arXiv subjects

Hao Xiong

Publications and source records attributed to Hao Xiong.

At least 37 records · Page 2Linked to original sources

arXiv2022

Non-cascaded Control Barrier Functions for the Safe Control of Quadrotors

Researchers have developed various cascaded controllers and non-cascaded controllers for the navigation and control of quadrotors in recent years. It is vital to ensure the safety of a quadrotor both in normal state and in abnormal state if a controller tends to make the quadrotor unsafe. To this end, this paper proposes a non-cascaded Control Barrier Function (CBF) for a quadrotor controlled by either cascaded controllers or a non-cascaded controller. Incorporated with a Quadratic Programming (QP), the non-cascaded CBF can simultaneously regulate the magnitude of the total thrust and the torque of the quadrotor determined a controller, so as to ensure the safety of the quadrotor both in normal state and in abnormal state. The non-cascaded CBF establishes a non-conservative forward invariant safe region, in which the controller of a quadrotor is fully or partially effective in the navigation or the pose control of the quadrotor. The non-cascaded CBF is applied to a quadrotor performing trajectory tracking and a quadrotor performing aggressive roll maneuvers in simulations to evaluate the effectiveness of the non-cascaded CBF.

eess.SY↗

arXiv2022

Safe Reinforcement Learning for a Robot Being Pursued but with Objectives Covering More Than Capture-avoidance

Reinforcement Learning (RL) algorithms show amazing performance in recent years, but placing RL in real-world applications such as self-driven vehicles may suffer safety problems. A self-driven vehicle moving to a target position following a learned policy may suffer a vehicle with unpredictable aggressive behaviors or even being pursued by a vehicle following a Nash strategy. To address the safety issue of the self-driven vehicle in this scenario, this paper conducts a preliminary study based on a system of robots. A safe RL framework with safety guarantees is developed for a robot being pursued but with objectives covering more than capture-avoidance. Simulations and experiments are conducted based on the system of robots to evaluate the effectiveness of the developed safe RL framework.

eess.SY↗

arXiv2022

Enhancing Sequential Recommendation with Graph Contrastive Learning

The sequential recommendation systems capture users' dynamic behavior patterns to predict their next interaction behaviors. Most existing sequential recommendation methods only exploit the local context information of an individual interaction sequence and learn model parameters solely based on the item prediction loss. Thus, they usually fail to learn appropriate sequence representations. This paper proposes a novel recommendation framework, namely Graph Contrastive Learning for Sequential Recommendation (GCL4SR). Specifically, GCL4SR employs a Weighted Item Transition Graph (WITG), built based on interaction sequences of all users, to provide global context information for each interaction and weaken the noise information in the sequence data. Moreover, GCL4SR uses subgraphs of WITG to augment the representation of each interaction sequence. Two auxiliary learning objectives have also been proposed to maximize the consistency between augmented representations induced by the same interaction sequence on WITG, and minimize the difference between the representations augmented by the global context on WITG and the local representation of the original sequence. Extensive experiments on real-world datasets demonstrate that GCL4SR consistently outperforms state-of-the-art sequential recommendation methods.

cs.IR↗

arXiv2022

DRLinFluids -- An open-source python platform of coupling Deep Reinforcement Learning and OpenFOAM

We propose an open-source python platform for applications of Deep Reinforcement Learning (DRL) in fluid mechanics. DRL has been widely used in optimizing decision-making in nonlinear and high-dimensional problems. Here, an agent maximizes a cumulative reward with learning a feedback policy by acting in an environment. In control theory terms, the cumulative reward would correspond to the cost function, the agent to the actuator, the environment to the measured signals and the learned policy to the feedback law. Thus, DRL assumes an interactive environment or, equivalently, control plant. The setup of a numerical simulation plant with DRL is challenging and time-consuming. In this work, a novel python platform, named DRLinFluids is developed for this purpose, with DRL for flow control and optimization problems in fluid mechanics. The simulations employ OpenFOAM as popular, flexible Navier-Stokes solver in industry and academia, and Tensorforce or Tianshou as widely used versatile DRL packages. The reliability and efficiency of DRLinFluids are demonstrated for two wake stabilization benchmark problems. DRLinFluids significantly reduces the application effort of DRL in fluid mechanics and is expected to greatly accelerates academic and industrial applications.

