Xiaoqian Chen

Papers

Total Citations

H-Index

About

Xiaoqian Chen is a pioneering researcher in the intersection of 3D perception and robotic manipulation, with a focus on adversarial machine learning and flexible robotics. Her most impactful work, "Gradient-based sparse voxel attacks on point cloud object detection" (2024, 11 citations), introduces a novel method for generating sparse, gradient-guided perturbations in voxelized point clouds, exposing critical vulnerabilities in LiDAR-based perception systems used in autonomous driving and robotics. This contribution has significant implications for developing robust 3D object detectors, earning her recognition in the security and computer vision communities. Chen also explores the frontier of bio-inspired robotics with her 2025 study on visual control of a cable-driven flexible robotic arm with a spinal structure, leveraging video understanding to achieve dexterous, adaptive manipulation. This work bridges perception and control, demonstrating how real-time visual feedback can guide complex, flexible mechanisms. Her research not only advances foundational understanding of adversarial robustness in 3D data but also pushes the boundaries of soft robotics, making her a rising figure in both fields.