Cell A* for Navigation of Unmanned Aerial Vehicles in Partially-known Environments
This work addresses path planning for mobile robots like UAVs in complex, partially-known settings, representing an incremental improvement over existing A* variants.
The paper tackles the challenge of autonomous navigation in partially-known environments by extending the A* algorithm to achieve stable path planning with reduced computational burden for long-distance tasks, resulting in a method capable of online collision-free and smooth path generation, as validated on drone and car platforms.
Proper path planning is the first step of robust and efficient autonomous navigation for mobile robots. Meanwhile, it is still challenging for robots to work in a complex environment without complete prior information. This paper presents an extension to the A* search algorithm and its variants to make the path planning stable with less computational burden while handling long-distance tasks. The implemented algorithm is capable of online searching for a collision-free and smooth path when heading to the defined goal position. This paper deploys the algorithm on the autonomous drone platform and implements it on a remote control car for algorithm efficiency validation.