Search

This article investigates the trajectory tracking control problem for wheeled mobile robot (WMR) subject to both velocity and torque constraints. Firstly, a more general model is established by considering the displacement between the centre of mass and the midpoint of the driving wheels of the WMR, based on which, a new bounded kinematic controller is proposed by combining the first-order filtering approach to keep the trajectory tracking error asymptotically stable. Then the dynamic controller is designed and the stability of the overall closed-loop system is proved by the Lyapunov stability theory and Barbalat's lemma. Some conditions are given to ensure that both the velocity constraints and torque constraints are satisfied. Finally, some numerical examples are given to show the effectiveness and advantages of the method proposed in this paper. [ABSTRACT FROM AUTHOR]

Indoor scenes are crucial components of urban spaces, with logos serving as vital information within these environments. The accurate perception of logos is essential for effectively operating mobile robots in indoor environments, which significantly contributes to many upper-level applications. With the rapid development of neural networks, numerous deep-learning-based object-detection methods have been applied to logo detection. However, most of these methods depend on large labeled datasets. Given the fast-changing nature of logos in indoor scenes, achieving reliable detection performance with either the existing large labeled datasets or a limited number of labeled logos remains challenging. In this article, we propose a method named MobileNetV2-YOLOv4-UP, which integrates unsupervised learning with few-shot learning for logo detection. We develop an autoencoder to obtain latent feature representations of logos by pre-training on a public unlabeled logo dataset. Subsequently, we construct a lightweight logo-detection network and embed the encoder weights as prior information. Training is performed on a small dataset of labeled indoor-scene logos to update the weights of the logo-detection network. Experimental results on the public logo625 dataset and our self-collected LOGO2000 dataset demonstrate that our method outperforms classic object-detection methods, achieving a mean average detection precision of 83.8%. Notably, our unsupervised pre-training strategy (UP) has proven effective, delivering a 15.4% improvement. [ABSTRACT FROM AUTHOR]

[Objectives] An energy management optimization strategy is proposed which considers the limitation of a ship's power system operation and greenhouse gas(GHG) emissions.[Methods] This strategy uses the differential evolution algorithm and real number code to optimize the dispatching speed of the ship,start and stop state of the generators and power distribution of the generator set with minimum consumption as the goal. These three plans can ensure compliance with environmental limits while reducing fuel consumption and ensuring efficiency.[Results] Taking the actual measured data of a cruise ferry as an example,the operating cost of the initial plan(plan 1)is 36 960.5 m.u while the operating costs of plan 2 and plan 3 are 36 938.1 m.u and 35 888.3 m.u respectively,showing a decrease of 0.06% and 2.90% when compared with the initial plan.[Conclusions] On the precondition that the optimal design method meets the limitations of the ship's generator,diesel engine operation,GHG limit and arrival distance,it can be seen that the ship's speed and propulsion curve become relatively stable,the figure tends to be trapezoidal and the efficiency of the ship's power system and fuel economy are significantly improved,while the amount of greenhouse gas emissions is simultaneously reduced.

Continuous implicit representations can flexibly describe complex 3D geometry and offer excellent potential for 3D point cloud analysis. However, it remains challenging for existing point-based deep learning architectures to leverage the implicit representations due to the discrepancy in data structures between implicit fields and point clouds. In this work, we propose a new point cloud representation by integrating the 3D Cartesian coordinates with the intrinsic geometric information encapsulated in its implicit field. Specifically, we parameterize the continuous unsigned distance field around each point into a low-dimensional feature vector that captures the local geometry. Then we concatenate the 3D Cartesian coordinates of each point with its encoded implicit feature vector as the network input. The proposed method can be plugged into an existing network architecture as a module without trainable weights. We also introduce a novel local canonicalization approach to ensure the transformation-invariance of encoded implicit features. With its local mechanism, our implicit feature encoding module can be applied to not only point clouds of single objects but also those of complex real-world scenes. We have validated the effectiveness of our approach using five well-known point-based deep networks (i.e., PointNet, SuperPoint Graph, RandLA-Net, CurveNet, and Point Structuring Net) on object-level classification and scene-level semantic segmentation tasks. Extensive experiments on both synthetic and real-world datasets have demonstrated the effectiveness of the proposed point representation. [ABSTRACT FROM AUTHOR]

The scattering properties of nonspherical particles can be approximately computed by equivalent spherical theory. The scattering properties of ice particles were approximately computed by Rayleigh approximation because the sizes of the ice particles are smaller than the wavelength of millimeter wave radar. Based on the above assumption, the echo fluctuation of moving particles was analyzed by computing the total backscattering field of a cirrus cloud using the classical vector potential technique. The simulation results showed that echo fluctuation influences the accuracy of retrieving the physical parameters of a cloud. To suppress the echo fluctuation of moving ice particles, a video integrator of a millimeter wave cloud radar would be used. However, video integrators lose the rapidly changing information of ice particles and reduce radar range resolution; thus, we propose the pace-diversity technique of MIMO radar to reduce the echo fluctuation, which could be validated by theoretical computation and experimental measurements. [ABSTRACT FROM AUTHOR]

• Feasibility proof of EVs participating in emergency power supply for important loads. • A novel pricing and scheduling strategy for EVs in emergency power supply. • An adaptive two-stage discharge pricing strategy between grid and EVs based on Q-learning. • Verifications on both effectiveness and economy of the strategy in different cases. In order to reduce the negative impact of blackout accidents caused by extreme disasters, and take the advantages of the distributed energy storage features of electric vehicles (EVs), a scheduling strategy for EVs to participate in emergency power supply for important loads is proposed. Firstly, the scheduling model of EVs participating in post-disaster emergency power supply for important loads is established considering blackout loss, EVs discharge compensation and duration of continuous power supply for important loads as the optimization objectives and the travel demand of EVs as the constraints. Secondly, based on the idea of cost pricing, the bidding ranges of both two participants as the grid and EVs are determined according to the calculation of their own scheduling cost and the estimation of the other's. Finally, the bidding function is established based on Q-learning, and the one-to-many two-stage discharge pricing strategy of the grid and EVs is proposed considering the transaction possibility and the learning relationship among participants. By case analysis of EVs participating in emergency power supply for important loads under different working conditions, it is proved that this strategy can reduce the peak-valley price difference, make the transaction price more reasonable, maximize the continuous power supply duration of important loads, and ensure the discharge income of EV users while reducing disaster loss. [ABSTRACT FROM AUTHOR]