arXiv subjects

He Li

Publications and source records attributed to He Li.

At least 109 records · Page 6Linked to original sources

arXiv2023

A Unified Perspective on Multiple Shooting In Differential Dynamic Programming

Differential Dynamic Programming (DDP) is an efficient computational tool for solving nonlinear optimal control problems. It was originally designed as a single shooting method and thus is sensitive to the initial guess supplied. This work considers the extension of DDP to multiple shooting (MS), improving its robustness to initial guesses. A novel derivation is proposed that accounts for the defect between shooting segments during the DDP backward pass, while still maintaining quadratic convergence locally. The derivation enables unifying multiple previous MS algorithms, and opens the door to many smaller algorithmic improvements. A penalty method is introduced to strategically control the step size, further improving the convergence performance. An adaptive merit function and a more reliable acceptance condition are employed for globalization. The effects of these improvements are benchmarked for trajectory optimization with a quadrotor, an acrobot, and a manipulator. MS-DDP is also demonstrated for use in Model Predictive Control (MPC) for dynamic jumping with a quadruped robot, showing its benefits over a single shooting approach.

cs.RO↗

arXiv2023

Constrained CycleGAN for Effective Generation of Ultrasound Sector Images of Improved Spatial Resolution

Objective. A phased or a curvilinear array produces ultrasound (US) images with a sector field of view (FOV), which inherently exhibits spatially-varying image resolution with inferior quality in the far zone and towards the two sides azimuthally. Sector US images with improved spatial resolutions are favorable for accurate quantitative analysis of large and dynamic organs, such as the heart. Therefore, this study aims to translate US images with spatially-varying resolution to ones with less spatially-varying resolution. CycleGAN has been a prominent choice for unpaired medical image translation; however, it neither guarantees structural consistency nor preserves backscattering patterns between input and generated images for unpaired US images. Approach. To circumvent this limitation, we propose a constrained CycleGAN (CCycleGAN), which directly performs US image generation with unpaired images acquired by different ultrasound array probes. In addition to conventional adversarial and cycle-consistency losses of CycleGAN, CCycleGAN introduces an identical loss and a correlation coefficient loss based on intrinsic US backscattered signal properties to constrain structural consistency and backscattering patterns, respectively. Instead of post-processed B-mode images, CCycleGAN uses envelope data directly obtained from beamformed radio-frequency signals without any other non-linear postprocessing. Main Results. In vitro phantom results demonstrate that CCycleGAN successfully generates images with improved spatial resolution as well as higher peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) compared with benchmarks. Significance. CCycleGAN-generated US images of the in vivo human beating heart further facilitate higher quality heart wall motion estimation than benchmarks-generated ones, particularly in deep regions.

eess.IV↗

arXiv2023

When Monte-Carlo Dropout Meets Multi-Exit: Optimizing Bayesian Neural Networks on FPGA

Bayesian Neural Networks (BayesNNs) have demonstrated their capability of providing calibrated prediction for safety-critical applications such as medical imaging and autonomous driving. However, the high algorithmic complexity and the poor hardware performance of BayesNNs hinder their deployment in real-life applications. To bridge this gap, this paper proposes a novel multi-exit Monte-Carlo Dropout (MCD)-based BayesNN that achieves well-calibrated predictions with low algorithmic complexity. To further reduce the barrier to adopting BayesNNs, we propose a transformation framework that can generate FPGA-based accelerators for multi-exit MCD-based BayesNNs. Several novel optimization techniques are introduced to improve hardware performance. Our experiments demonstrate that our auto-generated accelerator achieves higher energy efficiency than CPU, GPU, and other state-of-the-art hardware implementations.

