Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , LLM Assistant for heterogeneous multi-robot system dynamic task planning(Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18); Multi-robot systems find good implantation in construction applications. The combination of the skills of the robots creates systems with high flexibility. However the combination of these skills is not enough to ensure complex task completion. Task planning needs to face the dynamic behaviors of construction environments. In this paper, a heterogeneous multi-robot system for construction tasks is presented. The system is composed by three robots that present complementary skills and is commanded through natural language requirements, imposing low training requirements for the user. Task planning is managed by a large language model assistant, which receives information about the environment and the state of the system along with the user request. With this information, the assistant provides the execution plan for the robots in a dynamic environment. The system is tested through different situations with real-world tasks, involving extensive interaction with the environment and dynamic planning. Environment recognition, tool manipulation, or obstacle removal are some of the tasks presented in the system.Publicationtype: Conference Paper42 238 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: with files , Experimental evaluation of iPad Pro LiDAR, for building modeling and possibilities to connect with AI technologies(Technische Universität Hamburg, Institut für Digitales und Autonomes Bauen, 2024-09-18); Measuring buildings is a recurring task when recording construction progress and existing buildings in BIM-models. LiDAR (Light Detection and Ranging) surveying systems allow fast and precise recording of environments but are usually not attractive in terms of price of widespread use. Nowadays, modern mobile devices equipped with LiDAR sensors offer a cost-effective alternative for measuring environments or structures. This Paper experimentally investigates to which extent the iPad Pro, with its various software solutions and the LiDAR technology available today, can be used to create building models. Four experiments were conducted to reflect real-life situations: (i) scanning closed space, (ii) scanning loop of a larger area, (iii) the range of the LiDAR sensor, and (iv) its accuracy as well as the functionality of direct automatic modeling of BIM-models compared to professional systems. The experimental investigations show that the iPad Pro can already be used to capture point clouds with minor quality reduction. Furthermore, the post-processing of the scan data using artificial intelligence is being investigated to derive further research questions on how the scan data can be automatically evaluated and the quality of the derived 3D building models can be improved.Publicationtype: Conference Paper26 302