Robotics, Volume 14, Issue 9
2025 September - 16 articles
Cover Story: This study presents a comprehensive framework for integrating Large Language Models (LLMs) into construction robot task planning, overcoming the rigid conventional hardcoded approaches. The framework systematically prepares structured BIM data, unstructured human instructions, and robot-specific parameters to form a knowledge base that an LLM can interpret. Through real-time dialogue, the LLM translates diverse inputs into robot plans, enabling user-driven adaptation and flexible task execution in dynamic construction environments. A prototype, demonstrated with a mobile painting robot in simulation, shows that GPT-4 can guide operations, respond to superintendent inputs, and reduce the need for extensive coding, paving the way for more intelligent and adaptable construction automation. View this paper - Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
- You may sign up for email alerts to receive table of contents of newly released issues.
- PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.