Abstract: Emergency escape route planning in coal mines must adapt promptly to the changing underground environment. Traditional methods, relying on static networks with fixed weights, lack the flexibility needed for real-time adjustments in response to dynamic underground conditions. To address this limitation, a dynamic route planning approach for coal mine emergency escape was proposed using a Dijkstra-ACO (ant colony optimization) hybrid algorithm. By analyzing the impacts of tunnel slope and water level on escape routes, an optimal route dynamic planning model for emergency escape in coal mines was developed. This model allowed for real-time adjustment of escape routes based on environmental changes in tunnel slope and water level, thereby improving escape efficiency and safety. The Dijkstra-ACO hybrid algorithm was employed to obtain the optimal route model, where the Dijkstra algorithm was used for rapid identification of an initial route, while the ACO algorithm refined the result to find the shortest and safest escape route, ensuring adaptability to environmental changes. A simulated coal mine environment was constructed, modeling various tunnel types and parameters, including slope, water level, to test the dynamic route planning approach. Results showed that in three test areas of varying sizes, i.e., 50 m×100 m, 100 m×200 m, and 150 m×250 m, the routes generated by the Dijkstra-ACO hybrid algorithm were over 19% shorter compared to those from the A^* algorithm and modified ACO algorithm, with an obstacle avoidance improvement of over 5%.