physics.flu-dyn↗

arXiv2021

JIZHI: A Fast and Cost-Effective Model-As-A-Service System for Web-Scale Online Inference at Baidu

In modern internet industries, deep learning based recommender systems have became an indispensable building block for a wide spectrum of applications, such as search engine, news feed, and short video clips. However, it remains challenging to carry the well-trained deep models for online real-time inference serving, with respect to the time-varying web-scale traffics from billions of users, in a cost-effective manner. In this work, we present JIZHI - a Model-as-a-Service system - that per second handles hundreds of millions of online inference requests to huge deep models with more than trillions of sparse parameters, for over twenty real-time recommendation services at Baidu, Inc. In JIZHI, the inference workflow of every recommendation request is transformed to a Staged Event-Driven Pipeline (SEDP), where each node in the pipeline refers to a staged computation or I/O intensive task processor. With traffics of real-time inference requests arrived, each modularized processor can be run in a fully asynchronized way and managed separately. Besides, JIZHI introduces heterogeneous and hierarchical storage to further accelerate the online inference process by reducing unnecessary computations and potential data access latency induced by ultra-sparse model parameters. Moreover, an intelligent resource manager has been deployed to maximize the throughput of JIZHI over the shared infrastructure by searching the optimal resource allocation plan from historical logs and fine-tuning the load shedding policies over intermediate system feedback. Extensive experiments have been done to demonstrate the advantages of JIZHI from the perspectives of end-to-end service latency, system-wide throughput, and resource consumption. JIZHI has helped Baidu saved more than ten million US dollars in hardware and utility costs while handling 200% more traffics without sacrificing inference efficiency.

cs.IR↗

arXiv2021

A Dynamics Perspective of Pursuit-Evasion Games of Intelligent Agents with the Ability to Learn

Pursuit-evasion games are ubiquitous in nature and in an artificial world. In nature, pursuer(s) and evader(s) are intelligent agents that can learn from experience, and dynamics (i.e., Newtonian or Lagrangian) is vital for the pursuer and the evader in some scenarios. To this end, this paper addresses the pursuit-evasion game of intelligent agents from the perspective of dynamics. A bio-inspired dynamics formulation of a pursuit-evasion game and baseline pursuit and evasion strategies are introduced at first. Then, reinforcement learning techniques are used to mimic the ability of intelligent agents to learn from experience. Based on the dynamics formulation and reinforcement learning techniques, the effects of improving both pursuit and evasion strategies based on experience on pursuit-evasion games are investigated at two levels 1) individual runs and 2) ranges of the parameters of pursuit-evasion games. Results of the investigation are consistent with nature observations and the natural law - survival of the fittest. More importantly, with respect to the result of a pursuit-evasion game of agents with baseline strategies, this study achieves a different result. It is shown that, in a pursuit-evasion game with a dynamics formulation, an evader is not able to escape from a slightly faster pursuer with an effective learned pursuit strategy, based on agile maneuvers and an effective learned evasion strategy.

eess.SY↗

arXiv2021

Safe Multi-Agent Reinforcement Learning through Decentralized Multiple Control Barrier Functions

