arXiv subjects

Zijie Zheng

Publications and source records attributed to Zijie Zheng.

15 recordsLinked to original sources

arXiv2025

Demonstrating DVS: Dynamic Virtual-Real Simulation Platform for Mobile Robotic Tasks

With the development of embodied artificial intelligence, robotic research has increasingly focused on complex tasks. Existing simulation platforms, however, are often limited to idealized environments, simple task scenarios and lack data interoperability. This restricts task decomposition and multi-task learning. Additionally, current simulation platforms face challenges in dynamic pedestrian modeling, scene editability, and synchronization between virtual and real assets. These limitations hinder real world robot deployment and feedback. To address these challenges, we propose DVS (Dynamic Virtual-Real Simulation Platform), a platform for dynamic virtual-real synchronization in mobile robotic tasks. DVS integrates a random pedestrian behavior modeling plugin and large-scale, customizable indoor scenes for generating annotated training datasets. It features an optical motion capture system, synchronizing object poses and coordinates between virtual and real world to support dynamic task benchmarking. Experimental validation shows that DVS supports tasks such as pedestrian trajectory prediction, robot path planning, and robotic arm grasping, with potential for both simulation and real world deployment. In this way, DVS represents more than just a versatile robotic platform; it paves the way for research in human intervention in robot execution tasks and real-time feedback algorithms in virtual-real fusion environments. More information about the simulation platform is available on https://immvlab.github.io/DVS/.

cs.RO↗

arXiv2025

VM-BHINet:Vision Mamba Bimanual Hand Interaction Network for 3D Interacting Hand Mesh Recovery From a Single RGB Image

Understanding bimanual hand interactions is essential for realistic 3D pose and shape reconstruction. However, existing methods struggle with occlusions, ambiguous appearances, and computational inefficiencies. To address these challenges, we propose Vision Mamba Bimanual Hand Interaction Network (VM-BHINet), introducing state space models (SSMs) into hand reconstruction to enhance interaction modeling while improving computational efficiency. The core component, Vision Mamba Interaction Feature Extraction Block (VM-IFEBlock), combines SSMs with local and global feature operations, enabling deep understanding of hand interactions. Experiments on the InterHand2.6M dataset show that VM-BHINet reduces Mean per-joint position error (MPJPE) and Mean per-vertex position error (MPVPE) by 2-3%, significantly surpassing state-of-the-art methods.

cs.CV↗

arXiv2024

THUD++: Large-Scale Dynamic Indoor Scene Dataset and Benchmark for Mobile Robots

Most existing mobile robotic datasets primarily capture static scenes, limiting their utility for evaluating robotic performance in dynamic environments. To address this, we present a mobile robot oriented large-scale indoor dataset, denoted as THUD++ (TsingHua University Dynamic) robotic dataset, for dynamic scene understanding. Our current dataset includes 13 large-scale dynamic scenarios, combining both real-world and synthetic data collected with a real robot platform and a physical simulation platform, respectively. The RGB-D dataset comprises over 90K image frames, 20M 2D/3D bounding boxes of static and dynamic objects, camera poses, and IMU. The trajectory dataset covers over 6,000 pedestrian trajectories in indoor scenes. Additionally, the dataset is augmented with a Unity3D-based simulation platform, allowing researchers to create custom scenes and test algorithms in a controlled environment. We evaluate state-of-the-art methods on THUD++ across mainstream indoor scene understanding tasks, e.g., 3D object detection, semantic segmentation, relocalization, pedestrian trajectory prediction, and navigation. Our experiments highlight the challenges mobile robots encounter in indoor environments, especially when navigating in complex, crowded, and dynamic scenes. By sharing this dataset, we aim to accelerate the development and testing of mobile robot algorithms, contributing to real-world robotic applications.

