A learning-guided optimization approach, i.e., a $Q$-Learning-guided Memetic Algorithm (QLMA), is proposed to solve path planning problems in unknown environments. Traditional path planning algorithms in unknown environments have the disadvantages of low efficiency and stability problems. Integrating learning strategies into a memetic algorithm is a natural way to enhance search performance. The proposed algorithm can be divided into two stages: learning and optimization. A $Q$-learning algorithm implements the learning stage, while the optimization stage is implemented by hybridization of a Genetic Algorithm (GA) and Simulated Annealing (SA) algorithm, i.e., a memetic algorithm. The learning stage aims to acquire information from current search states. The $Q$-learning algorithm’s environmental learning capability is formed by rewards received from changes in distance to the target. Therefore, the path strategy could be adjusted continually, and effective paths could be identified. The optimization stage aims to utilize the obtained information and enhance the quality of known paths. A GA improves the global search ability, while an SA algorithm enhances the local search ability. The experimental study was conducted on 30 test scenarios with three types of index points. The proposed algorithm outperforms the other two algorithms significantly in the test scenarios.

The ability of an autonomous decision-making system to withstand disruptions is reflected in its performance boundary, which is a crucial indicator of its resilience. A performance boundary identification approach based on neighbor boundary degrees is proposed for autonomous decision-making systems, taking into account the features of multi-space distribution and incremental creation of performance boundary data. In order to solve the absolute scale measurement problem, we first design the neighbor boundary degree index. Then, we propose a performance boundary identification process based on neighbor boundary degree, which addresses the challenges of a complex performance boundary search space and non-uniform scale throughout the space. Secondly, the incremental performance boundary Identification method based on neighbor boundary degree is proposed by combining incremental data with the original identification results in order to accurately describe the performance boundary and to achieve efficient incremental data processing. An approximate nearest neighbor search optimization technique that enhances local sensitive hashing is then suggested in order to address the efficiency issue of nearest neighbor search and reverse nearest neighbor search that arose in the incremental phase. Finally, benchmark systems and path planning systems are used as autonomous decision-making systems to carry out verification and analysis of theoretical research work. Experimental results show that the performance boundary identification method based on neighbor boundary degree has good generalization ability of algorithm parameters. In the experiment on the path planning system, this method has a 13.68% higher boundary recognition accuracy and a 91.57% shorter running time compared to the comparison method.

To improve the accuracy of typhoon prediction, it is necessary to detect the internal structure of a typhoon. The motion model of a floating weather sensing node becomes the key to affect the channel frequency expansion performance and communication quality. This study proposes a floating weather sensing node motion modeling method based on the chaotic mapping. After the chaotic attractor is obtained by simulation, the position trajectory of the floating weather sensing node is obtained by space and coordinate conversion, and the three-dimensional velocity of each point on the position trajectory is obtained by multidimensional linear interpolation. On this basis, the established motion model is used to study the Doppler frequency shift, which is based on the software and physical platform. The software simulates the relative motion of the transceiver and calculates the Doppler frequency shift. The physical platform can add the Doppler frequency shift to the actual transmitted signal. The results show that this method can effectively reflect the influence of the floating weather sensing node motion on signal transmission. It is helpful to research the characteristics of the communication link and the design of a signal transceiver for typhoon detection to further improve the communication quality and to obtain more accurate interior structure characteristic data of a typhoon.

For a multi-robot system, the accurate global map building based on a local map obtained by a single robot is an essential issue. The map building process is always divided into three stages: single-robot map acquisition, multi-robot map transmission, and multi-robot map merging. Based on the different stages of map building, this paper proposes a multi-stage optimization (MSO) method to improve the accuracy of the global map. In the map acquisition stage, we windowed the map based on the position of the robot to obtain the local map. Furthermore, we adopted the extended Kalman filter (EKF) to improve the positioning accuracy, thereby enhancing the accuracy of the map acquisition by the single robot. In the map transmission stage, considering the robustness of the multi-robot system in the real environment, we designed a dynamic self-organized communication topology (DSCT) based on the master and slave sketch to ensure the efficiency and accuracy of map transferring. In the map merging stage, multi-layer information filtering (MLIF) was investigated to increase the accuracy of the global map. We performed simulation experiments on the Gazebo platform and compared the result of the proposed method with that of classic map building methods. In addition, the practicability of this method has been verified on the Turtlebot3 burger robot. Experimental results proved that the MSO method improves the accuracy of the global map built by the multi-robot system.