查看更多>>摘要：Video portrait segmentation(VPS),aiming at segmenting prominent foreground portraits from video frames,has received much attention in recent years.However,the simplicity of existing VPS datasets leads to a limitation on extensive research of the task.In this work,we propose a new intricate large-scale multi-scene video portrait segmentation dataset MVPS consisting of 101 video clips in 7 scenario categories,in which 10843 sampled frames are finely annotated at the pixel level.The dataset has diverse scenes and complicated background environments,which is the most complex dataset in VPS to our best knowledge.Through the observation of a large number of videos with portraits during dataset construction,we find that due to the joint structure of the human body,the motion of portraits is part-associated,which leads to the different parts being relatively independent in motion.That is,the motion of different parts of the portraits is imbalanced.Towards this imbalance,an intuitive and reasonable idea is that different motion states in portraits can be better exploited by decoupling the portraits into parts.To achieve this,we propose a part-decoupling network(PDNet)for VPS.Specifically,an inter-frame part-discriminated attention(IPDA)module is proposed which unsupervisedly segments portrait into parts and utilizes different attentiveness on discriminative features specified to each different part.In this way,appropriate attention can be imposed on portrait parts with imbalanced motion to extract part-discriminated correlations,so that the portraits can be segmented more accurately.Experimental results demonstrate that our method achieves leading performance with the comparison to state-of-the-art methods.
查看更多>>摘要：This study addresses the stability and stabilization problems of discrete-time semi-Markov jump linear systems(S-MJLSs)with unavailable sojourn-time information.The sojourn-time probability mass functions(S-TPMFs)of discrete-time semi-Markov chains are no longer confined to the geometric distribu-tion,and it is difficult to obtain accurate and comprehensive information for S-TPMFs in practice.This is be-cause S-TPMFs are usually deduced from the statistical characteristics according to the sampled-data,while adequate samples are often costly and time consuming.In this study,when the S-TPMFs for semi-Markov chains are assumed to be unavailable,the σ-error mean square stability is investigated for discrete-time S-MJLSs with some widely used assumptions;for semi-Markov chains,only the transition probability matrix of the embedded chain is used.In addition,the existence conditions of the effective controller are provided for closed-loop systems without using the information of S-TPMFs.Numerical examples are presented to illustrate the validity of the obtained theoretical results.
查看更多>>摘要：In this study,an adaptive neural network(NN)control is proposed for nonlinear two-degree-of-freedom(2-DOF)helicopter systems considering the input constraints and global prescribed performance.First,radial basis function NN(RBFNN)is employed to estimate the unknown dynamics of the helicopter system.Second,a smooth nonaffine function is exploited to approximate and address nonlinear constraint functions.Subsequently,a new prescribed function is proposed,and an original constrained error is trans-formed into an equivalent unconstrained error using the error transformation and barrier function transfor-mation methods.The analysis of the established Lyapunov function proves that the controlled system is globally uniformly bounded.Finally,the simulation and experimental results on a constructed Quanser's test platform verify the rationality and feasibility of the proposed control.
查看更多>>摘要：In reinforcement learning(RL),training a policy from scratch with online experiences can be inefficient because of the difficulties in exploration.Recently,offline RL provides a promising solution by giving an initialized offline policy,which can be refined through online interactions.However,existing approaches primarily perform offline and online learning in the same task,without considering the task generalization problem in offline-to-online adaptation.In real-world applications,it is common that we only have an offline dataset from a specific task while aiming for fast online-adaptation for several tasks.To address this problem,our work builds upon the investigation of successor representations for task generalization in online RL and extends the framework to incorporate offline-to-online learning.We demonstrate that the conventional paradigm using successor features cannot effectively utilize offline data and improve the performance for the new task by online fine-tuning.To mitigate this,we introduce a novel methodology that leverages offline data to acquire an ensemble of successor representations and subsequently constructs ensemble Q functions.This approach enables robust representation learning from datasets with different coverage and facilitates fast adaption of Q functions towards new tasks during the online fine-tuning phase.Extensive empirical evaluations provide compelling evidence showcasing the superior performance of our method in generalizing to diverse or even unseen tasks.
