Task-Oriented Navigation with Semantic Perception for Monocular Camera-Based Mobile Robots

Abstract

For mobile robots to execute commands given by humans in environments lacking localization infrastructure, they must be capable of making semantic inferences about the environment. To this end, we present a task-based navigation method for a mobile robot using single monocular camera. The robot’s perception mechanism consists of a SSD-InceptionV2 for target object detection and MiDaS-Small for depth map estimation. By exploiting the geometric advantage of the motion plane of ground robots, metric distances derived from relative depth outputs are used in the obstacle avoidance algorithm, and a Kalman filter is applied to ensure continuity in target object tracking. Tests conducted on a Jetson TX2 platform verified that the system exhibits stable performance at approximately 15 FPS and successfully completes its task. The results demonstrate that mobile robot navigation systems can be developed in infrastructure-free environments using solely camera-based perception.