In the field of autonomous driving, relying solely on environmental information captured by single vehicle's LiDAR often falls short of perception requirements in complex scenarios. Adopting a vehicle-infrastructu...
详细信息
Temporal information plays a pivotal role in Bird’s-Eye-View (BEV) driving scene understanding, which can alleviate the visual information sparsity. However, the indiscriminate temporal fusion method will cause the b...
详细信息
In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To ...
详细信息
In public roads, autonomous vehicles (AVs) face the challenge of frequent interactions with human-driven vehicles (HDVs), which render uncertain driving behavior due to varying social characteristics among humans. To effectively assess the risks prevailing in the vicinity of AVs in social interactive traffic scenarios and achieve safe autonomous driving, this article proposes a social-suitable and safety-sensitive trajectory planning (S $^{\text{4}}$ TP) framework. Specifically, S $^{\text{4}}$ TP integrates the Social-Aware Trajectory Prediction (SATP) and Social-Aware Driving Risk Field (SADRF) modules. SATP utilizes Transformers to effectively encode the driving scene and incorporates an AV's planned trajectory during the prediction decoding process. SADRF assesses the expected surrounding risk degrees during AVs-HDVs interactions, each with different social characteristics, visualized as two-dimensional heat maps centered on the AV. SADRF models the driving intentions of the surrounding HDVs and predicts trajectories based on the representation of vehicular interactions. S $^{\text{4}}$ TP employs an optimization-based approach for motion planning, utilizing the predicted HDVs' trajectories as input. With the integration of SADRF, S $^{\text{4}}$ TP executes real-time online optimization of the planned trajectory of AV within low-risk regions, thus improving the safety and the interpretability of the planned trajectory. We have conducted comprehensive tests of the proposed method using the SMARTS simulator. Experimental results in complex social scenarios, such as unprotected left-turn intersections, merging, cruising, and overtaking, validate the superiority of our proposed S $^{\text{4}}$ TP in terms of safety and rationality. S $^{\text{4}}$ TP achieves a pass rate of 100% across all scenarios, surpassing the current state-of-the-art methods Fanta of 98.25% and Predictive-Decision of 94.75%.
The class quantum Merlin–Arthur(QMA),as the quantum analog of nondeterministic polynomial time,contains the decision problems whose YES instance can be verified efficiently with a quantum *** problem of deciding the ...
详细信息
The class quantum Merlin–Arthur(QMA),as the quantum analog of nondeterministic polynomial time,contains the decision problems whose YES instance can be verified efficiently with a quantum *** problem of deciding the group non-membership(GNM)of a group element is conjectured to be a member of *** works on the verification of GNM,which still lacks experimental demonstration,required a quantum circuit with O(n~5)group oracle ***,we provide an efficient way to verify GNM problems,in which each quantum circuit only contains O(1)group of oracle calls,and the number of qubits in each circuit is reduced by *** on this protocol,we then experimentally demonstrate the new verification process with a four-element group in an all-optical *** new protocol is validated experimentally by observing a significant completeness-soundness gap between the probabilities of accepting elements in and outside the *** work efficiently simplifies the verification of GNM and is helpful in constructing more quantum protocols based on the near-term quantum devices.
In this paper, a novel adaptive multi-scale time-frequency network (AMTFN) is proposed to provide high-resolution time-frequency representations for nonstationary signals. AMTFN is an end-to-end deep network, which fi...
详细信息
To reasonably improve the missing attribute data and effectively integrate sample data and uncertain expert knowledge, this paper proposes a new fault diagnosis method based on a belief rule base (BRB). In the case of...
To reasonably improve the missing attribute data and effectively integrate sample data and uncertain expert knowledge, this paper proposes a new fault diagnosis method based on a belief rule base (BRB). In the case of missing attribute data, the maximum likelihood estimation (MLE) method is used to complete the missing attribute data, and the fault diagnosis method of the multi-UAVs is constructed by using other complete attribute data as the input information of BRB. Finally, the effectiveness of the proposed method is verified by experimental simulation.
