arXiv subjects

Fei Gao

Publications and source records attributed to Fei Gao.

At least 379 records · Page 21Linked to original sources

arXiv2022

Autonomous and Adaptive Navigation for Terrestrial-Aerial Bimodal Vehicles

Terrestrial-aerial bimodal vehicles bloom in both academia and industry because they incorporate both the high mobility of aerial vehicles and the long endurance of ground vehicles. In this work, we present an autonomous and adaptive navigation framework to bring complete autonomy to this class of vehicles. The framework mainly includes 1) a hierarchical motion planner that generates safe and low-power terrestrial-aerial trajectories in unknown environments and 2) a unified motion controller which dynamically adjusts energy consumption in terrestrial locomotion. Extensive real-world experiments and benchmark comparisons are conducted on a customized robot platform to validate the proposed framework's robustness and performance. During the tests, the robot safely traverses complex environments with terrestrial-aerial integrated mobility, and achieves $7\times$ energy savings in terrestrial locomotion. Finally, we will release our code and hardware configuration for the reference of the community.

cs.RO↗

arXiv2021

Size-adjustable Ring-shape Photoacoustic Tomography System

Photoacoustic tomography (PAT) combines the advantages of the spectroscopic optical absorption contrast and acoustic resolution with deep penetration, and becomes an important novel biomedical imaging technology for scientific research and clinical diagnosis. In this paper, an imaging size-adjustable PAT system is proposed for clinical applications, which can adapt for different size imaging targets. Comparing with the conventional PAT system setup which with a fixed radius ring shape ultrasound transducer (UT) array, the proposed system, which is based on sectorial ultrasound transducer array (SUTA), is more flexible for different size targets imaging. There are 32 elements for each SUTA, and four SUTAs form a 128-channel UT array for photoacoustic wave detection. The four SUTAs are controlled by four stepper motors, and change the SUTAs distribute positon that adapt for imaging applications. The radius of the proposed system imaging region of interest (ROI) can be adjusted from 50 mm to 90 mm, which is much more flexible than the conventional full ring UT array PAT system. The simulation results generated by the MATLAB k-wave toolbox very well demonstrate the feasibility of the proposed system. To further validate the proposed system for size-adjustable imaging, a vascular mimicking phantom and ex-vivo pork breast with indocyanine green (ICG) injected are imaged to prove its feasibility for clinical applications.

physics.ins-det↗

arXiv2021

Global boundedness and Allee effect for a nonlocal time fractional reaction-diffusion equation

The global boundedness and asymptotic behavior are investigated for the solutions of a nonlocal time fractional reaction-diffusion equation (NTFRDE) $$ \frac{\partial^{α}u}{\partial t^{α}}=Δu+μu^{2}(1-kJ*u)-γu, \qquad(x,t)\in\mathbb{R}^{N}\times(0,+\infty)$$ with $0<α<1,β, μ,k>0,N\leq 2$ and $u(x,0)=u_{0}(x)$. Under appropriate assumptions on $J$ and the property of time fractional derivative, it is proved that for any nonnegative and bounded initial conditions, the problem has a global bounded classical solution if $k^{*}=0$ for $N=1$ or $k^{*}=(μC^{2}_{GN}+1)η^{-1}$ for $N=2$, where $C_{GN}$ is the constant in Gagliardo-Nirenberg inequality. With further assumptions on the initial datum, for small $μ$ values, the solution is shown to converge to $0$ exponentially or locally uniformly as $t \rightarrow \infty$, which is referred as the Allee effect in sense of Caputo derivative. Moreover, under the condition of $J \equiv 1$, it is proved that the nonlinear NTFRDE has a global bounded solution in any dimensional space with the nonlinear diffusion terms $Δu^{m}\, (2-\frac{2}{N}< m\leq 3)$.

math.AP↗

arXiv2021

Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective

Network Embedding aims to learn a function mapping the nodes to Euclidean space contribute to multiple learning analysis tasks on networks. However, the noisy information behind the real-world networks and the overfitting problem both negatively impact the quality of embedding vectors. To tackle these problems, researchers utilize Adversarial Training for Network Embedding (AdvTNE) and achieve state-of-the-art performance. Unlike the mainstream methods introducing perturbations on the network structure or the data feature, AdvTNE directly perturbs the model parameters, which provides a new chance to understand the mechanism behind. In this paper, we explain AdvTNE theoretically from an optimization perspective. Considering the Power-law property of networks and the optimization objective, we analyze the reason for its excellent results. According to the above analysis, we propose a new activation to enhance the performance of AdvTNE. We conduct extensive experiments on four real networks to validate the effectiveness of our method in node classification and link prediction. The results demonstrate that our method is superior to the state-of-the-art baseline methods.