Multi-Agent Reinforcement Learning (MARL) algorithms show amazing performance in simulation in recent years, but placing MARL in real-world applications may suffer safety problems. MARL with centralized shields was proposed and verified in safety games recently. However, centralized shielding approaches can be infeasible in several real-world multi-agent applications that involve non-cooperative agents or communication delay. Thus, we propose to combine MARL with decentralized Control Barrier Function (CBF) shields based on available local information. We establish a safe MARL framework with decentralized multiple CBFs and develop Multi-Agent Deep Deterministic Policy Gradient (MADDPG) to Multi-Agent Deep Deterministic Policy Gradient with decentralized multiple Control Barrier Functions (MADDPG-CBF). Based on a collision-avoidance problem that includes not only cooperative agents but obstacles, we demonstrate the construction of multiple CBFs with safety guarantees in theory. Experiments are conducted and experiment results verify that the proposed safe MARL framework can guarantee the safety of agents included in MARL.

cs.MA↗

arXiv2020

Magnon laser based on Brillouin light scattering

An analogous laser action of magnons would be a subject of interest and is crucial for the study of nonlinear magnons spintronics. Here, we demonstrate the magnon laser behavior based on Brillouin light scattering in a ferrimagnetic insulator sphere which supports optical whispering gallery modes and magnon resonances. We show that the excited magnon plays what has traditionally been the role of the Stokes wave and is coherently amplified during the Brillouin scattering process, making magnon laser possible. Furthermore, the stimulating excited magnon number increasing exponentially with the input light power can be manipulated by adjusting the external magnetic field. In addition to providing insight into magneto-optical interaction, the study of magnon laser action will help to develop novel technologies for handling spin-wave excitations and could affect scientific fields beyond magnonics. Potential applications range from preparing coherent magnon sources to operating onchip functional magnetic devices.

physics.optics↗

arXiv2020

Multi-robot Cooperative Object Transportation using Decentralized Deep Reinforcement Learning

Object transportation could be a challenging problem for a single robot due to the oversize and/or overweight issues. A multi-robot system can take the advantage of increased driving power and more flexible configuration to solve such a problem. However, increased number of individuals also changed the dynamics of the system which makes control of a multi-robot system more complicated. Even worse, if the whole system is sitting on a centralized decision making unit, the data flow could be easily overloaded due to the upscaling of the system. In this research, we propose a decentralized control scheme on a multi-robot system with each individual equipped with a deep Q-network (DQN) controller to perform an oversized object transportation task. DQN is a deep reinforcement learning algorithm thus does not require the knowledge of system dynamics, instead, it enables the robots to learn appropriate control strategies through trial-and-error style interactions within the task environment. Since analogous controllers are distributed on the individuals, the computational bottleneck is avoided systematically. We demonstrate such a system in a scenario of carrying an oversized rod through a doorway by a two-robot team. The presented multi-robot system learns abstract features of the task and cooperative behaviors are observed. The decentralized DQN-style controller is showing strong robustness against uncertainties. In addition, We propose a universal metric to assess the cooperation quantitatively.

cs.RO↗

arXiv2020

Revealing the configurations and host-guest interactions of small aromatics confined in porous frameworks by electron microscopy

Directly imaging the configurations of small molecules at the ambient temperatures will greatly promote the study of their chemical and physical properties, including the host-guest interactions of organics in porous materials during the adsorption, catalysis and energy storage. However, due to the current challenges on the small-molecule imaging by the (scanning) transmission electron microscopy ((S)TEM), we still have a lack of the molecular-level understandings on the host-guest interactions and other molecular behaviors. Here, we achieved the STEM imaging of various small aromatics confined in the MFI-type zeolite frameworks by using the integrated differential phase contrast (iDPC) technique. Due to the strong confinement effect in MFI channels, the 1D solid-like aromatic columns showed the coherent configurations, which were clearly resolved by enhancing the host-guest interactions. Then, we also evaluated the strength of host-guest interactions directly by the image analysis and revealed the desorption behaviors of confined aromatics during the in-situ heating process. These results not only helped us to reveal the configurations and host-guest interactions of small aromatics during the adsorption/desorption in porous materials, but also expanded the applications of STEM to further study other molecular behaviors in the real space.

