← Search

Xuefeng Chen

7 accepted papers

2026

GaussianDWM: 3D Gaussian Driving World Model for Unified Scene Understanding and Multi-Modal Generation

CVPR 2026

Driving World Models (DWMs) have been developing rapidly with the advances of generative models. However, existing DWMs lack 3D scene understanding capabilities and can only generate content conditioned on input data, without the ability to interpret or reason about the driving environment. Moreover

Cited by 0SourcecodeScholar
2026

K-Track: A Kirigami-Inspired Tracked Robot With Negative Pressure Co-operative Adhesion for Wall-to-Wall Transition

RA-L 2026

This letter presents a novel wall-climbing robot design that combines kirigami-inspired adhesive tracks with negative pressure absorption, enabling reliable wall-to-wall transitions in complex environments. The kirigami-inspired tracks demonstrate a significant enhancement in adhesion performance, a

Cited by 0SourceScholar
2025

Bioinspired Microrobot Climbing on Fabrics Using a Single Actuator

RA-L 2025

Microrobots climbing on fabrics are well-suited for reconnaissance and rescue tasks in indoor environments. However, achieving stable adhesion while maintaining a simplified locomotion mechanism remains a formidable challenge. This study presents a 4cm, 18.2g climbing robot designed with a single-ac

Cited by 1SourceScholar
2025

Learning Upright and Forward-Facing Object Poses using Category-level Canonical Representations

IROS 2025

Constructing a unified canonical pose representation for 3D object categories is crucial for pose estimation and robotic scene understanding. Previous unified pose representations often relied on manual alignment, such as in ShapeNet and ModelNet. Recently, self-supervised canonicalization methods h

Cited by 0SourcecodeScholar
2024

Rigid-Soft Hybrid Suction Cups for Enhanced Anti-Torque and Energy-Efficient Attachment

RA-L 2024

In the realm of robotics, suction-based adhesion plays a pivotal role in applications ranging from object transfer to wall-climbing robots. To improve the sealing and attachment stability of suction cups, researchers have employed state-of-the-art techniques, including the use of soft materials with

Cited by 3SourceScholar