Andy Kaminski
Papers
3
Total Citations
63
H-Index
3
About
Andy Kaminski is a leading researcher at the intersection of robotics, artificial intelligence, and natural language processing, with a core focus on enabling robots to plan and act intelligently in open-world environments. His major contributions center on bridging the gap between classical, rule-based task planning and the flexible, knowledge-rich capabilities of modern large language models (LLMs) and vision-language models (VLMs). Kaminski’s seminal work, “Integrating action knowledge and LLMs for task planning and situation handling in open worlds” (53 citations), demonstrates how to fuse structured action knowledge with the reasoning power of LLMs, allowing robots to dynamically adapt to unforeseen situations. He further advanced this paradigm by grounding classical planners in visual perception through VLMs, as seen in his highly cited 2023 paper (7 citations). Most recently, his 2024 work on DKPROMPT (3 citations) introduces a novel method for domain knowledge prompting, enabling VLMs to generate more robust and context-aware plans for complex, visually-grounded tasks. Kaminski’s research is pivotal for creating service robots that can move beyond controlled labs to operate reliably in the unpredictable, open-world settings of homes and hospitals.
Research Focus
Key Achievements
Top Papers
- 1
- 2Grounding Classical Task Planners via Vision-Language Models7 citations · 2023
- 3