cond-mat.mtrl-sci↗

arXiv2020

DGL-KE: Training Knowledge Graph Embeddings at Scale

Knowledge graphs have emerged as a key abstraction for organizing information in diverse domains and their embeddings are increasingly used to harness their information in various information retrieval and machine learning tasks. However, the ever growing size of knowledge graphs requires computationally efficient algorithms capable of scaling to graphs with millions of nodes and billions of edges. This paper presents DGL-KE, an open-source package to efficiently compute knowledge graph embeddings. DGL-KE introduces various novel optimizations that accelerate training on knowledge graphs with millions of nodes and billions of edges using multi-processing, multi-GPU, and distributed parallelism. These optimizations are designed to increase data locality, reduce communication overhead, overlap computations with memory accesses, and achieve high operation efficiency. Experiments on knowledge graphs consisting of over 86M nodes and 338M edges show that DGL-KE can compute embeddings in 100 minutes on an EC2 instance with 8 GPUs and 30 minutes on an EC2 cluster with 4 machines with 48 cores/machine. These results represent a 2x~5x speedup over the best competing approaches. DGL-KE is available on https://github.com/awslabs/dgl-ke.

cs.DC↗

arXiv2020

Real-Space Imaging of the Ordered Small Molecule Orientations in Porous Frameworks by Electron Microscopy

The real-space imaging of small molecules is always challenging under the electron microscopes, but highly demanded for investigating various nanoscale interactions, such as hydrogen bond and van der Waals (vdW) force. Especially, identifying the host-guest interactions in porous materials directly at the molecular level will bring a deeper insight into the behaviors of guest molecules during the sorption, catalysis, gas separation and energy storage. In this work, we directly resolved the ordered configurations of p-xylenes (PXs) adsorbed in ZSM-5 frameworks by the scanning transmission electron microscopy (STEM) with the integrated differential phase contrast (iDPC) technique to identify the host-guest vdW interactions. Based on these observations, we revealed that the PXs in one straight channel modified the channel geometry with a coherent orientation. And the adjacent straight channels were deformed up to 8.8% along the different directions corresponding to three dominant PX configurations, resulting a negligible overall expansion of ZSM-5 lattices. Then, we could also image the disorder and desorption of PXs in ZSM-5 channels during the in situ heating. This work not only helped us to study the host-guest vdW interactions and the sorption behaviors of PXs in ZSM-5, but also provided an efficient tool for further imaging and studying other single-molecule behaviors under STEMs.

cond-mat.mtrl-sci↗

arXiv2019

Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding

Speech-to-text translation (ST), which translates source language speech into target language text, has attracted intensive attention in recent years. Compared to the traditional pipeline system, the end-to-end ST model has potential benefits of lower latency, smaller model size, and less error propagation. However, it is notoriously difficult to implement such a model without transcriptions as intermediate. Existing works generally apply multi-task learning to improve translation quality by jointly training end-to-end ST along with automatic speech recognition (ASR). However, different tasks in this method cannot utilize information from each other, which limits the improvement. Other works propose a two-stage model where the second model can use the hidden state from the first one, but its cascade manner greatly affects the efficiency of training and inference process. In this paper, we propose a novel interactive attention mechanism which enables ASR and ST to perform synchronously and interactively in a single model. Specifically, the generation of transcriptions and translations not only relies on its previous outputs but also the outputs predicted in the other task. Experiments on TED speech translation corpora have shown that our proposed model can outperform strong baselines on the quality of speech translation and achieve better speech recognition performances as well.

cs.CL↗

arXiv2019

Magnon Blockade in a Hybrid Ferromagnet-Superconductor Quantum System

The implementation of a single magnon level quantum manipulation is one of the fundamental targets in quantum magnetism with a significant practical relevance for precision metrology, quantum information processing, and quantum simulation. Here, we demonstrate theoretically the feasibility of using a hybrid ferromagnet-superconductor quantum system to prepare a single magnon source based on magnon blockade effects. By numerically solving the quantum master equation, we show that the second-order correlation function of the magnon mode depends crucially on the relation between the qubit-magnon coupling strength and the driving detuning, and simultaneously signatures of the magnon blockade appear only under quite stringent conditions of a cryogenic temperature. In addition to providing perception into the quantum phenomena of magnon, the study of magnon blockade effects will help to develop novel technologies for exploring the undiscovered magnon traits at the quantum level and may find applications in designing single magnon emitters.