cs.LG↗

arXiv2021

Phase structure of 2+1-flavour QCD and the magnetic equation of state

We determine the chiral phase structure of $2+1$-flavour QCD in dependence of temperature and the light flavour quark mass with Dyson-Schwinger equations. Specifically, we compute the renormalised chiral condensate and its susceptibility. The latter is used to determine the (pseudo)critical temperature for general light current quark masses. In the chiral limit we obtain a critical temperature of about 141\,MeV. This result is in quantitative agreement with recent functional renormalisation group results in QCD, and is compatible with the respective lattice results. We also compute the order parameter potential of the light chiral condensate and map out the regime in the phase diagram which exhibits quasi-massless modes, and discuss the respective chiral dynamics.

hep-ph↗

arXiv2021

Resistance-Time Co-Modulated PointNet for Temporal Super-Resolution Simulation of Blood Vessel Flows

In this paper, a novel deep learning framework is proposed for temporal super-resolution simulation of blood vessel flows, in which a high-temporal-resolution time-varying blood vessel flow simulation is generated from a low-temporal-resolution flow simulation result. In our framework, point-cloud is used to represent the complex blood vessel model, resistance-time aided PointNet model is proposed for extracting the time-space features of the time-varying flow field, and finally we can reconstruct the high-accuracy and high-resolution flow field through the Decoder module. In particular, the amplitude loss and the orientation loss of the velocity are proposed from the vector characteristics of the velocity. And the combination of these two metrics constitutes the final loss function for network training. Several examples are given to illustrate the effective and efficiency of the proposed framework for temporal super-resolution simulation of blood vessel flows.

eess.IV↗

arXiv2021

Deep Learning Adapted Acceleration for Limited-view Photoacoustic Computed Tomography

Photoacoustic imaging (PAI) is a non-invasive imaging modality that detects the ultrasound signal generated from tissue with light excitation. Photoacoustic computed tomography (PACT) uses unfocused large-area light to illuminate the target with ultrasound transducer array for PA signal detection. Limited-view issue could cause a low-quality image in PACT due to the limitation of geometric condition. The model-based method is used to resolve this problem, which contains different regularization. To adapt fast and high-quality reconstruction of limited-view PA data, in this paper, a model-based method that combines the mathematical variational model with deep learning is proposed to speed up and regularize the unrolled procedure of reconstruction. A deep neural network is designed to adapt the step of the gradient updated term of data consistency in the gradient descent procedure, which can obtain a high-quality PA image only with a few iterations. Note that all parameters and priors are automatically learned during the offline training stage. In experiments, we show that this method outperforms the other methods with half-view (180 degrees) simulation and real data. The comparison of different model-based methods show that our proposed scheme has superior performances (over 0.05 for SSIM) with same iteration (3 times) steps. Furthermore, an unseen data is used to validate the generalization of different methods. Finally, we find that our method obtains superior results (0.94 value of SSIM for in vivo) with a high robustness and accelerated reconstruction.

eess.IV↗

arXiv2021

Quantum algorithm for Neighborhood Preserving Embedding

Neighborhood Preserving Embedding (NPE) is an important linear dimensionality reduction technique that aims at preserving the local manifold structure. NPE contains three steps, i.e., finding the nearest neighbors of each data point, constructing the weight matrix, and obtaining the transformation matrix. Liang et al. proposed a variational quantum algorithm (VQA) for NPE [Phys. Rev. A 101, 032323 (2020)]. The algorithm consists of three quantum sub-algorithms, corresponding to the three steps of NPE, and was expected to have an exponential speedup on the dimensionality $n$. However, the algorithm has two disadvantages: (1) It is incomplete in the sense that the input of the third sub-algorithm cannot be obtained by the second sub-algorithm. (2) Its complexity cannot be rigorously analyzed because the third sub-algorithm in it is a VQA. In this paper, we propose a complete quantum algorithm for NPE, in which we redesign the three sub-algorithms and give a rigorous complexity analysis. It is shown that our algorithm can achieve a polynomial speedup on the number of data points $m$ and an exponential speedup on the dimensionality $n$ under certain conditions over the classical NPE algorithm, and achieve significant speedup compared to Liang et al.'s algorithm even without considering the complexity of the VQA.

quant-ph↗

arXiv2021

PM2.5-GNN: A Domain Knowledge Enhanced Graph Neural Network For PM2.5 Forecasting

When predicting PM2.5 concentrations, it is necessary to consider complex information sources since the concentrations are influenced by various factors within a long period. In this paper, we identify a set of critical domain knowledge for PM2.5 forecasting and develop a novel graph based model, PM2.5-GNN, being capable of capturing long-term dependencies. On a real-world dataset, we validate the effectiveness of the proposed model and examine its abilities of capturing both fine-grained and long-term influences in PM2.5 process. The proposed PM2.5-GNN has also been deployed online to provide free forecasting service.

