Abstract: In the path planning process of the robot going to the fire, aiming at the problems of too many traversed nodes and too many turns in the traditional A* algorithm in the fire rescue process, an improved A* algorithm is proposed, which adds weighting to the heuristic function. In order to improve the operating efficiency of the algorithm, the Manhattan distance is introduced, and the penalty function and reward factor are introduced to reduce the number of turns of the robot in the process of rushing to the fire field. After arriving at the fire field, it is necessary to traverse the fire field area. In the research, based on the principle of heat radiation at the fire point, the inner spiral algorithm is used to approach the fire field in a gradient manner to reduce the impact of high temperature on the operation performance of the inspection robot. The simulation results show that, compared with the traditional A* algorithm, the improved A* algorithm can effectively reduce the number of traversed nodes and the number of turns in the process of going to the fire field, and improve the operation efficiency of the inspection robot. During the process, the inner spiral algorithm can traverse the fire area with a high coverage rate.

Key words: forest and grass fire rescue, fully automated intelligent inspection robot, A* algorithm, inner spiral algorithm, fire point heat radiation