Run Peng

Papers

Total Citations

H-Index

About

Run Peng is a leading researcher in embodied AI and robot navigation, with a focus on enabling intelligent agents to operate in open-world environments. His most-cited work, "Think, Act, and Ask: Open-World Interactive Personalized Robot Navigation" (2024, 19 citations), pioneers a novel paradigm for Zero-Shot Object Navigation (ZSON) that integrates reasoning, action, and natural language interaction. Unlike prior approaches that simply follow static instructions to locate generic objects, Peng’s framework allows robots to actively engage with humans through dialogue, asking clarifying questions to resolve ambiguity and personalize navigation tasks. This breakthrough addresses a critical gap in robotics—moving beyond rigid, pre-defined commands to truly adaptive, human-aware behavior. By combining large language models with spatial reasoning, his work has set a new standard for interactive navigation, earning recognition for its potential to transform service robots, assistive technologies, and autonomous systems. Peng’s contributions are shaping the future of human-robot collaboration, making him a rising star in the field of embodied AI.