cs.RO↗

arXiv2023

Eliminating Leakage in Volatile Memory with Anti-Ferroelectric Transistors

Cache serves as a temporary data memory module in many general-purpose processors and domain-specific accelerators. Its density, power, speed, and reliability play a critical role in enhancing the overall system performance and quality of service. Conventional volatile memories, including static random-access memory (SRAM) and embedded dynamic random-access memory (eDRAM) in the complementary metal-oxide-semiconductor technology, have high performance and good reliability. However, the inherent leakage in both SRAM and eDRAM hinders further improvement towards smaller feature sizes and higher energy efficiency. Although the emerging nonvolatile memories can eliminate the leakage efficiently, the penalties of lower speed and degraded reliability are significant. This article reveals a new opportunity towards leakage-free volatile static memory beyond the known paradigms of existing volatile and nonvolatile memories. By engineering a double-well energy landscape with the assistance of a clamping voltage bias, leakage-free and refresh-free state retention of volatile memory is achieved for the first time. This new memory is highlighted by both the ultra-low leakage of nonvolatile memories and the speed, energy, and reliability advantages of volatile memories. A proof-of-concept memory is demonstrated using in-house anti-ferroelectric field-effect transistors (AFeFETs), delivering an extrapolated endurance of about 1012 cycles, a retention time of over 10 years, and no subthreshold channel leakage current. Such a new concept of AFeFET-based memory enables an improved balance between density, power, and reliability beyond all existing memory solutions.

cs.ET↗

arXiv2022

Computational Associative Memory with Amorphous InGaZnO Channel 3D NAND-Compatible FG Transistors

3D NAND enables continuous NAND density and cost scaling beyond conventional 2D NAND. However, its poly-Si channel suffers from low mobility, large device variations, and instability caused by grain boundaries. Here, we overcome these drawbacks by introducing an amorphous indium-gallium-zinc-oxide (a-IGZO) channel, which has the advantages of ultra-low OFF current, back-end-of-line compatibility, higher mobility and better uniformity than poly-Si, and free of grain boundaries due to the amorphous nature. Ultra-scaled floating-gate (FG) transistors with a channel length of 60 nm are reported, achieving the highest ON current of 127 uA/um among all reported a-IGZO-based flash devices for high-density, low-power, and high-performance 3D NAND applications. Furthermore, a non-volatile and area-efficient ternary content-addressable memory (TCAM) with only two a-IGZO FG transistors is experimentally demonstrated. Array-level simulations using experimentally calibrated models show that this design achieves at least 240x array-size scalability and 2.7-fold reduction in search energy than 16T-CMOS, 2T2R, and 2FeFET TCAMs.

cond-mat.mes-hall↗

arXiv2022

End-to-End Rubbing Restoration Using Generative Adversarial Networks

Rubbing restorations are significant for preserving world cultural history. In this paper, we propose the RubbingGAN model for restoring incomplete rubbing characters. Specifically, we collect characters from the Zhang Menglong Bei and build up the first rubbing restoration dataset. We design the first generative adversarial network for rubbing restoration. Based on the dataset we collect, we apply the RubbingGAN to learn the Zhang Menglong Bei font style and restore the characters. The results of experiments show that RubbingGAN can repair both slightly and severely incomplete rubbing characters fast and effectively.

cs.CV↗

arXiv2022

A Novel Non-Volatile Inverter-based CiM: Continuous Sign Weight Transition and Low Power on-Chip Training

In this work, we report a novel design, one-transistor-one-inverter (1T1I), to satisfy high speed and low power on-chip training requirements. By leveraging doped HfO2 with ferroelectricity, a non-volatile inverter is successfully demonstrated, enabling desired continuous weight transition between negative and positive via the programmable threshold voltage (VTH) of ferroelectric field-effect transistors (FeFETs). Compared with commonly used designs with the similar function, 1T1I uniquely achieves pure on-chip-based weight transition at an optimized working current without relying on assistance from off-chip calculation units for signed-weight comparison, facilitating high-speed training at low power consumption. Further improvements in linearity and training speed can be obtained via a two-transistor-one-inverter (2T1I) design. Overall, focusing on energy and time efficiencies, this work provides a valuable design strategy for future FeFET-based computing-in-memory (CiM).

