LiDAR-Based Safe and Realistic Path Planning in Partially Observable Environments
Shunta Ishizuya, Takuto Sakuma, Shōhei Kato · 2022 IEEE 11th Global Conference on Consumer Electronics (GCCE) · 2022
The difficulty of the robot’s navigation task in a partially observable environment is to find the optimal collision-free path with limited information. However, the traditionally used path planning algorithm finds the optimal path, but cannot directly account for robot collisions. We propose a method that directly considers collisions and efficiently finds short realistic paths. The proposed method is confirmed to be effective for robots to find short realistic paths in partially observed environments.