A5078491548- Autonomous Vehicle Technology and Safety
- Antenna Design and Analysis
- Metamaterials and Metasurfaces Applications
- Advanced Antenna and Metasurface Technologies
- Traffic Prediction and Management Techniques
- Older Adults Driving Studies
- Advanced Neural Network Applications
- Human-Automation Interaction and Safety
- EEG and Brain-Computer Interfaces
- Traffic control and management
- Innovations in Concrete and Construction Materials
- BIM and Construction Integration
- Traffic and Road Safety
- Modular Robots and Swarm Intelligence
- Advanced Memory and Neural Computing
- Gear and Bearing Dynamics Analysis
- Vehicle emissions and performance
- Tribology and Lubrication Engineering
- Adhesion, Friction, and Surface Interactions
- Microwave Engineering and Waveguides
- Transportation Systems and Logistics
- Neural Networks and Reservoir Computing
- Nonlinear Dynamics and Pattern Formation
- Wireless Communication Security Techniques
- Explainable Artificial Intelligence (XAI)
Aerospace Information Research Institute
2021-2025
Chinese Academy of Sciences
2021-2025
City University of Macau
2024
University of Macau
2024
State Key Laboratory of Transducer Technology
2021
China University of Petroleum, East China
2018
Space-time-coding digital metasurface has drawn worldwide attention with the ability to improve communication quality and change direction of electromagnetic (EM) wave propagation in real-time. This article proposes a deep learning-assisted method design space-time-coding element (STCDME) state recognition mapping technique methods. Compared traditional pure EM simulation methods simulate all states, proposed fully considers relationship between different states STCDME accelerate design....
ABSTRACT In this paper, an improved W‐band bandpass filter for the synthetic aperture radar (SAR) system with a center frequency of 96 GHz is designed and implemented. Compared conventional rectangular waveguide resonator filters, two specially oversized cavities are combined in structure to create transmission zeros (TZs), which improves sharp cutoff rate remains simplicity structure. Meanwhile, position each TZ independently controlled by dimensions one specific resonator, makes it easier...
Accurate trajectory prediction is essential for the safety and efficiency of autonomous driving. Traditional models often struggle with real-time processing, capturing non-linearity uncertainty in traffic environments, dense traffic, modeling temporal dynamics interactions. We introduce NEST (Neuromodulated Small-world Hypergraph Trajectory Prediction), a novel framework that integrates Networks hypergraphs superior interaction accuracy. This integration enables capture both local extended...
Deep learning plays a vital role in the design of electromagnetic (EM) structures. However, current research, single neural network typically supports only one structure and requires complex framework to accommodate multiple designs. This paper proposes using neural-assist for facilitating EM We employ two filling methods control vector length, an identification method ensure accurate prediction results, random auxiliary vectors increase data volume reduce loss. Subsequently, we forward...
This paper introduces a trajectory prediction model tailored for autonomous driving, focusing on capturing complex interactions in dynamic traffic scenarios without reliance high-definition maps. The model, termed MFTraj, harnesses historical data combined with novel geometric graph-based behavior-aware module. At its core, an adaptive structure-aware interactive graph convolutional network captures both positional and behavioral features of road users, preserving spatial-temporal...
In recent years, jamming strategies for Synthetic Aperture Radar (SAR) pertaining to target detection and identification, such as the creation of false targets, electromagnetic (EM) deception, signal spoofing, have been increasingly emphasized. Distinct from traditional SAR approaches, introduction an innovative artificial material cloak in presents augmented capabilities. These methods demonstrate a proficient redirection incident EM waves specific or arbitrary directions, effectively...
Abstract Reservoir computing (RC) is a recently introduced bio-inspired computational framework capable of excellent performances in the temporal data processing, owing to its derivation from recurrent neural network (RNN). It well-known for fast and effective training scheme, as well ease hardware implementation, but also problematic sensitivity performance optimizable architecture parameters. In this article, particular time-delayed RC with single clamped–clamped silicon beam resonator...
Accurately and safely predicting the trajectories of surrounding vehicles is essential for fully realizing autonomous driving (AD). This paper presents Human-Like Trajectory Prediction model (HLTP++), which emulates human cognitive processes to improve trajectory prediction in AD. HLTP++ incorporates a novel teacher-student knowledge distillation framework. The "teacher" equipped with an adaptive visual sector, mimics dynamic allocation attention drivers exhibit based on factors like spatial...
Recent advancements in autonomous driving have seen a paradigm shift towards end-to-end learning paradigms, which map sensory inputs directly to actions, thereby enhancing the robustness and adaptability of vehicles. However, these models often sacrifice interpretability, posing significant challenges trust, safety, regulatory compliance. To address issues, we introduce DRIVE -- Dependable Robust Interpretable Visionary Ensemble Framework Autonomous Driving, comprehensive framework designed...
Accurate trajectory prediction is essential for the safety and efficiency of autonomous driving. Traditional models often struggle with real-time processing, capturing non-linearity uncertainty in traffic environments, dense traffic, modeling temporal dynamics interactions. We introduce NEST (Neuromodulated Small-world Hypergraph Trajectory Prediction), a novel framework that integrates Networks hypergraphs superior interaction accuracy. This integration enables capture both local extended...
A three degree of freedom model spiral groove liquid lubricated seal was established for studying the effects centrifugal inertia on dynamic characteristics. The stiffness and damping coefficients with those without were obtained by means finite element method, then comparative analysis carried out. Results indicate that are increased linearly increase rotating speed. Dynamic decrease increasing film thickness. axial coefficient angular coupling can be neglected under different speed When...
This paper presents a low-profile broadband dual circularly polarized antenna with flexible configuration of peripheral metasurface to implement diversified functions, for example, reduction radar cross section (RCS). The core based on the theory characteristic mode consists <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$3\times 3$</tex> modified subwavelength square metal patches as well an inductive microstrip side feed structure overall low...