Tapping Into Autonomous Trucking Data: An Intelligent Routine Maintenance Framework for Texas

Details

• Creators:
  Chin, Kristie ; McAuley, Anna ; Werner, Mark ; Maples, Hunter ; Gold, Andrea
• Corporate Creators:
  University of Texas at Austin. Center for Transportation Research
• Corporate Contributors:
  Texas Department of Transportation. Research and Technology Implementation Office ; United States. Department of Transportation. Federal Highway Administration
• Subject/TRT Terms:
  Artificial Intelligence Automation Autonomous Vehicles Data Collection Maintenance Strategic Planning Trucking
• Publication/ Report Number:
  FHWA/TX-23/0-7129-1
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States;Texas
• Edition:
  September 2021–August 2023
• Corporate Publisher:
  University of Texas at Austin. Center for Transportation Research
• Abstract:
  Texas has become a major hub for autonomous trucking activity, with companies operating routes daily and continuing to expand operations onto new roadways. Equipped with high-definition cameras and sensor suites, autonomous trucks present a new data opportunity for the Texas Department of Transportation (TxDOT) to improve its routine maintenance operations. Partnering with two autonomous trucking companies and three TxDOT Districts, the University of Texas at Austin Center for Transportation Research (CTR) developed an intelligent routine maintenance framework (IRMF) and prototype. The IRMF establishes workflows for detecting, assigning, and resolving routine maintenance events. Based on public-and private-stakeholder input, the research team prioritized six routine maintenance events for inclusion in the protype: potholes, striping and pavement markers, guardrails and cable barriers, debris, and work zones. The prototype leveraged TxDOT’s Nighttime Inspection Suite to enable participating Districts to access 411 autonomous trucking events and compare with traditional TxDOT inspections. Additionally, the research team created a dashboard for mapping and visualizing the routine maintenance events by type, roadway, and District. Finally, the research team formulated a growth and sustainability plan that includes complementary artificial intelligence (AI) solutions, a cost-benefit analysis, and procurement pathways. Overall, the project establishes a proof of concept upon which TxDOT can build, automate, and ultimately scale statewide. By integrating data from autonomous trucks and other third-party data sources, TxDOT can improve the coverage, resolution, and timeliness of its routine maintenance data; reduce response times; and increase the safety of its roadways for automated and traditional vehicles alike.
• Format:
  PDF
• Funding:
  0-6999-21
• Collection(s):
  US Transportation Collection Autonomous Vehicles
• Main Document Checksum:
  urn:sha-512:8a3512e1d665a1dc7ea04eab9bb5bdf6c9ba3f182ec0e18549b6475f2cf54eade41b62f308959e441aeb17fd633be99f852ee1b2f980753bd8cddb76798a1be4
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/77786/dot_77786_DS1.pdf
• File Type:
  [PDF - 1.90 MB ]