Weikai Ding
Papers
3
Total Citations
15
H-Index
2
About
Weikai Ding is a robotics researcher advancing the frontier of autonomous locomotion and human-robot interaction. His work focuses on three key areas: model predictive control for legged robots, multimodal locomotion for wheeled-legged platforms, and large language model (LLM)-driven interaction systems. His most cited paper (2024, 11 citations) introduces an observer-based state feedback MPC framework that corrects inaccuracies in state mapping caused by load fluctuations and external forces—a critical step toward robust, real-world legged robot deployment. In 2025, Ding proposed a wheeled-legged robot design for multi-terrain locomotion in plateau environments, addressing the trade-off between payload capacity and agile mobility. He also developed the VST-LLM HRI framework, which integrates visual, speech, and text modalities via LLM prompts to enable closed-loop perception, planning, and control without fine-tuning. These contributions demonstrate Ding’s ability to bridge control theory, mechanical design, and AI, with direct implications for search-and-rescue, planetary exploration, and assistive robotics. His work is already shaping how robots perceive, move, and collaborate with humans in unstructured environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3