Searcharxiv⌕ Search

arXiv subjects

Fang Deng

Publications and source records attributed to Fang Deng.

28 records · Page 2Linked to original sources

Scalable Hierarchical Reinforcement Learning for Hyper Scale Multi-Robot Task Planning

To improve the efficiency of warehousing system and meet huge customer orders, we aim to solve the challenges of dimension disaster and dynamic properties in hyper scale multi-robot task planning (MRTP) for robotic mobile fulfillment system (RMFS). Existing research indicates that hierarchical reinforcement learning (HRL) is an effective method to reduce these challenges. Based on that, we construct an efficient multi-stage HRL-based multi-robot task planner for hyper scale MRTP in RMFS, and the planning process is represented with a special temporal graph topology. To ensure optimality, the planner is designed with a centralized architecture, but it also brings the challenges of scaling up and generalization that require policies to maintain performance for various unlearned scales and maps. To tackle these difficulties, we first construct a hierarchical temporal attention network (HTAN) to ensure basic ability of handling inputs with unfixed lengths, and then design multi-stage curricula for hierarchical policy learning to further improve the scaling up and generalization ability while avoiding catastrophic forgetting. Additionally, we notice that policies with hierarchical structure suffer from unfair credit assignment that is similar to that in multi-agent reinforcement learning, inspired of which, we propose a hierarchical reinforcement learning algorithm with counterfactual rollout baseline to improve learning performance. Experimental results demonstrate that our planner outperform other state-of-the-art methods on various MRTP instances in both simulated and real-world RMFS. Also, our planner can successfully scale up to hyper scale MRTP instances in RMFS with up to 200 robots and 1000 retrieval racks on unlearned maps while keeping superior performance over other methods.

cs.RO↗

Data-driven Control Against False Data Injection Attacks

The rise of cyber-security concerns has brought significant attention to the analysis and design of cyber-physical systems (CPSs). Among the various types of cyberattacks, denial-of-service (DoS) attacks and false data injection (FDI) attacks can be easily launched and have become prominent threats. While resilient control against DoS attacks has received substantial research efforts, countermeasures developed against FDI attacks have been relatively limited, particularly when explicit system models are not available. To address this gap, the present paper focuses on the design of data-driven controllers for unknown linear systems subject to FDI attacks on the actuators, utilizing input-state data. To this end, a general FDI attack model is presented, which imposes minimally constraints on the switching frequency of attack channels and the magnitude of attack matrices. A dynamic state feedback control law is designed based on offline and online input-state data, which adapts to the channel switching of FDI attacks. This is achieved by solving two data-based semi-definite programs (SDPs) on-the-fly to yield a tight approximation of the set of subsystems consistent with both offline clean data and online attack-corrupted data. It is shown that under mild conditions on the attack, the proposed SDPs are recursively feasible and controller achieves exponential stability. Numerical examples showcase its effectiveness in mitigating the impact of FDI attacks.

eess.SY↗

High quality Fe1+yTe synthesized by chemical vapor deposition with conspicuous vortex flow

Two-dimensional (2D) materials provide an ideal platform to explore novel superconducting behavior including Ising superconductivity, topological superconductivity and Majorana bound states in different 2D stoichiometric Ta-, Nb-, and Fe-based crystals. However, tuning the element content in 2D compounds for regulating their superconductivity has not been realized. In this work, we report the synthesis of high quality Fe1+yTe with tunable Fe content by chemical vapor deposition (CVD). The quality and composition of Fe1+yTe are characterized by Raman spectroscopy, X-ray photoelectron spectroscopy (XPS) and scanning transmission electron microscopy (STEM). The superconducting behavior of Fe1+yTe crystals with varying Fe contents is observed. The superconducting transition of selected Fe1.13Te sample is sharp (ΔTc = 1 K), while Fe1.43Te with a high-Fe content shows a relative broad superconducting transition (ΔTc = 2.6 K) at zero magnetic field. Significantly, the conspicuous vortex flow and a transition from a 3D vortex liquid state to a 2D vortex liquid state is observed in Fe1.43Te sample. Our work highlights the tunability of the superconducting properties of Fe1+yTe and sheds light on the vortex dynamics in Fe-based superconductors, which facilitates us to understand the intrinsic mechanisms of high-temperature superconductivity.

physics.app-ph↗

Attitude Tracking of Uncertain Flexible Spacecraft Systems Subject to Unknown External Disturbances

In this paper, we investigate the attitude tracking problem of uncertain flexible spacecraft systems subject to external disturbances. In sharp contrast to existing results, the dynamics of flexible spacecraft systems and external disturbances are allowed to be unknown. To deal with the challenges by these unknown factors, we develop a class of nonlinear internal models which converts the attitude tracking problem of uncertain flexible spacecraft systems into a regulation problem of an augmented system. Furthermore, to overcome the difficulties caused by the unmeasurable modal variable, the uncertainty introduced by the internal model, and the cross-coupling of the uncertainties with the system state, we design an auxiliary dynamic system for auxiliary stabilization, a dynamic compensator for dynamic compensation, and a linearly parameterized transformation for adaptive regulation in sequence. By introducing a series of coordinate and input transformations, we propose an adaptive dynamic control law to achieve regulation of the augmented system and thus leading to the solution to the attitude tracking problem. In addition, we analyze the convergence issue of the estimated parameter to its true value by the persistently exciting condition. Finally, the effec tiveness of the developed approach is verified by its application to the attitude manoeuvre of a flexible spacecraft system in the presence of external disturbances.