quant-ph↗

arXiv2019

Multiple Sclerosis Lesion Inpainting Using Non-Local Partial Convolutions

Multiple sclerosis (MS) is an inflammatory demyelinating disease of the central nervous system (CNS) that results in focal injury to the grey and white matter. The presence of white matter lesions biases morphometric analyses such as registration, individual longitudinal measurements and tissue segmentation for brain volume measurements. Lesion-inpainting with intensities derived from surrounding healthy tissue represents one approach to alleviate such problems. However, existing methods inpaint lesions based on texture information derived from local surrounding tissue, often leading to inconsistent inpainting and the generation of artifacts such as intensity discrepancy and blurriness. Based on these observations, we propose non-local partial convolutions (NLPC) that integrates a Unet-like network with the non-local module. The non-local module is exploited to capture long range dependencies between the lesion area and remaining normal-appearing brain regions. Then, the lesion area is filled by referring to normal-appearing regions with more similar features. This method generates inpainted regions that appear more realistic and natural. Our quantitative experimental results also demonstrate superiority of this technique of existing state-of-the-art inpainting methods.

cs.CV↗

arXiv2019

Multi-agent Learning for Neural Machine Translation

Conventional Neural Machine Translation (NMT) models benefit from the training with an additional agent, e.g., dual learning, and bidirectional decoding with one agent decoding from left to right and the other decoding in the opposite direction. In this paper, we extend the training framework to the multi-agent scenario by introducing diverse agents in an interactive updating process. At training time, each agent learns advanced knowledge from others, and they work together to improve translation quality. Experimental results on NIST Chinese-English, IWSLT 2014 German-English, WMT 2014 English-German and large-scale Chinese-English translation tasks indicate that our approach achieves absolute improvements over the strong baseline systems and shows competitive performance on all tasks.

cs.CL↗

arXiv2019

DuTongChuan: Context-aware Translation Model for Simultaneous Interpreting

In this paper, we present DuTongChuan, a novel context-aware translation model for simultaneous interpreting. This model allows to constantly read streaming text from the Automatic Speech Recognition (ASR) model and simultaneously determine the boundaries of Information Units (IUs) one after another. The detected IU is then translated into a fluent translation with two simple yet effective decoding strategies: partial decoding and context-aware decoding. In practice, by controlling the granularity of IUs and the size of the context, we can get a good trade-off between latency and translation quality easily. Elaborate evaluation from human translators reveals that our system achieves promising translation quality (85.71% for Chinese-English, and 86.36% for English-Chinese), specially in the sense of surprisingly good discourse coherence. According to an End-to-End (speech-to-speech simultaneous interpreting) evaluation, this model presents impressive performance in reducing latency (to less than 3 seconds at most times). Furthermore, we successfully deploy this model in a variety of Baidu's products which have hundreds of millions of users, and we release it as a service in our AI platform.

cs.CL↗

arXiv2019

STACL: Simultaneous Translation with Implicit Anticipation and Controllable Latency using Prefix-to-Prefix Framework

Simultaneous translation, which translates sentences before they are finished, is useful in many scenarios but is notoriously difficult due to word-order differences. While the conventional seq-to-seq framework is only suitable for full-sentence translation, we propose a novel prefix-to-prefix framework for simultaneous translation that implicitly learns to anticipate in a single translation model. Within this framework, we present a very simple yet surprisingly effective wait-k policy trained to generate the target sentence concurrently with the source sentence, but always k words behind. Experiments show our strategy achieves low latency and reasonable quality (compared to full-sentence translation) on 4 directions: zh<->en and de<->en.

cs.CL↗