cond-mat.mes-hall↗

arXiv2019

HetMEC: Latency-optimal Task Assignment and Resource Allocation for Heterogeneous Mobile Edge Computing

Driven by great demands on low-latency services of the edge devices (EDs), mobile edge computing (MEC) has been proposed to enable the computing capacities at the edge of the radio access network. However, conventional MEC servers suffer disadvantages such as limited computing capacity, preventing the computation-intensive tasks to be processed in time. To relief this issue, we propose the heterogeneous MEC (HetMEC) where the data that cannot be timely processed at the edge are allowed be offloaded to the upper-layer MEC servers, and finally to the cloud center (CC) with more powerful computing capacity. We design the latency minimization algorithm by jointly coordinating the task assignment, computing and transmission resources among the EDs, multi-layer MEC servers, and the CC. Simulation results indicate that our proposed algorithm can achieve a lower latency and higher processing rate than the conventional MEC scheme.

eess.SP↗

arXiv2018

UAV Aided Aerial-Ground IoT for Air Quality Sensing in Smart City: Architecture, Technologies and Implementation

As air pollution is becoming the largest environmental health risk, the monitoring of air quality has drawn much attention in both theoretical studies and practical implementations. In this article, we present a real-time, fine-grained and power-efficient air quality monitoring system based on aerial and ground sensing. The architecture of this system consists of four layers: the sensing layer to collect data, the transmission layer to enable bidirectional communications, the processing layer to analyze and process the data, and the presentation layer to provide graphic interface for users. Three major techniques are investigated in our implementation, given by the data processing, the deployment strategy and the power control. For data processing, spacial fitting and short-term prediction are performed to eliminate the influences of the incomplete measurement and the latency of data uploading. The deployment strategies of ground sensing and aerial sensing are investigated to improve the quality of the collected data. The power control is further considered to balance between power consumption and data accuracy. Our implementation has been deployed in Peking University and Xidian University since February 2018, and has collected about 100 thousand effective data samples by June 2018.

cs.OH↗

arXiv2018

EdgeFlow: Open-Source Multi-layer Data Flow Processing in Edge Computing for 5G and Beyond

Edge computing has evolved to be a promising avenue to enhance the system computing capability by offloading processing tasks from the cloud to edge devices. In this paper, we propose a multi-layer edge computing framework called EdgeFlow. In this framework, different nodes ranging from edge devices to cloud data centers are categorized into corresponding layers and cooperate together for data processing. With the help of EdgeFlow, one can balance the trade-off between computing and communication capability so that the tasks are assigned to each layer optimally. At the same time, resources are carefully allocated throughout the whole network to mitigate performance fluctuation. The proposed open-source data flow processing framework is implemented on a platform that can emulate various computing nodes in multiple layers and corresponding network connections. Evaluated on the face recognition scenario, EdgeFlow can significantly reduce task finish time and perform more tolerance to run-time variation, compared with the pure cloud computing, the pure edge computing and Cloudlet. Potential applications of EdgeFlow, including network function visualization, Internet of Things, and vehicular networks, are also discussed in the end of this work.

cs.NI↗

arXiv2018

UAV Offloading: Spectrum Trading Contract Design for UAV Assisted 5G Networks

Unmanned Aerial Vehicle (UAV) has been recognized as a promising way to assist future wireless communications due to its high flexibility of deployment and scheduling. In this paper, we focus on temporarily deployed UAVs that provide downlink data offloading in some regions under a macro base station (MBS). Since the manager of the MBS and the operators of the UAVs could be of different interest groups, we formulate the corresponding spectrum trading problem by means of contract theory, where the manager of the MBS has to design an optimal contract to maximize its own revenue. Such contract comprises a set of bandwidth options and corresponding prices, and each UAV operator only chooses the most profitable one from all the options in the whole contract. We analytically derive the optimal pricing strategy based on fixed bandwidth assignment, and then propose a dynamic programming algorithm to calculate the optimal bandwidth assignment in polynomial time. By simulations, we compare the outcome of the MBS optimal contract with that of a social optimal one, and find that a selfish MBS manager sells less bandwidth to the UAV operators.

