Selected work

Representative Papers

Requirements for Aligned, Dynamic Resolution of Conflicts in Operational Constraints

Nov 14, 2025

Autonomous AI systems struggle to simultaneously satisfy procedural, legal, and ethical constraints in real-world environments, leading to decision-making dilemmas under conflicting norms. Method: We propose a dynamic decision-making framework that integrates normative, pragmatic, and contextual knowledge. It enables AI to autonomously generate candidate actions under constraint conflicts, evaluate them across multiple dimensions—including goal consistency and value alignment—and produce human-interpretable action justifications. Technically, the framework unifies multi-source knowledge reasoning, fine-grained situational understanding, and explainable planning—moving beyond limitations of end-to-end policy learning. Contribution/Results: This work is the first to systematically characterize the knowledge types and mechanisms required for compliant and reasonable decision-making in underspecified scenarios. Empirical evaluation demonstrates substantial improvements in behavioral planning robustness, contextual adaptability, and alignment with human values.

0 citationsRead paper

Using Natural Language for Human-Robot Collaboration in the Real World

Aug 15, 2025

This study addresses the challenge of enabling embodied robots to collaboratively perform complex tasks with humans in real-world environments through natural language. We propose an end-to-end architecture that deeply integrates large language models (LLMs)—e.g., ChatGPT—into embodied cognitive agents. Our method unifies LLM-based language processing, contextual knowledge modeling, human-robot interaction mechanisms, and an embodied reasoning framework to achieve closed-loop coordination among dynamic language understanding, context-aware perception, and physical task execution. Crucially, we move beyond conventional command-following paradigms by enabling robots to iteratively refine language comprehension and collaborative strategies grounded in situated experience. Through three systematic proof-of-concept experiments, we empirically validate the efficacy of LLMs in multi-step instruction parsing, context-dependent reasoning, and collaborative dialogue. The results establish a reproducible technical pathway and empirical foundation for developing intelligent collaborative robots endowed with situational cognition and interactive learning capabilities.

0 citationsRead paper

Challenges in Grounding Language in the Real World

Jun 20, 2025

This work addresses the semantic grounding problem in embodied intelligence—specifically, the challenge of reliably mapping natural language instructions to physical robot actions in real-world environments. To overcome this fundamental limitation, we propose a cognitively inspired, tightly coupled architecture integrating robotic task learning with large language models (LLMs). Our method systematically identifies core grounding bottlenecks and innovatively unifies online interactive task learning (ITL) with LLM-based semantic understanding through a cognitive robot architecture, an LLM interface, and a multimodal semantic alignment mechanism. We implement and evaluate a scalable integrated prototype that closes the loop from natural language instruction to physical action execution. Experimental results demonstrate robust end-to-end performance across diverse manipulation tasks, validating the framework’s effectiveness in realistic settings. This work contributes both a reusable methodology and a concrete technical pathway toward natural, adaptive human–robot collaboration in unstructured physical environments.

0 citationsRead paper

Recent publications

Latest Papers

Requirements for Aligned, Dynamic Resolution of Conflicts in Operational Constraints

Nov 14, 2025

Autonomous AI systems struggle to simultaneously satisfy procedural, legal, and ethical constraints in real-world environments, leading to decision-making dilemmas under conflicting norms. Method: We propose a dynamic decision-making framework that integrates normative, pragmatic, and contextual knowledge. It enables AI to autonomously generate candidate actions under constraint conflicts, evaluate them across multiple dimensions—including goal consistency and value alignment—and produce human-interpretable action justifications. Technically, the framework unifies multi-source knowledge reasoning, fine-grained situational understanding, and explainable planning—moving beyond limitations of end-to-end policy learning. Contribution/Results: This work is the first to systematically characterize the knowledge types and mechanisms required for compliant and reasonable decision-making in underspecified scenarios. Empirical evaluation demonstrates substantial improvements in behavioral planning robustness, contextual adaptability, and alignment with human values.

0 citationsRead paper

Using Natural Language for Human-Robot Collaboration in the Real World

Aug 15, 2025

This study addresses the challenge of enabling embodied robots to collaboratively perform complex tasks with humans in real-world environments through natural language. We propose an end-to-end architecture that deeply integrates large language models (LLMs)—e.g., ChatGPT—into embodied cognitive agents. Our method unifies LLM-based language processing, contextual knowledge modeling, human-robot interaction mechanisms, and an embodied reasoning framework to achieve closed-loop coordination among dynamic language understanding, context-aware perception, and physical task execution. Crucially, we move beyond conventional command-following paradigms by enabling robots to iteratively refine language comprehension and collaborative strategies grounded in situated experience. Through three systematic proof-of-concept experiments, we empirically validate the efficacy of LLMs in multi-step instruction parsing, context-dependent reasoning, and collaborative dialogue. The results establish a reproducible technical pathway and empirical foundation for developing intelligent collaborative robots endowed with situational cognition and interactive learning capabilities.

0 citationsRead paper

Challenges in Grounding Language in the Real World

Jun 20, 2025

This work addresses the semantic grounding problem in embodied intelligence—specifically, the challenge of reliably mapping natural language instructions to physical robot actions in real-world environments. To overcome this fundamental limitation, we propose a cognitively inspired, tightly coupled architecture integrating robotic task learning with large language models (LLMs). Our method systematically identifies core grounding bottlenecks and innovatively unifies online interactive task learning (ITL) with LLM-based semantic understanding through a cognitive robot architecture, an LLM interface, and a multimodal semantic alignment mechanism. We implement and evaluate a scalable integrated prototype that closes the loop from natural language instruction to physical action execution. Experimental results demonstrate robust end-to-end performance across diverse manipulation tasks, validating the framework’s effectiveness in realistic settings. This work contributes both a reusable methodology and a concrete technical pathway toward natural, adaptive human–robot collaboration in unstructured physical environments.

0 citationsRead paper