Visual odometry (VO) is one of essential techniques in mobile robots field, an accurate VO system is of great significance for mobile robot simultaneous localization and mapping. As for traditional monocular VO systems, they work by presuming the monocular scale is 1 (scale=1), or relying on ground truth (GT) to estimate scale. As a result, the traditional monocular VO systems estimate the pose state with big drift or cannot work on the image sequence without GT. Although some classical monocular VO systems have been proposed, however, they still have imperfect performance or even unable to work in some extreme scene conditions, such as scene is monotony without obvious texture information or camera large-scale displacement motion. As for learning-based VO system, it is realized by training deep neural networks in supervised or self-supervised manner to end-to-end estimate the pose state, however, the accuracy of pose estimation entirely depends on the ability of networks. Although the ability of networks can be improved by increasing the number of training datasets and optimizing the network structure, it is inevitable to encounter problems such as insufficient generalization ability and insufficient accuracy on rotational pose estimation. In this paper, a monocular VO system named DL_Hybrid is proposed, which takes full advantage of DL networks used in image processing and geometric localization theory based on hybrid pose estimation methods. The DL_Hybrid VO system can estimate a six-DoF pose one-frame-by-one-frame and recover camera trajectory, and it can extract accurate key points from per-frame even in extreme scene condition, and it has good performance even in the extreme moving condition, such as camera rotation-only action or static action, also it can work well in the condition of camera large-scale displacement motion. The real scale is also accurately estimated without depending on GT, and the pose estimation method is designed based on hybrid 2d-2d&3d-2d localization theory to make the DL_Hyrid VO system to estimate translational and rotational information with accuracy and robustness. Experiment results show that the proposed DL_Hybrid VO system has better performance than traditional and learning-based VO systems.

At present, the tracking accuracy of underwater passive target tracking is often limited due to models that are overly simple, with low complexity, poor universality, and an inability to learn. In this paper, a cubature Kalman filter (CKF) algorithm based on a gated recurrent unit (GRU) network is proposed. The filter innovation, prediction error, and filter gain obtained from the CKF are used as the input to the GRU network, and the filter error value is used as the output to train the network. End-to-end online learning is carried out using the designed fully connected network, and the current state of the target is predicted. In this paper, a deep neural network based on the GRU architecture is used to convert the tracking prediction problem into a time series prediction problem in the field of artificial intelligence, and its strong fitting ability is used to resolve the uncertainty of the target motion. Simulation results show that an unmanned underwater vehicle (UUV) state estimation method based on the GRU filter proposed in this paper offers better accuracy and stability than the traditional state estimation method.

In the context of global climate change, the implementation of building energy conservation and carbon reduction, as well as the realization of zero-energy buildings, is a key measure to cope with climate change and resource depletion. A substation is an indispensable building in the process of urbanization construction. However, in existing cold areas, the heating form of substations generally adopts electric heating, which consumes a large amount of energy. This paper optimizes the existing HVAC form of substations through the rational utilization of surrounding environmental resources and puts forward reasonable building energy-saving and carbon-reduction methods. It demonstrates the feasibility of combining solar photovoltaic power generation systems, air source heat pumps, and natural ventilation to optimize energy savings and carbon reduction in the main control building of a substation in a cold area. The computational fluid dynamics (CFD) method is used to demonstrate the feasibility of natural ventilation during the summer and transition seasons. The data indicate that the installation of a solar photovoltaic power generation system results in an average annual power generation of 18.75 MWh. Additionally, using an air source heat pump can save 44.5% of electricity compared to electric heating. When both a solar photovoltaic power generation system and an air source heat pump are used to provide a building with cold and heat sources, the annual emissions of CO₂ can be reduced by 4.90 tons compared to a traditional electric heating system.

Considering the complexity and uncertainty of decision-making in the operating environment of an unmanned underwater vehicle (UUV), this study proposes an autonomous decision-making method based on the dynamic influence diagram (DID) and expected utility theory. First, a threat assessment model is established for situation awareness of the UUV. Accordingly, a DID model is developed for autonomous decision-making of the UUV. Then, based on the threat assessment results for the UUV, the utility of each decision-making plan in the decision-making nodes is inferred and predicted. Subsequently, the principle of maximum expected utility is used to select an optimal autonomous decision-making plan. Finally, the effectiveness of the DID method is verified by simulation. Compared with the traditional expert systems, the DID system shows great adaptability and exhibits better solutions of dynamic decision problems under uncertainty.

The Gaussian mixture filter can solve the non-Gaussian problem of target tracking in complex environment by the multimode approximation method, but the weights of the Gaussian component of the conventional Gaussian mixture filter are only updated with the arrival of the measurement value in the measurement update stage. When the nonlinear degree of the system is high or the measurement value is missing, the weight of the Gauss component remains unchanged, and the probability density function of the system state cannot be accurately approximated. To solve this problem, this paper proposes an algorithm to update adaptive weights for the Gaussian components of a Gaussian mixture cubature Kalman filter (CKF) in the time update stage. The proposed method approximates the non-Gaussian noise by splitting the system state, process noise, and observation noise into several Gaussian components and updates the weight of the Gaussian components in the time update stage. The method contributes to obtaining a better approximation of the posterior probability density function, which is constrained by the substantial uncertainty associated with the measurements or ambiguity in the model. The estimation accuracy of the proposed algorithm was analyzed using a Taylor expansion. A series of extensive trials was performed to assess the estimation precision corresponding to various algorithms. The results based on the data pertaining to the lake trial of an unmanned underwater vehicle (UUV) demonstrated the superiority of the proposed algorithm in terms of its better accuracy and stability compared to those of conventional tracking algorithms, along with the associated reasonable computational time that could satisfy real-time tracking requirements.