cs.LG↗

arXiv2023

Phenomenological study of $J/ψ\toΞ^0(Λπ^0) \barΞ^0(\barΛ γ)$ decays

The measurement of decay parameters is one of the important goals of particle physics experiments, and the measurement serves as a probe to search for evidence of CP violation in baryonic decays. The experimental results will help advance existing theoretical research and establish new experimental objectives. In this paper, we formulate the asymmetric parameters that characterize parity violation, and then derive formulas for the measurement of CP violation. The formulae for the joint angular distribution of the full decay chain as well as the polarization observable of $Ξ^ 0 $, $\bar { Ξ} ^ 0 $, $Λ$ and $\bar { Λ} $ are also provided for experiments. Lastly, we evaluated the sensitivity of two asymmetric parameters: $α_ { Ξ^ 0 \to Λπ^ 0 } $ (abbreviated as $α_ { Ξ^ 0 } $) and $α_ { \bar { Ξ} ^ 0 \to \bar { Λ} γ} $ (abbreviated as $α_ {\barΞ^0 } $) for future experimental measurement.

hep-ph↗

arXiv2023

iCOIL: Scenario Aware Autonomous Parking Via Integrated Constrained Optimization and Imitation Learning

Autonomous parking (AP) is an emering technique to navigate an intelligent vehicle to a parking space without any human intervention. Existing AP methods based on mathematical optimization or machine learning may lead to potential failures due to either excessive execution time or lack of generalization. To fill this gap, this paper proposes an integrated constrained optimization and imitation learning (iCOIL) approach to achieve efficient and reliable AP. The iCOIL method has two candidate working modes, i.e., CO and IL, and adopts a hybrid scenario analysis (HSA) model to determine the better mode under various scenarios. We implement and verify iCOIL on the Macao Car Racing Metaverse (MoCAM) platform. Results show that iCOIL properly adapts to different scenarios during the entire AP procedure, and achieves significantly larger success rates than other benchmarks.

cs.RO↗

arXiv2023

AnomMAN: Detect Anomaly on Multi-view Attributed Networks

Anomaly detection on attributed networks is widely used in online shopping, financial transactions, communication networks, and so on. However, most existing works trying to detect anomalies on attributed networks only consider a single kind of interaction, so they cannot deal with various kinds of interactions on multi-view attributed networks. It remains a challenging task to jointly consider all different kinds of interactions and detect anomalous instances on multi-view attributed networks. In this paper, we propose a graph convolution-based framework, named AnomMAN, to detect Anomaly on Multi-view Attributed Networks. To jointly consider attributes and all kinds of interactions on multi-view attributed networks, we use the attention mechanism to define the importance of all views in networks. Since the low-pass characteristic of graph convolution operation filters out most high-frequency signals (aonmaly signals), it cannot be directly applied to anomaly detection tasks. AnomMAN introduces the graph auto-encoder module to turn the disadvantage of low-pass features into an advantage. According to experiments on real-world datasets, AnomMAN outperforms the state-of-the-art models and two variants of our proposed model.

cs.SI↗

arXiv2023

Efficient hybrid density functional calculation by deep learning

Hybrid density functional calculation is indispensable to accurate description of electronic structure, whereas the formidable computational cost restricts its broad application. Here we develop a deep equivariant neural network method (named DeepH-hybrid) to learn the hybrid-functional Hamiltonian from self-consistent field calculations of small structures, and apply the trained neural networks for efficient electronic-structure calculation by passing the self-consistent iterations. The method is systematically checked to show high efficiency and accuracy, making the study of large-scale materials with hybrid-functional accuracy feasible. As an important application, the DeepH-hybrid method is applied to study large-supercell Moiré twisted materials, offering the first case study on how the inclusion of exact exchange affects flat bands in the magic-angle twisted bilayer graphene.

