Modern space exploration hasn't quite reached Star Trek levels of boldly going where no one has gone before. But if, like the denizens of the USS Enterprise, astronauts one day want to land on an uncharted planet, they'd first want to know what's on — and under — the surface.
Virginia Tech research could clear the way for that with a new set of tools that scan vibrations in terrain to determine how far below the surface rocks extend. And it's not science fiction.
Erik Komendera , an assistant professor of mechanical engineering, once worked as an engineer at the NASA Langley Research Center. His latest research with Ph.D. candidate Yiyan Ruan , published in IEEE Sensors Journal , may help rovers to land safely on Mars, the Moon, or other largely unexplored planets. It could also have Earth-bound applications, such as analyzing construction or disaster scenarios when potential hazards are buried.
Vibrations as measuring tools
Factors such as the elevation and roughness of terrain and the height of rocks affect options for where to put down a spacecraft on current missions to Mars .
If a rock is in the way of a potential landing surface, a robotic excavator could chip away at it. But if the rock is actually a buried boulder, that robot shouldn't waste energy and wear out tools trying to remove something that is immovable.
"For as long as humans have built things on Earth, we have had to deal with large and heavy obstacles that cannot simply be ignored or scooped out of the way without careful planning," Komendera said. "It's easy enough for us to just look at rocks and make some quick, testable judgments. Is this rock resting or partially buried? Can I move this alone or do I need help and tools? But what if robots need to do this? How can robots make those judgments? Now we have an answer."
Komendera is putting together a set of tools that could save the excavators a lot of work. To test their approach, his team buried 18 concrete blocks of different sizes and shapes at different depths in sand. They struck the exposed rock with an instrumented hammer, then measured the resulting vibrations remotely using a scanning laser Doppler vibrometer.
After testing the vibration at multiple heights on the rock's surface, researchers fed the results to a neural network that learned the relationship between vibration characteristics, visible rock geometry, and burial depth.
AI decodes vibration information
The team used the data to train the AI to analyze and compare the results. The relationship between soil stiffness, the angle at which the rocks made contact with the sand, and other factors made taking the readings complex. By teaching AI to account for these factors, the team was able to build models that could reliably determine depth.
"Estimating how deep a rock is buried using vibrations can be tricky," Ruan said. "The feedback is affected by the rock's geometry and the way the soil holds it. By carefully selecting features from vibration measurements and exposed geometry, we were able to produce reliable data using a compact neural network with just two hidden layers."
Those models could one day guide a robotic excavator on Mars to handle obstacles correctly in the terrain. For now, the team plans to continue building datasets and testing their approach on Earth, where the tool could be useful for determining the components of unstable rock formations, measuring underground caverns, even helping with disaster cleanup.
Original study : DOI.10.1109/JSEN.2026.3733381
