Shangyue Zhu
Papers
2
Total Citations
13
H-Index
2
About
Shangyue Zhu is a researcher advancing the frontier of robotic autonomous navigation through innovative machine learning techniques. Their primary research areas include imitation learning, multi-sensory data fusion, and semi-supervised learning, with a focus on reducing human intervention in robotic systems. Zhu’s major contributions lie in developing automated labeling methods that minimize the need for costly and error-prone human supervision during robot training. In their 2019 paper, “Automated Labeling for Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning on Big Data” (10 citations), they pioneered a framework that leverages big data and multi-sensory inputs to enable robots to learn navigation tasks more efficiently. An earlier 2017 work, “Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning” (3 citations), laid the groundwork for this approach. Zhu’s research addresses a critical bottleneck in imitation learning—the reliance on human trainers—by enabling robots to autonomously generate labels from sensory data. This work holds promise for scaling autonomous systems in real-world environments, from self-driving cars to warehouse robots, making Zhu a notable contributor to the field of intelligent robotics.
Research Focus
Key Achievements
Top Papers
- 1
- 2