cond-mat.mtrl-sci↗

arXiv2022

Deep-learning electronic-structure calculation of magnetic superstructures

Ab initio study of magnetic superstructures (e.g., magnetic skyrmion) is indispensable to the research of novel materials but bottlenecked by its formidable computational cost. For solving the bottleneck problem, we develop a deep equivariant neural network method (named xDeepH) to represent density functional theory Hamiltonian $H_\text{DFT}$ as a function of atomic and magnetic structures and apply neural networks for efficient electronic structure calculation. Intelligence of neural networks is optimized by incorporating a priori knowledge about the important locality and symmetry properties into the method. Particularly, we design a neural-network architecture fully preserving all equivalent requirements on $H_\text{DFT}$ by the Euclidean and time-reversal symmetries ($E(3) \times \{I, T\}$), which is essential to improve method performance. High accuracy (sub-meV error) and good transferability of xDeepH are shown by systematic experiments on nanotube, spin-spiral, and Moiré magnets, and the capability of studying magnetic skyrmion is also demonstrated. The method could find promising applications in magnetic materials research and inspire development of deep-learning ab initio methods.

physics.comp-ph↗

arXiv2022

General framework for E(3)-equivariant neural network representation of density functional theory Hamiltonian

Combination of deep learning and ab initio calculation has shown great promise in revolutionizing future scientific research, but how to design neural network models incorporating a priori knowledge and symmetry requirements is a key challenging subject. Here we propose an E(3)-equivariant deep-learning framework to represent density functional theory (DFT) Hamiltonian as a function of material structure, which can naturally preserve the Euclidean symmetry even in the presence of spin-orbit coupling. Our DeepH-E3 method enables very efficient electronic-structure calculation at ab initio accuracy by learning from DFT data of small-sized structures, making routine study of large-scale supercells ($> 10^4$ atoms) feasible. Remarkably, the method can reach sub-meV prediction accuracy at high training efficiency, showing state-of-the-art performance in our experiments. The work is not only of general significance to deep-learning method development, but also creates new opportunities for materials research, such as building Moiré-twisted material database.

physics.comp-ph↗

arXiv2022

Joint Detections of Frequency and Direction of Arrival in Wideband Based on Programmable Metasurface

We propose to achieve joint detections of frequency and direction of arrival in wideband using single sensor based on an active metasurface with programmable transmission states of pass and stop. By integrating two PIN diodes with the opposite directions into the proposed single-layer and ultrathin meta-atom, the transmission performance with 10 dB difference between the pass and stop states is realized in the bandwidth from 5.9 GHz to 8.8 GHz using field-circuit co-simulations. Accordingly, random receiving patterns are generated by controlling the programmable metasurface composed of the switchable meta-atoms. Afterwards, the frequency and direction information of sources located in the far field are detected using the modified algorithm of estimating signal parameters via rotational invariance techniques (ESPRIT) and the compressive sensing method, respectively. A sample of the programmable metasurface is fabricated and the voltage control system is built up correspondingly. To entirely verify the validity of the proposed method, we conduct three kinds of experiments with one single source, double sources with different frequencies, and double sources with the same frequency, respectively. In all cases, the source information of frequency and direction has been detected preciously in measurements in the frequency band from 6.2 GHz to 8.8 GHz.

physics.app-ph↗

arXiv2022

New Parameter Measurements for the Ultra-Short-Period Planet TOI-1807b

The ultra-short-period (USP) planets are exoplanets with very short orbital periods ($\textit{P} < 1$ day), and TOI-1807b is one such planet recently discovered by the TESS mission where it orbits in the TOI-1807 system that is still little known nowadays. In this paper, we re-analyzed the transit light curves of TOI-1807 using the latest TESS data from Sector 49, combined with previous data from Sector 22 and 23. By running the MCMC simulation through all three sectors, we found that our transit model fits the data from Sector 49 the best, and we deduced that TOI-1807b is a Super-Earth with a mass of $2.27^{+0.49}_{-0.58}\, M_\oplus$, a radius of $1.37^{+0.10}_{-0.09}\, R_\oplus$, a density of $0.875^{+0.264}_{-0.285}\, ρ_\oplus$, and a surface temperature of $1499^{+82}_{-129}\, \mathrm{K}$. We confirmed that TOI-1807b orbits at approximately $0.0135^{+0.0013}_{-0.0022}\, \mathrm{AU}$ with a period of $0.54929^{+0.00012}_{-0.00005}\, \mathrm{days}$, which raises the possibility of the planet being tidally locked due to spin-orbit synchronization. In addition, we suggest that TOI-1807b might slowly undergo its orbital decay process, and we further identify that TOI-1807b is in a circular, synchronous orbit and permanently deformed due to tides, leading to $\sim$4% correction in density. Since TOI-1807 is such a young star with an age of only $300 \pm 80\, \mathrm{Myr}$, we also imply that the radiation emitted from active TOI-1807 could be so intense that it might have destroyed most of the atmosphere over the surface of TOI-1807b.

