{
  "id": 8819850,
  "title": "Centre testing AI system to identify rural road defects",
  "url": "https://urgent.news/2026/09/21/centre-testing-ai-system-to-identify-rural-road-defects",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-21T02:24:20.000Z",
  "source": {
    "name": "Hindustan Times",
    "slug": "hindustan-times",
    "url": "https://www.hindustantimes.com/india-news/centre-testing-ai-system-to-identify-rural-road-defects-101789931789298.html"
  },
  "original_language": "en",
  "account": "The Indian government is currently piloting an artificial intelligence system designed to detect road defects in rural areas using footage captured on mobile phones. This field-validation exercise has been ongoing since earlier this month, with the Ministry of Rural Development confirming an \"in-principle approval\" for trials on roads constructed under the Pradhan Mantri Gram Sadak Yojana (PMGSY) program. Developed by the Centre for Development of Advanced Computing (C-DAC) in collaboration with the National Rural Infrastructure Development Agency (NRIDA), the AI-based road condition assessment tool is being tested solely to support informed maintenance decisions, while engineers will continue to physically verify defects and compare their measurements with the AI-generated findings.\n\nInitially trialed on six roads in Pune, Lucknow, Kamrup (Assam), and Ri-Bhoi (Meghalaya) earlier this year, the system has since undergone improvements and been tested on seven additional roads in Kanpur and Berasia block of Bhopal. The testing aims to identify visible road defects such as potholes, longitudinal and transverse cracks, edge breaks, surface depressions, patches, and vegetation-related obstructions. The national validation exercise commenced on September 1, with states and Union territories identifying Programme Implementation Units (PIUs) for trials on PMGSY roads.\n\nThe government plans to use a mobile application to record videos of road conditions, leveraging dashcams that may be considered in the future depending on field requirements. The ministry is exploring the possibility of quarterly assessments under a proposed technology-enabled maintenance framework, though no final decision has been made. The AI-generated assessments will aid in identifying maintenance requirements while engineers maintain responsibility for verifying the findings and making decisions based on existing procedures. The Defects Liability Period, currently set at five years from the completion date, remains in place, ensuring contractors are accountable for correcting defects and carrying out routine maintenance.\n\nBefore wider implementation, the ministry will establish a verification and review protocol, examining discrepancies between AI and engineer assessments. Integration with the existing e-MARG mobile application is also being considered as part of the technology framework. The initiative promises to enhance transparency, objectivity, and efficiency in rural road maintenance assessments, aligning with the government's commitment to leveraging technology for improved rural infrastructure.",
  "summary": "The government is testing an artificial intelligence system that can identify potholes, cracks and other defects on rural roads from videos recorded on mobile phones, with a nationwide field-validation exercise underway since earlier this month, a senior official said on Sunday",
  "key_points": [
    "Indian government pilots AI system to detect rural road defects via mobile phone footage.",
    "Developed by C-DAC and NRIDA, tool tests on 13 roads across India since September.",
    "AI assessments aim to aid maintenance decisions while physical verification by engineers continues."
  ],
  "editors_take": "The AI system's testing marks a shift towards technology-enabled maintenance in rural road upkeep, potentially increasing transparency and efficiency in defect identification and prioritization.",
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}