查看更多>>摘要：In this paper,nonsingular prescribed-time control is studied based on periodic delayed sliding mode surfaces.Different from the existing sliding mode control,where either singularity problems may appear or the convergence time depends on the initial state,the proposed sliding mode control approaches can achieve prescribed-time convergence without singularity.The proposed nonsingular sliding mode control approaches can be applied to both second-order and high-order nonlinear systems with prescribed-time convergence.As applications of the proposed sliding mode control approaches,the control of hypersonic vehicle systems is revisited.Numerical simulations on the nonlinear model of the hypersonic vehicle system show the effectiveness of the proposed methods.
查看更多>>摘要：In this paper,we consider the distributed generalized Nash equilibrium(GNE)seeking problem in strongly monotone games.The transmission among players is implemented through a digital communication network with limited bandwidth.For improving communication efficiency or/and security,an event-triggered coding-decoding-based communication is first proposed,where the data(decision variable)are first mapped to a series of finite-level codewords and,only when an event condition is satisfied,then sent to the neighboring agents.Moreover,a distributed communication-efficient GNE seeking algorithm is constructed accordingly,and the overrelaxation scheme is further taken into consideration.Through primal-dual analysis,the proposed algorithm is proven to converge to a variational GNE with fixed step-sizes by recasting it as an inexact forward-backward iteration.Finally,numerical simulations illustrate the benefit of the proposed algorithms in terms of saving communication resources.
查看更多>>摘要：This paper investigates the minimum-time trajectory planning problem of an autonomous ve-hicle.To deal with unknown and uncertain dynamics of the vehicle,the trajectory planning problem is modeled as a Markov decision process with a continuous action space.To solve it,we propose a continuous advantage learning(CAL)algorithm based on the advantage-value equation,and adopt a stochastic policy in the form of multivariate Gaussian distribution to encourage exploration.A shared actor-critic architecture is designed to simultaneously approximate the stochastic policy and the value function,which greatly reduces the computation burden compared to general actor-critic methods.Moreover,the shared actor-critic is up-dated with a loss function built as mean square consistency error of the advantage-value equation,and the update step is performed several times at each time step to improve data efficiency.Simulations validate the effectiveness of the proposed CAL algorithm and its better performance than the soft actor-critic algorithm.
查看更多>>摘要：Research on flexible strain sensors has advanced rapidly in recent years,with particular attention being devoted to two-dimensional(2D)semiconductor materials owing to their exceptional mechanical and electrical properties that are conducive to sophisticated sensing performance.However,resistive strain sensors based on 2D semiconductor materials typically exhibit positive gauge factors(GF),while materials for strain sensors with a negative GF remain elusive.We have identified a trend of reduction in the band gap of the emerging 2D semiconductor material tellurium(Te)under strain in simulations reported in past research,and have observed a negative GF in the Te-based strain sensor.In this study,we combined Te with a flexible polyethylene terephthalate(PET)substrate to manufacture a flexible strain sensor with a significantly negative GF.The results of tests revealed that the Te-based strain sensor achieved an impressive maximum sensitivity of-139.7 within a small range of bending-induced strain(＜1％).Furthermore,it exhibited excellent linearity and good cyclic stability,and was successfully applied to monitor limb movements.The work here verifies the significant potential for the use of Te-based strain sensors in next-generation flexible electronics.
查看更多>>摘要：We consider Shor's quantum factoring algorithm in the setting of noisy quantum gates.Under a generic model of random noise for(controlled)rotation gates,we prove that the algorithm does not factor integers of the form pq when the noise exceeds a vanishingly small level in terms of n-the number of bits of the integer to be factored,where p and q are from a well-defined set of primes of positive density.We further prove that with probability 1-o(1)over random prime pairs(p,q),Shor's factoring algorithm does not factor numbers of the form pq,with the same level of random noise present.
NETL
NSTL
万方数据