Skip to content
SIH Buddyby Ganeev Singh
Dev
All problem statements
SIH26039Proceed with cautionacceptance 2/5

Al-Powered Underground Mine Safety, Monitoring and Rescue System.

Governmcnt of Jharkhand · Travel & Tourism · Hardware

The robot is the easy part and everyone builds it; the parts that actually decide whether this could ever be deployed — through-rock communications and certified gas sensing — are out of reach, so be sure you can answer the comms question before you commit.

What it actually is

When something goes wrong in an underground coal mine — a gas leak, a roof collapse, flooding — rescue teams go in blind, with no idea what the air or the tunnels are like inside. That costs time and puts the rescuers themselves at risk. The ask is a robot that goes in first, reads the conditions, looks for trapped workers and sends it all back to the surface.

What to build

A rugged ground rover, or the compact aerial alternative the statement permits, carrying a gas sensing head for the hazardous atmospheres underground mines produce, environmental sensing for temperature and humidity, thermal and low-light cameras for navigating and finding people in zero visibility, and a communications chain that actually works past line of sight underground — meaning either a tether or self-deploying relay nodes, since radio does not pass through rock — streaming live video, thermal frames and gas readings to a surface control station with a map of where the rover has been and where each reading was taken.

Smallest thing that wins the room

Drive the rover into a smoke-filled unlit corridor, drop relay nodes as it goes, and hold the video and gas telemetry live at the surface station after it has passed two corners with no line of sight.

How crowded this one gets

A guess, projected from the 2025 statements — the last year where both the submission counts and the winners were published.

Crowded450–500 teams expectedroughly 1 in 381–421 wins it

Quieter than 6% of the 226 · #213 of 226 by expected field · reaches the 500 cap

Heavily contested. The obvious build has already been done by twenty other teams.

Why: state governments drew the biggest crowds in 2025; hardware halves the field a software statement gets.

This is a guess, not a fact

Nobody has published 2026’s numbers yet. This is an analysed estimate from last year’s pattern, so please do not take it as the truth — check the live counter on the SIH portal before you decide anything. The range covers the middle half of likely outcomes, so one statement in two lands outside it. Entry closes at 500 ideas per statement, so no range goes past that — a statement that reaches the cap fills and shuts rather than drawing an unlimited crowd. The model reads only three things a team can see before choosing — software or hardware, the theme, and what kind of body posted it — and those explain about a quarter of the variation in last year’s field sizes (R² 0.25 on held-out statements). Trust the band more than the number, and the ordering more than either. It cannot see how good your idea is, which is the part that actually decides it.

The scores

The number is the shorthand. The line under it is the reason.

What you will be writing

  • tracked chassis with ROS2 teleoperation
  • electrochemical CH4 / CO / O2 gas sensing head
  • FLIR Lepton thermal + IR low-light imaging
  • self-deploying LoRa or tethered relay comms
  • LiDAR SLAM for GPS-denied mapping
  • surface control station with telemetry replay
  • Mine safety and rescue
  • Field robotics
  • Hazardous environment sensing

Prior art to read before you start

underground search and rescue robot · toxic gas and atmosphere monitoring · GPS-denied navigation and mapping

Analysed by Claude Opus. Every score above is a judgment call with its reasoning attached — kindly cross-check this against the official statement on the SIH portal before your team commits to it.