Abstract: In response to the challenges of weak global search ability, slow convergence speed, and easy falling into local optima in existing ant colony algorithms for path planning of fire robots, an ant colony path planning algorithm based on rollback and forward and backward optimization strategies is proposed. It enhances global search capability and speed by improving global initialization information, adopting rollback strategies and ant colony forward and backward optimization methods. The simulation results based on MATLAB and ROS show that the improved ant colony algorithm proposed in this paper improves convergence, reduces iteration times, shortens patrol path length, and saves valuable time for firefighting robot fire rescue.

Key words: firefighting robot, path planning, ant colony algorithm, rollback strategy, forward and backward optimization