Enhanced Robot Motion Block of A-Star Algorithm for Robotic Path Planning

Area of Science:

• Robotics
• Artificial Intelligence
• Computer Science

Background:

• Robot path-planning is crucial for autonomous navigation.
• Conventional A-star (A*) algorithm has limitations in time, space, and search nodes.
• Robot motion block (RMB) optimization is key to improving path-planning efficiency.

Purpose of the Study:

• To propose an optimized robot motion block (RMB) with an adaptive cost function.
• To enhance the performance of the A-star (A*) algorithm for robot path-planning.
• To reduce the number of search nodes and time complexity in path-planning.

Main Methods:

• Developed an adaptive cost function that tracks the goal node and adjusts movement costs.
• Integrated the adaptive cost function with an optimal RMB.
• Conducted extensive experiments using an open-source dataset with varied grid maps and node sets.
• Performed a ROS experiment with a robot and lidar sensor data in a simulated environment.

Main Results:

• Achieved a 93.98% reduction in search nodes and a 98.94% improvement in time complexity compared to the conventional A* algorithm.
• Maintained comparable path costs against state-of-the-art algorithms.
• Demonstrated significant performance improvements in a simulated laboratory environment using ROS and lidar data.

Conclusions:

• The proposed adaptive cost function and optimal RMB significantly enhance A* algorithm performance for robot path-planning.
• The method offers a robust and efficient solution for complex navigation tasks.
• Validated effectiveness through extensive experiments and a real-world simulation.