Abstract:

To address the complex layouts and dense inspection points of oilfield metering and water⁃injection facilities, where the conventional A* algorithm exhibits low search efficiency, this study proposes a path⁃planning method for oilfield inspection robots based on an improved weighted A* algorithm. First, metering rooms, water⁃injection rooms, stairways, doors, and various outdoor obstacles were modeled using the actual layout of the Shenyang Oil Production Plant of Liaohe Oilfield Company, and a regular 60×60 grid map was constructed. Multiple inspection targets were then defined according to the actual locations of on⁃site valves. A goal⁃distance⁃dependent dynamic weight function was introduced into the weighted A* framework to strengthen directional guidance during long⁃range planning while yielding smoother and more stable local paths near the target. An adaptive node projection mechanism and eight⁃neighborhood constraints were also incorporated to improve path feasibility and robustness in complex environments. In addition, a lightweight traveling salesman problem (TSP) heuristic based on the nearest⁃neighbor strategy was used to optimize the inspection sequence for indoor valves. Turning⁃point extraction was subsequently applied to simplify the planned paths and eliminate redundant nodes. The proposed method was validated in a three⁃dimensional simulation environment built using ROS2 and RViz. The results show that the improved weighted A* algorithm outperforms the conventional A* algorithm significantly in terms of path length, number of turning points, and trajectory smoothness, thereby enhancing the path⁃planning performance of oilfield inspection robots.

Key words: Oilfield inspection robot, Path planning, Weighted A* algorithm, Dynamic weight, Grid map

摘要：

为解决油田计量间和注水间等站库区域结构复杂、巡检点分布密集以及传统A*算法在此类环境中搜索效率偏低等问题，提出了一种基于改进加权A*算法的油田巡检机器人路径规划方法。首先，依据辽河油田公司沈阳采油厂的真实站区布局，对计量间、注水间、楼梯、房门及多类室外障碍物进行结构化建模，并构建了尺寸为 60×60的规则栅格地图，同时按照现场阀门的实际布置确定了多个巡检目标点；在加权A*算法框架中引入与目标距离相关的动态权重函数，使算法在远距离规划时具备更强的方向指向性，在靠近目标区域时能够获得更平滑且更稳定的局部路径；同时，结合节点自适应投影机制与八邻域约束，提高规划过程在复杂环境中的可行性与鲁棒性；此外，采用基于最近邻策略的轻量级TSP方法优化室内阀门的巡检顺序，并通过拐点提取简化生成路径，以减少冗余节点；最终在基于ROS2与RViz的三维仿真环境中完成验证。结果表明，在路径长度、拐点数量及轨迹平滑性等方面，基于改进加权A*算法较传统A*算法具有显著优势，可有效提升油田巡检机器人的路径规划性能。

关键词: 油田巡检机器人, 路径规划, 加权A* 算法, 动态权重, 栅格地图