Semantic navigation for automated robotic inspection and indoor environment quality monitoring

Maintaining a comfortable indoor environment is essential for enhancing occupant well-being. However, traditional inspection methods rely on manual input of precise coordinates for target objects, limiting efficiency. This paper proposes a semantic navigation approach to improve robotic inspection intelligence and efficiency. A revised RandLA-Net and KNN algorithm construct a semantic map rich in detailed object information, supporting semantic navigation. Subsequently, an object instance reasoning algorithm automatically identifies and extracts target object coordinates from the semantic map using human-like language commands. Given the position information, a semantics-aware A* algorithm calculates safer, more efficient navigation paths through enhanced robot-environment interaction. Experiments demonstrate a position accuracy of ∼0.08 m for objects in the semantic map and effective coordinate extraction by the reasoning algorithm. The semantics-aware A* algorithm generates paths farther from obstacles and cluttered areas with less computational time, indicating its superior performance in terms of the robot's safety and inspection efficiency.