 智能控制 

分 类 号：TP24[自动化与计算机技术—检测技术与自动化装置]