In this paper, a degeneracy avoidance method for a point and line based visual SLAM algorithm is proposed. Visual SLAM predominantly uses point features. However, point features lack robustness in low texture and illuminance variant environments. Therefore, line features are used to compensate the weaknesses of point features. In addition, point features are poor in representing discernable features for the naked eye, meaning mapped point features cannot be recognized. To overcome the limitations above, line features were actively employed in previous studies. However, since degeneracy arises in the process of using line features, this paper attempts to solve this problem. First, a simple method to identify degenerate lines is presented. In addition, a novel structural constraint is proposed to avoid the degeneracy problem. At last, a point and line based monocular SLAM system using a robust optical-flow based lien tracking method is implemented. The results are verified using experiments with the EuRoC dataset and compared with other state-of-the-art algorithms. It is proven that our method yields more accurate localization as well as mapping results.

With the increase in developments in underwater infrastructure, the demand for development of autonomous vehicle navigation system in structured environment is also increased. However, the localization in a structured environment is a challenging problem due to signal uncertainties and distortions. In order to overcome these problems, we propose the camera and sonar aided integrated navigation system. In the proposed sensor-fusion-based localization scheme, the AUV estimates its own position continuously using artificial landmarks. The artificial landmarks for image sonar is deployed along the path to guide the AUV to the structure. The active vision markers are installed on the jacket structure, and they function as both landmarks and waypoints. This approach prevents the inherent drift of dead-reckoning velocities and collision with structures. The proposed approach was verified through a real sea experiment. The AUV conducted the full autonomous navigation from the dock to the jacket structure, and then returned to the dock without collision or significant localization error. These results show the feasibility of full autonomous navigation in a structured environment.