Surface Penetration and Imaging for Infrastructure Inspection Using Radar Sensors as UAS Payload – Year Two Effort

Even though radar technologies, such as Ground Penetration Radar (GPR) and Synthetic Aperture Radar (SAR), have been investigated in previous USDOT projects based on the advantages of all-weather and surface penetration sensing capabilities, a small, agile, and low-power version of such radar as a payload of Unmanned Aerial Vehicle (UAV) or Unmanned Ground Vehicles (UGV) have not yet been demonstrated before. Another trend in bridge/road/pavement inspection is robot-based, automatic, multi-sensor integration from a distributed network. Several manned ground-based platforms with cameras and other sensors (LIDAR, acoustic, piezoelectric, IR, RFID, etc.) have been reported to be used previously in DOT projects. This includes machine learning (ML) processing methods to identify structure and material health issues better. However, more in-depth investigation is still needed to mature these algorithms. Transferring these R&D efforts to operational capabilities still depends on real-world challenges, such as infrastructure accessibility, safety, environments, and maturity of the sensor systems. The specific objectives include: (1) Developing and demonstrating a new low-size, weight, and power radar sensor that meets the UAS payload requirements and the need for surface penetration inspections; (2) Establishing a formal operational procedure that can be applied to the regional and national tasks. (3) Evaluate the performance and capability of an integrated UAS system and sensing payload through data collections under different environments, and (4) Achieve dual-function (imaging and profiling) through existing signal processing and applying novel machine-learning methods. The novel contribution of the new radar sensor package proposed from this project mainly lies in three aspects: (1) Wideband microwave radar inspection with both designs from lower-frequency, traditional GPR frequency band, and higher frequency, microwave radar band that offers better resolution and smaller sensor aperture sizes, by leveraging the latest component technology of radar sensors. (2) Enabling and implementing the integration into a small UAS (sUAS) platform, which has fewer restrictions from ground traffic, can access the difficult areas for human operators and demonstrate such platforms through flight tests. (3) Introduction of Machine Learning (ML) method based on high-fidelity physical modeling of the interactions between structures and microwave sensors and decision-tree type sensor data models. Thus, the capability of detecting various types of defects in the 3D domain is enhanced compared to existing radar sensors. The following tasks will be pursued for the successful completion of this project. Task 1: Complete radar sensor designs, compare two sensor design options based on different frequencies and finalize the chip-hardware solution selection for implementation. Task 2: Complete radar sensor integration into the UAS platform, run more flight test operations in relevant environments, collect radar data from the bridge surface, and propose a plan to fly over other structural areas. Process data using trained ML models based on the simulation models and demonstrate the application and operational value of the payload sensor system in realistic and relevant environments. Task 3: Investigate, integrate, and demonstrate radar sensor registration for a unique 3D profiling product that combines 2D surface imaging and radar depth profile, using the ML algorithm to process the imaging. The algorithm would explore the combination of sensor data from radar and camera for the same inspection sample area. Task 4: Performing demonstration activities at the Choctaw Nation facility for application evaluation and expansion ideas for future collaboration.

• Record URL:
  • https://www.sptc.org/cy2-ou-15

Language

• English

Project

• Status: Active
• Funding: $105,404.00
• Contract Numbers:

  CY2-OU-15

  69A3552348306

• Sponsor Organizations:

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Managing Organizations:

  Southern Plains Transportation Center

  University of Oklahoma
  202 W Boyd St, Room 213A
  Norman, OK  United States  73019
• Project Managers:

  Dunn, Denise

• Performing Organizations:

  University of Oklahoma, Norman

  School of Civil Engineering and Environmental Science
  202 West Boyd Street, Room 334
  Norman, OK  United States  73019
• Principal Investigators:

  Zhang, Rockee

  Suarez, Hernan

• Start Date: 20241001
• Expected Completion Date: 20250930
• Actual Completion Date: 0
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Bridges; Data collection; Drones; Infrastructure; Inspection; Machine learning; Radar; Sensors
• Geographic Terms: Oklahoma
• Subject Areas: Bridges and other structures; Data and Information Technology; Highways; Maintenance and Preservation;

Filing Info

• Accession Number: 01941682
• Record Type: Research project
• Source Agency: Southern Plains Transportation Center
• Contract Numbers: CY2-OU-15, 69A3552348306
• Files: UTC, RIP
• Created Date: Jan 1 2025 4:11PM