Browsing by Author "Lytle, Alan Marshall"

Now showing 1 - 2 of 2
  • Thumbnail Image
    The development of a remotely piloted vehicle (RPV) with real-time position measurement (RtPM) for hazardous waste site characterization
    Lytle, Alan Marshall (Virginia Tech, 1994-12-15)
    This research was initiated to investigate the application of mobile robotics to hazardous waste site characterization, with the specific emphasis of employing the laser-based positioning measurement system developed by Spatial Positioning Systems, inc. (SPSi) for tracking a mobile robot and geographically tagging collected environmental data. The two specific objectives of this work were to design and construct a remotely piloted robotic system which could enter a simulated hazardous waste site and perform some aspect of initial characterization sampling, and to perform a feasibility study on the use of the SPSi system for outdoor mobile robot tracking. A Honda all-terrain vehicle was converted to a robotic test platform incorporating the SPSi system for positioning and a magnetometer for environmental sensing. The digitally-sampled magnetometer output was geographically tagged with sensor position, and transmitted to a remote computer for display and storage. Although the mechanics of integrating the SPSi system and an environmental sensor on a mobile robot were demonstrated, survey attempts with the mobile robot were unsuccessful because the SPSi system was unable to track the robot's movements outdoors on the simulated hazardous waste site. Tracking capability up to a limiting velocity of approximately 0.35 mls (0.8 mph) was demonstrated with the SPSi system. This restrictive limiting velocity as well as various errors later discovered in SPSi's tracking algorithm prevented a successful implementation of the positioning system on the robot.
  • Thumbnail Image
    A Framework for Object Recognition in Construction Using Building Information Modeling and High Frame Rate 3D Imaging
    Lytle, Alan Marshall (Virginia Tech, 2011-04-01)
    Object recognition systems require baseline information upon which to compare sensed data to enable a recognition task. The ability to integrate a diverse set of object recognition data for different components in a Building Information Model (BIM) will enable many autonomous systems to access and use these data in an on-demand learning capacity, and will accelerate the integration of object recognition systems in the construction environment. This research presents a new framework for linking feature descriptors to a BIM to support construction object recognition. The proposed framework is based upon the Property and External Reference Resource schemas within the IFC 2x3 TC1 architecture. Within this framework a new Property Set (Pset_ObjectRecognition) is suggested which provides an on-demand capability to access available feature descriptor information either embedded in the IFC model or referenced in an external model database. The Property Set is extensible, and can be modified and adjusted as required for future research and field implementation. With this framework multiple sets of feature descriptors associated with different sensing modalities and different algorithms can all be aggregated into one Property Set and assigned to either object types or object instances.