eess.SP↗

arXiv2017

Realtime Profiling of Fine-Grained Air Quality Index Distribution using UAV Sensing

Given significant air pollution problems, air quality index (AQI) monitoring has recently received increasing attention. In this paper, we design a mobile AQI monitoring system boarded on unmanned-aerial-vehicles (UAVs), called ARMS, to efficiently build fine-grained AQI maps in realtime. Specifically, we first propose the Gaussian plume model on basis of the neural network (GPM-NN), to physically characterize the particle dispersion in the air. Based on GPM-NN, we propose a battery efficient and adaptive monitoring algorithm to monitor AQI at the selected locations and construct an accurate AQI map with the sensed data. The proposed adaptive monitoring algorithm is evaluated in two typical scenarios, a two-dimensional open space like a roadside park, and a three-dimensional space like a courtyard inside a building. Experimental results demonstrate that our system can provide higher prediction accuracy of AQI with GPM-NN than other existing models, while greatly reducing the power consumption with the adaptive monitoring algorithm.

eess.SP↗

arXiv2017

Game Theoretic Approaches to Massive Data Processing in Wireless Networks

Wireless communication networks are becoming highly virtualized with two-layer hierarchies, in which controllers at the upper layer with tasks to achieve can ask a large number of agents at the lower layer to help realize computation, storage, and transmission functions. Through offloading data processing to the agents, the controllers can accomplish otherwise prohibitive big data processing. Incentive mechanisms are needed for the agents to perform the controllers' tasks in order to satisfy the corresponding objectives of controllers and agents. In this article, a hierarchical game framework with fast convergence and scalability is proposed to meet the demand for real-time processing for such situations. Possible future research directions in this emerging area are also discussed.

cs.DC↗

arXiv2016

Resource Allocation in Wireless Powered Relay Networks: A Bargaining Game Approach

Simultaneously information and power transfer in mobile relay networks have recently emerged, where the relay can harvest the radio frequency (RF) energy and then use this energy for data forwarding and system operation. Most of the previous works do not consider that the relay may have its own objectives, such as using the harvested energy for its own transmission instead of maximizing transmission of the network. Therefore, in this paper, we propose a Nash bargaining approach to balance the information transmission efficiency of source-destination pairs and the harvested energy of the relay in a wireless powered relay network with multiple source-destination pairs and one relay. We analyze and prove that the Nash bargaining problem has several desirable properties such as the discreteness and quasi-concavity, when it is decomposed into three sub-problems: the energy transmission power optimization, the power control for data transmission and the time division between energy transmission and data transmission. Based on the theoretical analysis, we propose an alternating power control and time division algorithm to find a suboptimal solution. Simulation results clearly show and demonstrate the properties of the problem and the convergence of our algorithm.

cs.IT↗

arXiv2016

Caching as a Service: Small-cell Caching Mechanism Design for Service Providers

Wireless network virtualization has been well recognized as a way to improve the flexibility of wireless networks by decoupling the functionality of the system and implementing infrastructure and spectrum as services. Recent studies have shown that caching provides a better performance to serve the content requests from mobile users. In this paper, we propose that \emph{caching can be applied as a service} in mobile networks, i.e., different service providers (SPs) cache their contents in the storages of wireless facilities that owned by mobile network operators (MNOs). Specifically, we focus on the scenario of \emph{small-cell networks}, where cache-enabled small-cell base stations (SBSs) are the facilities to cache contents. To deal with the competition for storages among multiple SPs, we design a mechanism based on multi-object auctions, where the time-dependent feature of system parameters and the frequency of content replacement are both taken into account. Simulation results show that our solution leads to a satisfactory outcome.

cs.GT↗