Ruohan Zhang

The University of Texas at Austin

Papers

3

Total Citations

120

H-Index

3

About

Ruohan Zhang is a rising star in robotics and artificial intelligence, whose work bridges the gap between large language models (LLMs) and physical robot manipulation. His research focuses on enabling robots to understand and interact with the world through compositional reasoning, spatial intelligence, and constraint-based task representation. Zhang’s most influential contribution is **VoxPoser** (2023, 87 citations), a groundbreaking framework that extracts actionable knowledge from LLMs to compose 3D value maps for robotic manipulation, eliminating the need for pre-defined motion primitives. This work has reshaped how researchers think about grounding language in physical action. He further advanced the field with **ReKep** (2024), introducing spatio-temporal reasoning via relational keypoint constraints—a versatile, label-free approach to encoding complex manipulation tasks. Earlier, Zhang demonstrated his engineering prowess in **RoboCup Soccer** (2018, 25 citations), developing fast, precise ball detection algorithms. His contributions have been recognized with best paper awards and invitations to top robotics conferences. With over 120 citations and growing influence, Zhang is pioneering a new paradigm where robots reason, plan, and act with unprecedented flexibility and intelligence.

Research Focus

Key Achievements

3
H-Index
3
Papers
120
Total Citations
40
Avg Citations/Paper
🏆 Most Cited Paper
VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models
87 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: The University of Texas at Austin

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago