Manman Xu

Papers

Total Citations

H-Index

About

Manman Xu is a researcher advancing the field of computer vision and robotics, with a primary focus on instance segmentation and deep learning architectures for autonomous systems. Their most notable contribution is the development of an end-to-end instance segmentation method that enhances the efficiency of indoor mobile robots in locating and segmenting environmental instances. By integrating the powerful ConvNeXt V2 as the backbone network of the RTMDet-based model, Xu significantly improved the performance of existing segmentation approaches, enabling more accurate and robust real-time scene understanding. This work, published in 2024, has already garnered 2 citations, reflecting its emerging impact in the robotics and computer vision communities. Xu's research addresses critical challenges in autonomous navigation and environmental perception, bridging the gap between advanced neural network design and practical robotic applications. Their methodological innovations in backbone network selection and model optimization demonstrate a keen ability to translate state-of-the-art deep learning techniques into tangible improvements for embodied AI systems. As the field of indoor robotics continues to evolve, Xu's contributions provide a foundation for more reliable and efficient autonomous agents.