Xin Ye

Papers

Total Citations

H-Index

About

Xin Ye is a researcher specializing in robotic perception, visual navigation, and autonomous systems, with a particular focus on bridging the gap between object recognition and intelligent robot decision-making. His most notable work, "Active Object Perceiver: Recognition-Guided Policy Learning for Object Searching on Mobile Robots" (2018), addresses one of the fundamental challenges in autonomous robotics: enabling a mobile robot to actively search for target objects in indoor environments using only visual inputs. This research represents a significant departure from traditional scene-driven navigation approaches, instead proposing a recognition-guided policy learning framework that allows robots to leverage their perceptual understanding to inform purposeful exploration strategies. The work has garnered 53 citations, reflecting its influence within the robotics and computer vision communities. Ye's contributions sit at the intersection of deep learning, reinforcement learning, and robotic autonomy — areas of growing importance as intelligent systems become increasingly embedded in real-world environments. His research offers meaningful advances toward robots that can operate with greater independence and contextual awareness, making his work highly relevant to students and researchers working on embodied AI, human-robot interaction, and next-generation autonomous systems.