Ruisong Pei

Papers

Total Citations

H-Index

About

Ruisong Pei is a robotics researcher advancing intelligent grasping systems for real-world applications, with a focus on multi-modal perception and generative architectures. His work centers on two key challenges: effectively fusing RGB and depth data for robotic manipulation, and developing efficient grasping models for complex environments like automated waste sorting. Pei’s most influential work, “MCS-ResNet: A Generative Robot Grasping Network Based on RGB-D Fusion” (2024, 9 citations), addresses a critical limitation in grasp detection—the underutilization of distinct information from RGB and depth modalities. By proposing a novel fusion architecture, his method significantly improves grasp success rates in cluttered scenes. Building on this, his 2025 paper “An Efficient Generative Intelligent Multiobjective Grasping Model for Kitchen Waste Sorting” (5 citations) tackles the practical challenge of automating waste sorting on conveyor belts, where data scarcity and algorithmic inefficiency have hindered adoption of generative approaches. Pei’s contributions are notable for bridging the gap between theoretical generative models and real-world robotic deployment, particularly in unstructured environments. His work demonstrates how multi-objective optimization and cross-modal learning can make robotic grasping both more robust and more practical for industrial and domestic applications.