math.OC↗

METER: A Dynamic Concept Adaptation Framework for Online Anomaly Detection

Real-time analytics and decision-making require online anomaly detection (OAD) to handle drifts in data streams efficiently and effectively. Unfortunately, existing approaches are often constrained by their limited detection capacity and slow adaptation to evolving data streams, inhibiting their efficacy and efficiency in handling concept drift, which is a major challenge in evolving data streams. In this paper, we introduce METER, a novel dynamic concept adaptation framework that introduces a new paradigm for OAD. METER addresses concept drift by first training a base detection model on historical data to capture recurring central concepts, and then learning to dynamically adapt to new concepts in data streams upon detecting concept drift. Particularly, METER employs a novel dynamic concept adaptation technique that leverages a hypernetwork to dynamically generate the parameter shift of the base detection model, providing a more effective and efficient solution than conventional retraining or fine-tuning approaches. Further, METER incorporates a lightweight drift detection controller, underpinned by evidential deep learning, to support robust and interpretable concept drift detection. We conduct an extensive experimental evaluation, and the results show that METER significantly outperforms existing OAD approaches in various application scenarios.

cs.LG↗

Flexible Job Shop Scheduling via Dual Attention Network Based Reinforcement Learning

Flexible manufacturing has given rise to complex scheduling problems such as the flexible job shop scheduling problem (FJSP). In FJSP, operations can be processed on multiple machines, leading to intricate relationships between operations and machines. Recent works have employed deep reinforcement learning (DRL) to learn priority dispatching rules (PDRs) for solving FJSP. However, the quality of solutions still has room for improvement relative to that by the exact methods such as OR-Tools. To address this issue, this paper presents a novel end-to-end learning framework that weds the merits of self-attention models for deep feature extraction and DRL for scalable decision-making. The complex relationships between operations and machines are represented precisely and concisely, for which a dual-attention network (DAN) comprising several interconnected operation message attention blocks and machine message attention blocks is proposed. The DAN exploits the complicated relationships to construct production-adaptive operation and machine features to support high-quality decisionmaking. Experimental results using synthetic data as well as public benchmarks corroborate that the proposed approach outperforms both traditional PDRs and the state-of-the-art DRL method. Moreover, it achieves results comparable to exact methods in certain cases and demonstrates favorable generalization ability to large-scale and real-world unseen FJSP tasks.

cs.LG↗

Space Mapping of Spline Spaces over Hierarchical T-meshes

In this paper, we construct a bijective mapping between a biquadratic spline space over the hierarchical T-mesh and the piecewise constant space over the corresponding crossing-vertex-relationship graph (CVR graph). We propose a novel structure, by which we offer an effective and easy operative method for constructing the basis functions of the biquadratic spline space. The mapping we construct is an isomorphism. The basis functions of the biquadratic spline space hold the properties such as linearly independent, completeness and the property of partition of unity, which are the same with the properties for the basis functions of piecewise constant space over the CVR graph. To demonstrate that the new basis functions are efficient, we apply the basis functions to fit some open surfaces.

cs.CG↗

Distributed Noise Covariance Matrices Estimation in Sensor Networks

Adaptive algorithms based on in-network processing over networks are useful for online parameter estimation of historical data (e.g., noise covariance) in predictive control and machine learning areas. This paper focuses on the distributed noise covariance matrices estimation problem for multi-sensor linear time-invariant (LTI) systems. Conventional noise covariance estimation approaches, e.g., auto-covariance least squares (ALS) method, suffers from the lack of the sensor's historical measurements and thus produces high variance of the ALS estimate. To solve the problem, we propose the distributed auto-covariance least squares (D-ALS) algorithm based on the batch covariance intersection (BCI) method by enlarging the innovations from the neighbors. The accuracy analysis of D-ALS algorithm is given to show the decrease of the variance of the D-ALS estimate. The numerical results of cooperative target tracking tasks in static and mobile sensor networks are demonstrated to show the feasibility and superiority of the proposed D-ALS algorithm.

math.OC↗

End-to-End Code-Switching ASR for Low-Resourced Language Pairs

Despite the significant progress in end-to-end (E2E) automatic speech recognition (ASR), E2E ASR for low resourced code-switching (CS) speech has not been well studied. In this work, we describe an E2E ASR pipeline for the recognition of CS speech in which a low-resourced language is mixed with a high resourced language. Low-resourcedness in acoustic data hinders the performance of E2E ASR systems more severely than the conventional ASR systems.~To mitigate this problem in the transcription of archives with code-switching Frisian-Dutch speech, we integrate a designated decoding scheme and perform rescoring with neural network-based language models to enable better utilization of the available textual resources. We first incorporate a multi-graph decoding approach which creates parallel search spaces for each monolingual and mixed recognition tasks to maximize the utilization of the textual resources from each language. Further, language model rescoring is performed using a recurrent neural network pre-trained with cross-lingual embedding and further adapted with the limited amount of in-domain CS text. The ASR experiments demonstrate the effectiveness of the described techniques in improving the recognition performance of an E2E CS ASR system in a low-resourced scenario.

cs.CL↗

Dimensions of Biquadratic and Bicubic Spline Spaces over Hierarchical T-meshes

This paper discusses the dimensions of biquadratic C1 spline spaces and bicubic C2 spline spaces over hierarchical T-meshes using the smoothing cofactor-conformality method. We obtain the dimension formula of biquadratic C1 spline spaces over hierarchical T-meshes in a concise way. In addition, we provide a dimension formula for bicubic C2 spline spaces over hierarchical T-mesh with fewer restrictions than that in the previous literature. A dimension formula for bicubic C2 spline spaces over a new type hierarchical T-mesh is also provided.

math.NA↗