RESUMEN
An autonomous place recognition system is essential for scenarios where GPS is useless, such as underground tunnels. However, it is difficult to use existing algorithms to fully utilize the small number of effective features in underground tunnel data, and recognition accuracy is difficult to guarantee. In order to solve this challenge, an efficient point cloud position recognition algorithm, named Dual-Attention Transformer Network (DAT-Net), is proposed in this paper. The algorithm firstly adopts the farthest point downsampling module to eliminate the invalid redundant points in the point cloud data and retain the basic shape of the point cloud, which reduces the size of the point cloud and, at the same time, reduces the influence of the invalid point cloud on the data analysis. After that, this paper proposes the dual-attention Transformer module to facilitate local information exchange by utilizing the multi-head self-attention mechanism. It extracts local descriptors and integrates highly discriminative global descriptors based on global context with the help of a feature fusion layer to obtain a more accurate and robust global feature representation. Experimental results show that the method proposed in this paper achieves an average F1 score of 0.841 on the SubT-Tunnel dataset and outperforms many existing state-of-the-art algorithms in recognition accuracy and robustness tests.
RESUMEN
Finding the optimal signal timing strategy is a difficult task for the problem of large-scale traffic signal control (TSC). Multiagent reinforcement learning (MARL) is a promising method to solve this problem. However, there is still room for improvement in extending to large-scale problems and modeling the behaviors of other agents for each individual agent. In this article, a new MARL, called cooperative double Q -learning (Co-DQL), is proposed, which has several prominent features. It uses a highly scalable independent double Q -learning method based on double estimators and the upper confidence bound (UCB) policy, which can eliminate the over-estimation problem existing in traditional independent Q -learning while ensuring exploration. It uses mean-field approximation to model the interaction among agents, thereby making agents learn a better cooperative strategy. In order to improve the stability and robustness of the learning process, we introduce a new reward allocation mechanism and a local state sharing method. In addition, we analyze the convergence properties of the proposed algorithm. Co-DQL is applied to TSC and tested on various traffic flow scenarios of TSC simulators. The results show that Co-DQL outperforms the state-of-the-art decentralized MARL algorithms in terms of multiple traffic metrics.
RESUMEN
An omnidirectional stereo vision sensor based on one single camera and catoptric system is proposed. As crucial components, one camera and two pyramid mirrors are used for imaging. The omnidirectional measurement towards different directions in the horizontal field can be performed by four pairs of virtual cameras, with a consummate synchronism and an improved compactness. Moreover, the perspective projection invariance is ensured in the imaging process, which avoids the imaging distortion reflected by the curved mirrors. In this paper, the structure model of the sensor was established and a sensor prototype was designed. The influences of the structural parameters on the field of view and the measurement accuracy were also discussed. In addition, real experiments and analyses were performed to evaluate the performance of the proposed sensor in the measurement application. The results proved the feasibility of the sensor, and exhibited a considerable accuracy in 3D coordinate reconstruction.
RESUMEN
This paper proposes a new method to detect and identify foreign matter mixed in a plastic bottle filled with transfusion solution. A spin-stop mechanism and mixed illumination style are applied to obtain high contrast images between moving foreign matter and a static transfusion background. The Gaussian mixture model is used to model the complex background of the transfusion image and to extract moving objects. A set of features of moving objects are extracted and selected by the ReliefF algorithm, and optimal feature vectors are fed into the back propagation (BP) neural network to distinguish between foreign matter and bubbles. The mind evolutionary algorithm (MEA) is applied to optimize the connection weights and thresholds of the BP neural network to obtain a higher classification accuracy and faster convergence rate. Experimental results show that the proposed method can effectively detect visible foreign matter in 250-mL transfusion bottles. The misdetection rate and false alarm rate are low, and the detection accuracy and detection speed are satisfactory.