The nonlinear control system of ship is complex, which is a focus of research and key core of dynamic tracking. Because the input of the actual system is often restricted by the physical constraints of the actuator an...
详细信息
ISBN:
(纸本)9781665478977
The nonlinear control system of ship is complex, which is a focus of research and key core of dynamic tracking. Because the input of the actual system is often restricted by the physical constraints of the actuator and energy-saving control, the feasible region of the control input is often constrained by these factors. Therefore, by combining Zhang-gradient (ZG) dynamics with S-function, in this paper, a novel controller for the limited input system is designed. Considering the fact that dynamic systems are generally nonlinear in practical applications, the nonlinear system study has more practical significance. Therefore, this paper extends the ZG control method based on gradient dynamics and the bivariate S-function to the tracking control of nonlinear ship system, and designs a ship course tracking controller with a limited input, which can control the rudder angle within a certain feasible region while successfully tracking the ship course.
Tuberculosis(TB)is an infectious disease caused by Mycobacterium *** the diagnostic technology of pulmonary tuberculosis(PTB)has advanced,accurate and differential diagnoses of PTB are still *** recent years,the rapid...
详细信息
Tuberculosis(TB)is an infectious disease caused by Mycobacterium *** the diagnostic technology of pulmonary tuberculosis(PTB)has advanced,accurate and differential diagnoses of PTB are still *** recent years,the rapid development of artificial intelligence(AI)and its wide application in the medical field have provided new opportunities for diagnosing and treating TB and *** machine learning model of AI has not only helped physicians improve diagnostic accuracy,but also enabled them to make early preventive diagnoses for individuals at increased risk of ***,AI can guide physicians to formulate targeted treatment strategies for PTB patients with different conditions.
Waves seriously impact port construction, worldwide route planning, military activities, and wave power generation. To improve the accuracy of significant wave height prediction, we proposed a novel prediction method,...
Waves seriously impact port construction, worldwide route planning, military activities, and wave power generation. To improve the accuracy of significant wave height prediction, we proposed a novel prediction method, a multi-layer perceptron combined with a backpropagation adjustment (MLP-BP) prediction model that combines mutation mode decomposition (VMD) and a simulated annealing optimization algorithm (SA). Firstly, we use the variable modulus method to decompose the significant wave height sequence data and transform the wave height sequence into multiple different sub-modes (IMF) to reduce the complexity and non-stationarity of the data. Secondly, the simulated annealing algorithm (SA) is used to optimize the weight and bias of the MLP-BP neural network to find the optimal parameter configuration and improve the performance and generalization ability of the prediction model. Finally, the decomposed sub-modal components of each significant wave height sequence are inserted into the MLP-BP neural network and the predicted values of each element are summed to obtain the final significant wave height prediction. The prediction results of the SSA-MLP-BP, PSO-MLP-BP, SA-MLP-BP, and VMD-SA-MLP-BP were compared and demonstrated that the VMD-SA-MLP-BP model performed best. The MAE, MAPE, MSE, RMSE, and R2 of the prediction evaluation indexes were 0.036 m, 11.7%, 0.004 m 2 , 0.067 m, and 0.983, respectively, which performed well in predicting significant wave height.
In this paper, we present a new approach to estimate the pose of an object being manipulated by a multi-fingered robotic hand. The method utilizes advanced tactile sensors with high spatial resolution to optimize the ...
In this paper, we present a new approach to estimate the pose of an object being manipulated by a multi-fingered robotic hand. The method utilizes advanced tactile sensors with high spatial resolution to optimize the estimation of the object's pose using an Extended Kalman Filter (EKF) based approach. We defined and derived the state and measurement equations, as well as evaluated the estimation accuracy in grasping tasks. The approach is able to effectively account for the pose transition caused by tactile pushing, and the mapping from the object's pose to the contact position and normal direction as measured by the tactile sensor. The method was evaluated in multiple grasping experiments in simulation scenarios. Results show that the estimation can converge towards the ground truth in a relatively short period of time, with displacement and rotation errors remaining within acceptable levels. This new method has the potential to improve the accuracy and reliability of robotic grasping and manipulation tasks.
暂无评论