To overcome the limitations of current visual and laser SLAM methods in narrow, feature-repetitive, and lighting-variable degraded scenarios, we propose a robust real-time mapping and localization system utilizing semantic dimensional chains (SDCs). SDC is a novel ordered semantic instance map representation. During the mapping phase, our system efficiently integrates diverse object detection and 2D-SLAM algorithms, constructing a prior semantic map through Bayesian filtering. In the preprocessing phase, a semantic map optimization algorithm based on neighborhood homogeneity is applied to effectively eliminate semantic noise. For localization, SDCs combined with precise localization algorithms enable rapid global localization. The system also features a kidnapping detection mechanism for swift pose recovery. We rigorously evaluated the system's performance in terms of robustness to lighting interference, global localization, and pose recovery in real-world degraded environments. Experimental results indicate that our localization system outperforms existing methods. Compared to a state-of-the-art vision-based localization algorithm, our semantic matching (SM) module exhibits superior resistance to lighting interference, resulting in a 15.38% increase in localization success rate (SR) and a 27.71% reduction in average localization time.

The path complexity generated by the Voronoi diagram in the existing algorithms is usually high, which leads to low efficiency in mobile robot navigation. This work proposes a Voronoi diagram optimization method based on the ray model. By re-connecting the key nodes in the map skeleton using the ray model principle, a more complete and concise Voronoi diagram is generated, and navigation paths that better conform to the principle of mobile robot motion are found. The path optimization effect of the algorithm is verified by simulation and real experiments, reducing the speed loss of the robot motion and improving navigation efficiency. This optimization method helps to reduce time cost and energy consumption, enabling mobile robots to integrate more efficiently and economically into people’s daily life.

This work proposes a lightweight object detection network model ShuffleNet-SSD (S-SSD) to solve the problem of single shot multibox detector (SSD) network model where it cannot meet the real-time performance requirement in the task of object detection and recognition of indoor mobile robot. This model is suitable for indoor mobile robot by improving the SSD network model based on ShuffleNet network. The main idea of the improvement is that S-SSD replaces VGG-16 network as the basic feature extraction network of SSD network model with ShuffleNet network. The proposed model is based on the design of deep separable convolution, point-by-point grouping convolution, and channel rearrangement. It retains the design idea of multiscale feature graph detection of SSD network model. This model ensures a slight decline in detection accuracy while greatly reduces the amount of computation generated by the network operation, thereby greatly improving the detection rate. A data set for the task of object detection and recognition of indoor mobile robot is made. The S-SSD lightweight network model is superior to the original SSD network model and tiny-YOLO lightweight network model in terms of detection accuracy and detection rate, and can simultaneously meet the requirement of detection accuracy and real-time performance in the task of indoor object detection and recognition of mobile robot. These findings are verified through the comparative experiments of object detection accuracy and detection rate and real-time object detection and recognition of mobile robot under the actual indoor scene.

The internal flow field model of valve spool and valve sleeve annular gap was established. The model was called oil film. The fluid motion state space was laminar flow by calculating of Reynolds number. The formulas about resistance torque and leakage of the valve spool and the valve sleeve annular gap were obtained by calculating. The formula of the energy loss was also obtained by calculating. The optimum annular gap which could make the energy loss to be minimum was obtained from the energy loss formula. In the conditions that valve spool and valve sleeve annular gap had different value, some fluid simulations were done by using FLUENT software. The simulation results showed that the two optimum annular gaps making the energy loss to be minimum was consistent with each other. The one optimum annular gap was obtained by calculating, the other optimum annular gap was obtained by fluid simulation. This provided a basis for optimization of the valve spool and valve sleeve gap value.

The obstacle avoidance fuzzy navigation strategy based on ultrasonic absolute position was proposed to improve the navigation efficiency and precision of the omni-directional mobile manipulator (ODMM). Comparing with the conventional navigation strategies, the superiority of this strategy is that it can momently get the accuracy positioning of robot and it can adjust posture and speed. The method of fusion redundancy ultrasonic information (FRUI) can improve the absolute positioning accuracy of ODMM. Absolute position based on fusion redundancy ultrasonic information(FRUI) and fuzzy navigation based on driving experience were all applied to the ODMM navigation. This strategies include the move-to-goal behavior based on absolute position and obstacle avoidance fuzzy navigation based on absolute positioning. Finally the experiment had been performed, the experimental result proved that the obstacle avoidance fuzzy navigation algorithm based on ultrasonic absolute positioning was effective and the navigation efficiency and precision of ODMM were greatly improved.