Shaohong Zhong
Papers
2
Total Citations
18
H-Index
2
About
Shaohong Zhong is a roboticist whose research lies at the intersection of manipulation, perception, and generative modeling. His work addresses two fundamental challenges in robotics: how to plan complex physical interactions and how to generate realistic tactile data without costly real-world collection. In his highly cited 2022 paper, "Reaching Through Latent Space," Zhong pioneered a novel path planning approach that optimizes robot trajectories within the latent space of a generative model, using constraint satisfaction classifiers to embed physical limitations directly into the planning process. This work has garnered 14 citations and represents a significant conceptual advance in bridging generative AI with motion planning. More recently, with "TactGen" (2024), Zhong tackled the data scarcity problem in tactile sensing by introducing a zero-shot sim-to-real transfer framework that generates high-fidelity tactile sensory data, enabling robots to "feel" without expensive physical data collection. Though early in his career, Zhong’s contributions are already shaping how researchers think about integrating generative models into robotic control and perception pipelines, pointing toward a future where robots can both plan and sense with unprecedented efficiency.
Research Focus
Key Achievements
Top Papers
- 1
- 2