eess.SP↗

arXiv2021

Block-encoding based quantum algorithm for linear systems with displacement structures

Matrices with the displacement structures of circulant, Toeplitz, and Hankel types as well as matrices with structures generalizing these types are omnipresent in computations of sciences and engineering. In this paper, we present efficient and memory-reduced quantum algorithms for solving linear systems with such structures by devising a new approach to implement the block-encodings of these structured matrices. More specifically, by decomposing $n\times n$ dense matrices into linear combinations of displacement matrices, we first deduce the parameterized representations of the matrices with displacement structures so that they can be treated similarly. With such representations, we then construct $ε$-approximate block-encodings of these structured matrices in two different data access models, i.e., the black-box model and the QRAM data structure model. It is shown the quantum linear system solvers based on the proposed block-encodings provide a quadratic speedup with respect to the dimension over classical algorithms in the black-box model and an exponential speedup in the QRAM data structure model. In particular, these linear system solvers subsume known results with significant improvements and also motivate new instances where there was no specialized quantum algorithm before. As an application, one of the quantum linear system solvers is applied to the linear prediction of time series, which justifies the claimed quantum speedup is achievable for problems of practical interest.

quant-ph↗

arXiv2021

External Forces Resilient Safe Motion Planning for Quadrotor

Adaptive autonomous navigation with no prior knowledge of extraneous disturbance is of great significance for quadrotors in a complex and unknown environment. The mainstream that considers external disturbance is to implement disturbance-rejected control and path tracking. However, the robust control to compensate for tracking deviations is not well-considered regarding energy consumption, and even the reference path will become risky and intractable with disturbance. As recent external forces estimation advances, it is possible to incorporate a real-time force estimator to develop more robust and safe planning frameworks. This paper proposes a systematic (re)planning framework that can resiliently generate safe trajectories under volatile conditions. Firstly, a front-end kinodynamic path is searched with force-biased motion primitives. Then we develop a nonlinear model predictive control (NMPC) as a local planner with Hamilton-Jacobi (HJ) forward reachability analysis for error dynamics caused by external forces. It guarantees collision avoidance by constraining the ellipsoid of the quadrotor body expanded with the forward reachable sets (FRSs) within safe convex polytopes. Our method is validated in simulations and real-world experiments with different sources of external forces.

cs.RO↗

arXiv2021

Quantum algorithms for anomaly detection using amplitude estimation

Anomaly detection plays a critical role in fraud detection, health care, intrusion detection, military surveillance, etc. Anomaly detection algorithm based on density estimation (called ADDE algorithm) is one of widely used algorithms. Liang et al. proposed a quantum version of the ADDE algorithm [Phys. Rev. A 99, 052310 (2019)] and it is believed that the algorithm has exponential speedups on both the number and the dimension of training data point over the classical algorithm. In this paper, we find that Liang et al.'s algorithm doesn't actually execute. Then we propose a new quantum ADDE algorithm based on amplitude estimation. It is shown that our algorithm can achieves exponential speedup on the number $M$ of training data points compared with the classical counterpart. Besides, the idea of our algorithm can be applied to optimize the anomaly detection algorithm based on kernel principal component analysis (called ADKPCA algorithm). Different from the quantum ADKPCA proposed by Liu et al. [Phys. Rev. A 97, 042315 (2018)], compared with the classical counterpart, which offer exponential speedup on the dimension $d$ of data points, our algorithm achieves exponential speedup on $M$.

quant-ph↗

arXiv2021

Chemical Freeze-out Parameters via a Non-perturbative QCD Approach

By analyzing the calculated baryon number susceptibility ratios ${χ_{1}^{B}}/{χ_{2}^{B}}$ and ${χ_{3}^{B}}/{χ_{1}^{B}}$ in two-flavor system via the Dyson-Schwinger equation approach of QCD, we determine the chemical freeze-out temperature and baryon chemical potential in cases of both thermodynamic limit and finite size. We calculate the center-of-mass energy dependence of the ${χ_{4}^{B}}/{χ_{2}^{B}}\, (κσ^{2})$ at the freeze-out line and find an excellent agreement with experimental data when taking into account the finite size effect. Our calculations indicate that the $κσ^{2}$ exhibits a nonmonotonic behavior in lower collision energy region. We also predict that the collision energy dependence of ${χ_{6}^{B}}/{χ_{2}^{B}}$ is nonmonotonic.

hep-ph↗

arXiv2021

Photoacoustic digital brain: numerical modelling and image reconstruction via deep learning

