With the development of intelligent concepts in various fields, research on driverless and intelligent industrial robots has increased. Vision-based simultaneous localization and mapping (SLAM) is a widely used technique. Most conventional visual SLAM algorithms are assumed to work in ideal static environments; however, such environments rarely exist in real life. Thus, it is important to develop visual SLAM algorithms that can determine their own positions and perceive the environment in real dynamic environments. This paper proposes a lightweight robust dynamic SLAM system based on a novel semantic segmentation network (LRD-SLAM). In the proposed system, a fast deep convolutional neural network (FNet) is implemented into ORB-SLAM2 as a semantic segmentation thread. In addition, a multiview geometry method is introduced, in which the accuracy of detecting dynamic points is further improved through the difference in parallax angle and depth, and the information of the keyframes is used to repair the static background information absent from the removal of dynamic objects, to facilitate the subsequent reconstruction of the point cloud map. Experimental results obtained using the TUM RGB-D dataset demonstrate that the proposed system improves the positioning accuracy and robustness of visual SLAM in indoor pedestrian dynamic environments.

Path planning for underwater vehicles in complex underwater environments has become one of the key research areas. However, there are many drawbacks, such as slow convergence rates, poor real-time performance, and local optima, which lead to not being able to find the optimal path. Based on the particle swarm optimization (PSO) algorithm, a new adaptive PSO algorithm with interaction evidence (IEAPSO) is proposed. Firstly, we design the control strategy with a dynamic inertia weight and adaptive learning factor to update the velocity and position of particles. Secondly, considering the influence of neighboring particles on their own velocity and position during the spatial search process, we put forward an improved strategy with interaction evidence between particles to adjust their own velocity and position. Finally, the IEAPSO algorithm is applied to path planning for underwater vehicles and corresponding simulation experiments are accomplished. Simulation results show that the IEAPSO algorithm on three-dimensional trajectories in complex environments has better performances than other algorithms.