In dynamic environments, the traditional A* algorithm is apt to suffer from issues such as low search efficiency, unnecessary turning points, close proximity to obstacles, and no obstacle avoidance capability in global path planning. To address these issues, this paper presents a new path planning method that integrates an optimized A* algorithm and the Dynamic Window Approach (DWA) to enhance the mobile robot's navigation efficiency and obstacle avoidance ability in dynamic environments. During the global path planning process, multi-dimensional optimizations are incorporated into the A* algorithm. They include optimizing the cost function, taking multi-round polyline optimization approaches, and avoiding obstacle vertices, which successfully reduce unnecessary turning points in the path, reduce the frequency of turns, smooth the path curvature, and greatly enhance the search efficiency of the algorithm. In the local obstacle avoidance stage, the distance factor of dynamic obstacles is incorporated into the DWA evaluation function system to enhance the robot's ability to avoid dynamic obstacles. To verify the effectiveness of this method, a series of simulation experiments was conducted in a grid map environment built on the MATLAB platform. Comparative experiments of the classic A* algorithm, improved A* algorithm, and the proposed fusion algorithm were conducted under various dynamic obstacle collision threat scenarios. The experimental results show that this paper's fusion algorithm has higher path planning quality, obstacle avoidance success rate, and real-time performance than traditional algorithms, realizing stable and reliable navigation of paths.

Meng Qin, Qingyuan Xiao, Huiheng Suo, Guangjun Lai, Zuteng Chen, Jian Wu, Chenkai Zhang, Xie Ma, Yingping Bai, Weihong Zhong. Dynamic Obstacle Avoidance Path Planning Algorithm Based on the Fusion of Improved A* and DWA. International Journal of Big Data Intelligent Technology (2025), Vol. 6, Issue 2: 36-45. https://doi.org/10.38007/IJBDIT.2025.060204.

[1] Liu L, Wang X, Yang X, et al. Path planning techniques for mobile robots: Review and prospect[J]. Expert Systems with Applications, 2023, 227: 120254.

[2] Qin H, Shao S, Wang T, et al. Review of autonomous path planning algorithms for mobile robots[J]. Drones, 2023, 7(3): 211.

[3] Zhang D, Chen C, Zhang G. AGV path planning based on improved A-star algorithm[C]//2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE, 2024, 7: 1590-1595.

[4] Yan X, Ding R, Luo Q, et al. A dynamic path planning algorithm based on the improved DWA algorithm[C]//2022 Global Reliability and Prognostics and Health Management (PHM-Yantai). IEEE, 2022: 1-7. 

[5] Li X, Hu X, Wang Z, et al. Path planning based on combinaion of improved A-STAR algorithm and DWA algorithm[C]//2020 2nd International Conference on Artificial Intelligence and Advanced Manufacture (AIAM). IEEE, 2020: 99-103.

[6] Zhang D, Chen C, Zhang G. AGV path planning based on improved A-star algorithm[C]//2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC). IEEE, 2024, 7: 1590-1595.

[7] Sang W, Yue Y, Zhai K, et al. Research on AGV Path Planning Integrating an Improved A* Algorithm and DWA Algorithm[J]. Applied Sciences, 2024, 14(17): 7551.

[8] Zhang C, Yang X, Zhou R, et al. A path planning method based on improved A* and fuzzy control dwa of underground mine vehicles[J]. Applied Sciences, 2024, 14(7): 3103.

[9] Song B, Tang S, Li Y. A new path planning strategy integrating improved ACO and DWA algorithms for mobile robots in dynamic environments[J]. Mathematical Biosciences and Engineering, 2024, 21(2): 2189-2211.

[10] Hajizadeh R ,Nazari F .Manifold learning through locally linear reconstruction based on Euclidean distance[J].Multimedia Tools and Applications,2024,84(1):1-21.

[11] Hu Y, Long H, Chen M. The analysis of pedestrian flow in the smart city by improved DWA with robot assistance[J]. Scientific reports, 2024, 14(1): 11456.

[12] Yin X, Cai P, Zhao K, et al. Dynamic path planning of AGV based on kinematical constraint A* algorithm and following DWA fusion algorithms[J]. Sensors, 2023, 23(8): 4102.