Photoacoustic tomography (PAT) is a newly developed medical imaging modality, which combines the advantages of pure optical imaging and ultrasound imaging, owning both high optical contrast and deep penetration depth. Very recently, PAT is studied in human brain imaging. Nevertheless, while ultrasound waves are passing through the human skull tissues, the strong acoustic attenuation and aberration will happen, which causes photoacoustic signals' distortion. In this work, we use 10 magnetic resonance angiography (MRA) human brain volumes, and manually segment them to obtain the 2D human brain numerical phantoms for PAT. The numerical phantoms contain six kinds of tissues which are scalp, skull, white matter, gray matter, blood vessel and cerebral cortex. For every numerical phantom, optical properties are assigned to every kind of tissues. Then, Monte-Carlo based optical simulation is deployed to obtain the photoacoustic initial pressure. Then, we made two k-wave simulation cases: one takes inhomogeneous medium and uneven sound velocity into consideration, and the other not. Then we use the sensor data of the former one as the input of U-net, and the sensor data of the latter one as the output of U-net to train the network. We randomly choose 7 human brain PA sinograms as the training dataset and 3 human brain PA sinograms as the testing set. The testing result shows that our method could correct the skull acoustic aberration and obtain the blood vessel distribution inside the human brain satisfactorily.

physics.med-ph↗

arXiv2021

Robust Trajectory Planning for Spatial-Temporal Multi-Drone Coordination in Large Scenes

In this paper, we describe a robust multi-drone planning framework for high-speed trajectories in large scenes. It uses a free-space-oriented map to free the optimization from cumbersome environment data. A capsule-like safety constraint is designed to avoid reciprocal collisions when vehicles deviate from their nominal flight progress under disturbance. We further show the minimum-singularity differential flatness of our drone dynamics with nonlinear drag effects involved. Leveraging the flatness map, trajectory optimization is efficiently conducted on the flat outputs while still subject to physical limits considering drag forces at high speeds. The robustness and effectiveness of our framework are both validated in large-scale simulations. It can compute collision-free trajectories satisfying high-fidelity vehicle constraints for hundreds of drones in a few minutes.

cs.RO↗

arXiv2021

STD-Trees: Spatio-temporal Deformable Trees for Multirotors Kinodynamic Planning

In constrained solution spaces with a huge number of homotopy classes, stand-alone sampling-based kinodynamic planners suffer low efficiency in convergence. Local optimization is integrated to alleviate this problem. In this paper, we propose to thrive the trajectory tree growing by optimizing the tree in the forms of deformation units, and each unit contains one tree node and all the edges connecting it. The deformation proceeds both spatially and temporally by optimizing the node state and edge time durations efficiently. The unit only changes the tree locally yet improves the overall quality of a corresponding sub-tree. Further, variants to deform different tree parts considering the computation burden and optimizing level are studied and compared, all showing much faster convergence. The proposed deformation is compatible with different RRT-based kinodynamic planning methods, and numerical experiments show that integrating the spatio-temporal deformation greatly accelerates the convergence and outperforms the spatial-only deformation.

cs.RO↗

arXiv2021

Fast-Racing: An Open-source Strong Baseline for SE(3) Planning in Autonomous Drone Racing

With the autonomy of aerial robots advances in recent years, autonomous drone racing has drawn increasing attention. In a professional pilot competition, a skilled operator always controls the drone to agilely avoid obstacles in aggressive attitudes, for reaching the destination as fast as possible. Autonomous flight like elite pilots requires planning in SE(3), whose non-triviality and complexity hindering a convincing solution in our community by now. To bridge this gap, this paper proposes an open-source baseline, which includes a high-performance SE(3) planner and a challenging simulation platform tailored for drone racing. We specify the SE(3) trajectory generation as a soft-penalty optimization problem, and speed up the solving process utilizing its underlying parallel structure. Moreover, to provide a testbed for challenging the planner, we develop delicate drone racing tracks which mimic real-world set-up and necessities planning in SE(3). Besides, we provide necessary system components such as common map interfaces and a baseline controller, to make our work plug-in-and-use. With our baseline, we hope to future foster the research of SE(3) planning and the competition of autonomous drone racing.

cs.RO↗

arXiv2021

Kernel Mean Estimation by Marginalized Corrupted Distributions

Estimating the kernel mean in a reproducing kernel Hilbert space is a critical component in many kernel learning algorithms. Given a finite sample, the standard estimate of the target kernel mean is the empirical average. Previous works have shown that better estimators can be constructed by shrinkage methods. In this work, we propose to corrupt data examples with noise from known distributions and present a new kernel mean estimator, called the marginalized kernel mean estimator, which estimates kernel mean under the corrupted distribution. Theoretically, we show that the marginalized kernel mean estimator introduces implicit regularization in kernel mean estimation. Empirically, we show on a variety of datasets that the marginalized kernel mean estimator obtains much lower estimation error than the existing estimators.

cs.LG↗