Ahluwalia et al. Res. Trends Int. J. Technol. Innov., July - September 2026, 1 (3) : 74-82
1Department of Mechanical Engineering, College of Engineering Pune, Pune, India; 2Department of Robotics and Automation, Amrita Vishwa Vidyapeetham, Coimbatore, India
Article History
Accepted : 08 Jul 2026
Published : 10 Jul 2026
Publication Issue
Volume 1, Issue 3
July - September 2026
Page Number74–82
Warehouse mobile robots must plan globally efficient routes while reacting to dynamic obstacles such as personnel and other robots without violating global path optimality by too wide a margin. This paper combines A* global planning on a static occupancy grid with a dynamic window approach (DWA) local planner for real-time obstacle avoidance, tested in a simulated 2,000 square metre warehouse with up to 15 dynamic obstacles. The hybrid planner achieved a 99.1 percent task completion rate with zero collisions across 500 trial runs, and average path length within 8 percent of the theoretical shortest path.
Keywords - path planning, mobile robotics, A* algorithm, dynamic window approach, warehouse automation
Purely global planners such as A* cannot react to obstacles unknown at planning time, while purely local reactive planners such as the dynamic window approach can become trapped in local minima in cluttered environments, motivating hybrid architectures that combine the strengths of both.
A hybrid planner was implemented in which A* computed an initial global path over a static occupancy grid representation of a 2,000 square metre simulated warehouse, with the dynamic window approach used to locally adjust velocity commands in real time to avoid up to 15 simultaneously moving dynamic obstacles representing personnel and other robots, re-planning the global path when local deviation exceeded a threshold.
Across 500 simulated trial runs with randomised obstacle trajectories, the hybrid planner achieved a 99.1 percent task completion rate with zero collisions, compared with 94.3 percent completion and a 2.4 percent collision rate for a DWA-only reactive baseline. Average realised path length was within 8 percent of the theoretical shortest path computed with perfect foreknowledge of obstacle trajectories.
Combining global A* planning with DWA-based local reactivity provides robust, near-collision-free navigation in dynamic warehouse settings without significant path-length penalty. Future work will evaluate the planner on physical robot hardware under real sensor noise conditions.
[1] Hart P. E. et al., A formal basis for the heuristic determination of minimum cost paths, IEEE Transactions on Systems Science and Cybernetics, 1968. [2] Fox D. et al., The dynamic window approach to collision avoidance, IEEE Robotics and Automation Magazine, 1997.
© 2026 The Author(s). Published by IJEIA Editorial Office. This is an open access article under the Creative Commons Attribution 4.0 International License (CC BY 4.0).
Karan Ahluwalia, Meghna Pillai (2026). Path Planning for Autonomous Mobile Robots in Dynamic Warehouse Environments Using Hybrid A*-DWA. IJEIA, 1(3), 74-82.