astro-ph.EP↗

arXiv2022

Zero-Shot Retargeting of Learned Quadruped Locomotion Policies Using Hybrid Kinodynamic Model Predictive Control

Reinforcement Learning (RL) has witnessed great strides for quadruped locomotion, with continued progress in the reliable sim-to-real transfer of policies. However, it remains a challenge to reuse a policy on another robot, which could save time for retraining. In this work, we present a framework for zero-shot policy retargeting wherein diverse motor skills can be transferred between robots of different shapes and sizes. The new framework centers on a planning-and-control pipeline that systematically integrates RL and Model Predictive Control (MPC). The planning stage employs RL to generate a dynamically plausible trajectory as well as the contact schedule, avoiding the combinatorial complexity of contact sequence optimization. This information is then used to seed the MPC to stabilize and robustify the policy roll-out via a new Hybrid Kinodynamic (HKD) model that implicitly optimizes the foothold locations. Hardware results show an ability to transfer policies from both the A1 and Laikago robots to the MIT Mini Cheetah robot without requiring any policy re-tuning.

cs.RO↗

arXiv2022

Versatile Real-Time Motion Synthesis via Kino-Dynamic MPC with Hybrid-Systems DDP

Specialized motions such as jumping are often achieved on quadruped robots by solving a trajectory optimization problem once and executing the trajectory using a tracking controller. This approach is in parallel with Model Predictive Control (MPC) strategies that commonly control regular gaits via online re-planning. In this work, we present a nonlinear MPC (NMPC) technique that unlocks on-the-fly re-planning of specialized motion skills and regular locomotion within a unified framework. The NMPC reasons about a hybrid kinodynamic model, and is solved using a variant of a constrained Differential Dynamic Programming (DDP) solver. The proposed NMPC enables the robot to perform a variety of agile skills like jumping, bounding, and trotting, and the rapid transition between these skills. We evaluated the proposed algorithm with three challenging motion sequences that combine multiple agile skills, on two quadruped platforms, Unitree A1, and MIT Mini Cheetah, showing its effectiveness and generality.

cs.RO↗

arXiv2022

Deep-Learning Density Functional Theory Hamiltonian for Efficient ab initio Electronic-Structure Calculation

The marriage of density functional theory (DFT) and deep learning methods has the potential to revolutionize modern computational materials science. Here we develop a deep neural network approach to represent DFT Hamiltonian (DeepH) of crystalline materials, aiming to bypass the computationally demanding self-consistent field iterations of DFT and substantially improve the efficiency of ab initio electronic-structure calculations. A general framework is proposed to deal with the large dimensionality and gauge (or rotation) covariance of DFT Hamiltonian matrix by virtue of locality and is realized by the message passing neural network for deep learning. High accuracy, high efficiency and good transferability of the DeepH method are generally demonstrated for various kinds of material systems and physical properties. The method provides a solution to the accuracy-efficiency dilemma of DFT and opens opportunities to explore large-scale material systems, as evidenced by a promising application to study twisted van der Waals materials.

