Reproduce “Multi-agent robotic systems and exploration algorithms: Applications for data collection in construction sites” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Samuel A. Prieto, Nikolaos Giakoumidis, Borja Garcia de Soto
Researchers from NYU Abu Dhabi developed a multi-agent robotic system and exploration methodology that integrates Building Information Models (BIM) to enable autonomous, comprehensive data collection in dynamic construction environments. The system, involving collaborative robots and human intervention, achieved 3D digitization of an occluded space, covering over 95% of the target area.
Key insights
- Multi-agent collaboration, combining different robotic capabilities and human intervention, is critical for addressing unpredictable challenges and completing tasks in dynamic construction environments.
- Leveraging Building Information Models (BIM) provides essential prior knowledge, allowing for intelligent stopping criteria in autonomous exploration and efficient identification of inaccessible areas requiring intervention.
- A modular system architecture built on ROS enables seamless real-time data exchange, sensor integration, and scalable communication for diverse robotic agents and functionalities.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.