Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Eine Plattform für die Wissenschaft: Bauingenieurwesen, Architektur und Urbanistik
Natural language instructions for intuitive human interaction with robotic assistants in field construction work
Abstract Human-Robot Collaboration (HRC) has shown promise of combining human workers' flexibility and robot assistants' physical abilities to jointly address the uncertainties inherent in construction work. In HRC, natural language-based interaction can enable human workers who are non-experts in robot programming to intuitively communicate with robot assistants. However, limited research has been conducted on this topic in construction. This paper proposes a framework to allow human workers to interact with construction robots based on natural language instructions for pick-and-place construction operations. The proposed method consists of three modules: Natural Language Understanding (NLU), Information Mapping (IM), and Robot Control (RC). A case study for drywall installation evaluates the proposed approach. Results indicate over 99% accuracy in NLU and IM, allowing a robot to perform tasks accurately for a given set of natural language instructions. It highlights the potential of using natural language-based interaction to replicate human-like communication in human-robot teams.
Highlights A natural language-based interaction framework for human-robot collaboration in field construction work. Natural language instructions and building information are used to generate work commands to assistive construction robots. A deep learning language model analyzes target, destination, and placement method. Drywall installation example demonstrates potential of natural interaction for collaborative human robot construction.
Natural language instructions for intuitive human interaction with robotic assistants in field construction work
Abstract Human-Robot Collaboration (HRC) has shown promise of combining human workers' flexibility and robot assistants' physical abilities to jointly address the uncertainties inherent in construction work. In HRC, natural language-based interaction can enable human workers who are non-experts in robot programming to intuitively communicate with robot assistants. However, limited research has been conducted on this topic in construction. This paper proposes a framework to allow human workers to interact with construction robots based on natural language instructions for pick-and-place construction operations. The proposed method consists of three modules: Natural Language Understanding (NLU), Information Mapping (IM), and Robot Control (RC). A case study for drywall installation evaluates the proposed approach. Results indicate over 99% accuracy in NLU and IM, allowing a robot to perform tasks accurately for a given set of natural language instructions. It highlights the potential of using natural language-based interaction to replicate human-like communication in human-robot teams.
Highlights A natural language-based interaction framework for human-robot collaboration in field construction work. Natural language instructions and building information are used to generate work commands to assistive construction robots. A deep learning language model analyzes target, destination, and placement method. Drywall installation example demonstrates potential of natural interaction for collaborative human robot construction.
Natural language instructions for intuitive human interaction with robotic assistants in field construction work
Park, Somin (Autor:in) / Wang, Xi (Autor:in) / Menassa, Carol C. (Autor:in) / Kamat, Vineet R. (Autor:in) / Chai, Joyce Y. (Autor:in)
24.02.2024
Aufsatz (Zeitschrift)
Elektronische Ressource
Englisch
Design for Natural and Intuitive Interaction: Touch-Based Human-Computer Interaction
| British Library Conference Proceedings
Jamming Formations - Intuitive design and fabrication process through human-computer interaction
| TIBKAT | 2019