Object detection is essential for an autonomous driving sensing system. Since the light condition is changed in unconstrained scenarios, the detection accuracy based on visible images can be greatly degraded. Although the detection accuracy can be improved by fusing visible and infrared images, existing multispectral object detection (MOD) algorithms suffer from inadequate inter-modal interaction and a lack of global dependence in the fusion approach. Thus, we propose a multispectral object detection framework called YOLO-MS by designing a Feature Interaction and Self-Attention Fusion Network (FISAFN) as the backbone network. Within the FISAFN, correlations between two modalities are extracted by the Feature Interaction Module (FIM) for reconstructing the information components of each modality and enhancing capability of information exchange. To filter redundant features and enhance complementary features, long-range information dependence between two modalities are established by using a Self-Attention Feature Fusion Module (SAFFM). Thus, a better information richness of the fused features can be achieved. Experimental results on the FLIR-aligned dataset and the MFD dataset demonstrate that the proposed YOLO-MS performs favorably against state-of-the-art approaches, including feature-level fusion and pixel-level fusion. And further, the proposed YOLO-MS possesses good detection performance under diverse scene conditions.

The application of Cyber-Physical System (CPS) and edge computing in smart logistics systems has greatly improved the work efficiency. This paper mainly focuses on the planning and scheduling problems in the Cyber-Physical System based multiple Automatic Guided Vehicles (multi-AGVs) logistics system. A virtual network map with uneven time constraints is firstly proposed, which realizes the control and interaction of actual work in the control layer. Then, an improved A* path planning algorithm based on the characteristics of the path network model is implemented. A novel traffic control method is added to the planning process to achieve time-sensitive and proactive scheduling and collision avoidance. Results of the numerical experiments reveal that the proposed Cyber-Physical System based heuristic method could be effectively applied to the multiple automatic guided vehicles logistics system to further improve system security as well as work efficiency.

This article develops a robust packetized predictive control framework to deal with the quantized-feedback control problem of networked systems subject to Markovian packet dropouts and input saturation. In the proposed framework, the Markov chain model of packet dropout is established from the link of the controller to the actuator. To deal with the quantized measurements, a robust packetized predictive control method is presented with a quantized-feedback law. The problem of unreliable transmission is addressed by proposing a packet dropout compensation strategy with a forgetting factor. An augmented Markovian jump system model is established to take the packet dropouts into account. The synthesis of packetized predictive control is then developed by minimizing a worst case cost function with respect to the model uncertainties. The recursive feasibility of the proposed controller design problem and the mean-square stability of the closed-loop systems are proved, respectively. The proposed packetized predictive control method is demonstrated by simulating a four-tank process system.

State-of-the-art face hallucination methods utilize convolutional neural networks to restore high-quality high-resolution (HR) face images from low-resolution (LR) face images by employing appearance knowledge. However, most of these solutions only deploy the appearance knowledge (such as face attributes) to modulate the first layer of convolution feature with channel-wise shifting and ignore the face-identity information while emphasizing the vision quality of the generated result. To address the above issues, we propose a semantic-driven residual network based on a generative adversarial network to restore the HR face image with proper identity from the LR face image. Firstly, precise semantic information is explored based on improved U-net. Secondly, the semantic information is concatenated into the residual blocks of the reconstruction module, which is exceptionally efficient in modulating the extracted feature and guiding the generation of HR face images. Finally, the proposed methods can obtain the pleasuring SR face image with a similar identity of LR face image, after adversarially optimizing the designed loss functions. Extensive experiments demonstrate that the proposed semantic-driven residual network performs against the state-of-the-arts both quantitatively and qualitatively.

In this paper, we investigate the robust control of multi-motor driving cutterhead system for tunnel boring machines (TBMs) with distributed model predictive control (MPC). By analyzing the working procedures of induction motor, coupling, reduction gear box and spur gear, a dynamical model of cutterhead system is established. The model is then represented into state-space model with additional loads. A sequential and iterative distributed MPC algorithm is established for optimizing the input torques for the driving motors. To design the distributed MPC, the whole system is decomposed into several subsystems according to the distribution of input torques. The future system outputs are predicted by using the nominal system model and the distributed MPC optimizes the input sequence at each time instant in a recursive fashion. The model errors are corrected by comparing the actual outputs and predicted outputs. A sequential and iterative algorithm is proposed to coordinate the distributed MPC controllers. Finally, simulations are carried out to validate the distributed MPC algorithm on torque optimization of cutterhead system in TBMs.