Jicong Ao
Papers
4
Total Citations
22
H-Index
2
About
Jicong Ao is an emerging robotics researcher whose work sits at the innovative intersection of large language models (LLMs) and autonomous robot task planning. His research focuses primarily on leveraging the reasoning capabilities of LLMs to automate the generation of behavior trees (BTs), a hierarchical control framework widely valued in robotics for its modularity and flexibility. Ao's most significant contribution, the "LLM-as-BT-Planner" framework, addresses one of robotics' persistent challenges: planning long-horizon, complex assembly tasks that traditionally demand labor-intensive manual programming. By harnessing LLMs to generate and refine behavior trees, his approach substantially reduces human effort while improving task adaptability. His work on integrating human instructions and feedback into sequential manipulation planning further demonstrates a commitment to building robots that collaborate naturally with human operators. Collectively, his publications have accumulated over 20 citations, reflecting growing recognition within the robotics and AI communities. Ao's research represents a timely and compelling direction as the field increasingly explores how foundation models can serve as cognitive engines for next-generation autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4