Guyue Zhou

xTED: Cross-Domain Adaptation via Diffusion-Based Trajectory Editing

Haoyi Niu, Q. Chen, Jianxiong Li, Guyue Zhou et autres

Reusing cross-domain data is vital for decision-making tasks with limited target data, yet existing methods often rely on complex, inflexible model-level designs. To address this, we propose the Cross-Domain Trajectory EDiting (xTED) framework, which bridges domain gaps directly at the data level. …

cn (code pays fourni par la source)

Small-bore gradient coil design with plate-rolling error correction for use in micro-MRI

Guyue Zhou, Yaohui Wang, Wenchen Wang, Wenhui Yang et autres

cn, au (code pays fourni par la source)

Design of Superconducting Shim Coils for Extremely-High-Field NMR Magnets Using Bi-2212 Wires

Haotian Miao, Guyue Zhou, H G Chen, Xiaowei Song et autres

cn, au (code pays fourni par la source)

Comparison of Passive Shimming Strategies: Overall versus Odd-Even Shim Tray Operation in a 3T Animal MRI Superconducting Magnet

Haotian Miao, Wenchen Wang, Guyue Zhou, Shunzhong Chen et autres

The image quality and spectral accuracy of magnetic resonance imaging (MRI) are highly dependent on the homogeneity of the static magnetic field (B0). In compact 3 T animal MRI systems, susceptibility effects and geometric constraints tend to amplify magnetic field distortions, making …

cn, au (code pays fourni par la source)

High-Performance Electromagnetic Shielding Structure for a Compact 7T Cryogen-Free MRI System

Guyue Zhou, Yaohui Wang, You Song

cn (code pays fourni par la source)

An EEG dataset for understanding driving expertise from naturalistic urban road experiments

Jiangtao Gong, Yueteng Yu, Yancheng Cao, Ruoxuan Yang et autres

Modern autonomous driving algorithms in complex urban environments strive for safety, comfort, and intelligence, qualities exemplified by expert drivers. This paper presents a comprehensive EEG dataset comparing 10 expert and 10 novice drivers in 13 naturalistic urban driving conditions on a fixed …

cn, au, hk (code pays fourni par la source)

A 26-Gram Butterfly-Inspired Robot Achieving Autonomous Tailless Flight

Weibin Gu, Chenrui Feng, Lian Liu, Chen Yang et autres

cn, it, uz (code pays fourni par la source)

Actively shielded gradient coil design for an all-superconducting planar MRI system using progressively-enhanced shielding constraints

Yiqing Yin, Wenchen Wang, Guyue Zhou, Haotian Miao et autres

cn, au (code pays fourni par la source)

A 26-Gram Tailless Butterfly-Inspired Flapping-Wing Robot with Onboard Attitude Control

Weibin Gu, Chenrui Feng, Lian Liu, Chen Yang et autres

Butterfly-inspired flapping-wing robots use broad compliant wings and low-frequency actuation, but pronounced wingbeat-synchronous body dynamics and time-varying inertia complicate onboard control. Here, we introduce AirPulse, a 26 g two-winged tailless flapping-wing robot with integrated venation-inspired wings, sensing, computation, and power, representing the …

A 26-Gram Tailless Butterfly-Inspired Flapping-Wing Robot with Onboard Attitude Control

Weibin Gu, Chenrui Feng, Lian Liu, Chen Yang et autres

Butterfly-inspired flapping-wing robots use broad compliant wings and low-frequency actuation, but pronounced wingbeat-synchronous body dynamics and time-varying inertia complicate onboard control. Here, we introduce AirPulse, a 26 g two-winged tailless flapping-wing robot with integrated venation-inspired wings, sensing, computation, and power, representing the …

TopoDiffuser: A Diffusion-Based Multimodal Trajectory Prediction Model with Topometric Maps

Zehui Xu, Junhui Wang, Yongliang Shi, Chong Gao et autres

This paper introduces TopoDiffuser, a diffusion-based framework for multimodal trajectory prediction that incorporates topometric maps to generate accurate, diverse, and road-compliant future motion forecasts. By embedding structural cues from topometric maps into the denoising process of a conditional diffusion model, the proposed …

cn (code pays fourni par la source)

DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments

Yufei Jia, Guangyu Wang, Yuhang Dong, Jinfu Wu et autres

We present Discoverse, the first unified, modular, open-source 3DGS-based simulation framework for Real2Sim2Real robot learning. It features a holistic Real2Sim pipeline that synthesizes hyper-realistic geometry and appearance of complex real-world scenarios, paving the way for analyzing and bridging the Sim2Real gap. Powered …

cn, us (code pays fourni par la source)