cond-mat.mtrl-sci↗

arXiv2022

Random Ensemble Reinforcement Learning for Traffic Signal Control

Traffic signal control is a significant part of the construction of intelligent transportation. An efficient traffic signal control strategy can reduce traffic congestion, improve urban road traffic efficiency and facilitate people's lives. Existing reinforcement learning approaches for traffic signal control mainly focus on learning through a separate neural network. Such an independent neural network may fall into the local optimum of the training results. Worse more, the collected data can only be sampled once, so the data utilization rate is low. Therefore, we propose the Random Ensemble Double DQN Light (RELight) model. It can dynamically learn traffic signal control strategies through reinforcement learning and combine random ensemble learning to avoid falling into the local optimum to reach the optimal strategy. Moreover, we introduce the Update-To-Data (UTD) ratio to control the number of data reuses to improve the problem of low data utilization. In addition, we have conducted sufficient experiments on synthetic data and real-world data to prove that our proposed method can achieve better traffic signal control effects than the existing optimal methods.

cs.LG↗

arXiv2022

Mini Cheetah, the Falling Cat: A Case Study in Machine Learning and Trajectory Optimization for Robot Acrobatics

Seemingly in defiance of basic physics, cats consistently land on their feet after falling. In this paper, we design a controller that lands the Mini Cheetah quadruped robot on its feet as well. Specifically, we explore how trajectory optimization and machine learning can work together to enable highly dynamic bioinspired behaviors. We find that a reflex approach, in which a neural network learns entire state trajectories, outperforms a policy approach, in which a neural network learns a mapping from states to control inputs. We validate our proposed controller in both simulation and hardware experiments, and are able to land the robot on its feet from falls with initial pitch angles between -90 and 90 degrees.

cs.RO↗

arXiv2021

Algorithm and Hardware Co-design for Reconfigurable CNN Accelerator

Recent advances in algorithm-hardware co-design for deep neural networks (DNNs) have demonstrated their potential in automatically designing neural architectures and hardware designs. Nevertheless, it is still a challenging optimization problem due to the expensive training cost and the time-consuming hardware implementation, which makes the exploration on the vast design space of neural architecture and hardware design intractable. In this paper, we demonstrate that our proposed approach is capable of locating designs on the Pareto frontier. This capability is enabled by a novel three-phase co-design framework, with the following new features: (a) decoupling DNN training from the design space exploration of hardware architecture and neural architecture, (b) providing a hardware-friendly neural architecture space by considering hardware characteristics in constructing the search cells, (c) adopting Gaussian process to predict accuracy, latency and power consumption to avoid time-consuming synthesis and place-and-route processes. In comparison with the manually-designed ResNet101, InceptionV2 and MobileNetV2, we can achieve up to 5% higher accuracy with up to 3x speed up on the ImageNet dataset. Compared with other state-of-the-art co-design frameworks, our found network and hardware configuration can achieve 2% ~ 6% higher accuracy, 2x ~ 26x smaller latency and 8.5x higher energy efficiency.

cs.LG↗

arXiv2021

DetectorNet: Transformer-enhanced Spatial Temporal Graph Neural Network for Traffic Prediction

Detectors with high coverage have direct and far-reaching benefits for road users in route planning and avoiding traffic congestion, but utilizing these data presents unique challenges including: the dynamic temporal correlation, and the dynamic spatial correlation caused by changes in road conditions. Although the existing work considers the significance of modeling with spatial-temporal correlation, what it has learned is still a static road network structure, which cannot reflect the dynamic changes of roads, and eventually loses much valuable potential information. To address these challenges, we propose DetectorNet enhanced by Transformer. Differs from previous studies, our model contains a Multi-view Temporal Attention module and a Dynamic Attention module, which focus on the long-distance and short-distance temporal correlation, and dynamic spatial correlation by dynamically updating the learned knowledge respectively, so as to make accurate prediction. In addition, the experimental results on two public datasets and the comparison results of four ablation experiments proves that the performance of DetectorNet is better than the eleven advanced baselines.

cs.CV↗