In 79 AD, a colossal and foreboding cloud carrying a lethal blend of gas and ash exploded into the Earth’s stratosphere. As a fiery concoction of debris descended from the heavens for nearly 18 straight hours, a bustling Mediterranean city was completely leveled, burying 2,000 of its residents alive under a blanket of asphyxiating fumes and rocks.
This was the dramatic end to the once prosperous Roman city of Pompeii, burried by a deadly volcanic eruption. Nearly 2,000 years later, 3.4 million tourists a year visit the remains of this formerly thriving metropolis, which is protected as a UNESCO World Heritage Site.
Pompeii’s tremendous popularity amplifies its historical impact and increases demand for its preservation. On the other hand, it makes it an attractive target for thieves and accelerates its natural decay, both of which are existential threats.
To ensure its survival for future generations, preservationists recently turned to cutting-edge technology powered by artificial intelligence. Spot, a robotic guard dog, patrols Pompeii, keeping a watchful digital eye on the 163 acres of dilapidating ruins.
Every Dog Has Its Day
Built by Boston Dynamics, the four-legged machine works day and night monitoring structural decay that has been centuries in the making. Along with a dedicated Pompeii drone – a Leica BLK2FLY autonomous flying laser scanner that uses lidar to track changes in the ruins over time – it collects troves of 3D data for use by archaeologists.
“A quadruped robot is capable of inspecting even the smallest of spaces in complete safety, gathering and recording data useful for the study and planning of interventions,” Pompeii’s caretakers reported.
“It improves both the quality of monitoring of the existing areas, and to further our knowledge of the state of progress of the works in areas undergoing recovery or restoration.”
Worker safety is a major priority. Spot can sniff around corridors and underground tunnels that sometimes are too dangerous for human exploration, including those dug by grave robbers.
“Often the safety conditions within the tunnels dug by grave robbers are extremely precarious, as a consequence of which the use of a robot could signify a breakthrough that would allow us to proceed with greater speed and in total safety," Pompeii Director General Gabriel Zuchtriegel said in a statement.
Man and machine are working in complete harmony, according to Brad Bonn, a customer application engineer at Boston Dynamics.
“The robot can be tasked with pre-determined missions to gather data in hazardous locations without human intervention,” Bonn explained in a blog post for Amazon Web Services (AWS).
“Operators can control Spot with a joystick via the Spot tablet and record an ‘autowalk’ mission – a pre-programmed route that Spot is able to navigate using obstacle avoidance and autonomous capabilities. Operators can instruct Spot to perform programmable tasks through an API interface that allows developers to acquire, store and retrieve sensor or camera data. Once an ‘autowalk’ mission has been recorded, Spot can be commanded to repeat the ‘autowalk’ mission without an operator.”
All Bytes and No Bark
Cloud computing allows Spot’s handlers to collect essential information and glean real-time insights from terabytes of raw data.
“Every step of setting up Spot’s automated inspections has been streamlined for effective data capture and processing,” Boston Dynamics said in a press release.
“Schedule missions for Spot to collect photos, thermal images, point clouds and other critical data; process that data into valuable and actionable signals at the edge with computer vision models; and create custom uploads to send those signals to your existing systems, so it’s easy to keep all of your data in one place for analysis and review.”
With access to the cloud, authorities can immediately deploy artificial intelligence and machine learning to identify structural hazards or even trespassers.
“AI systems depend on data, but reliable, repeatable data is hard to collect in busy, remote or hazardous work sites,” Boston Dynamics stated. ”Spot solves this problem by acting as a dynamic sensor, collecting data where and when it’s needed, freeing operators from tedious data collection
Pompeii isn’t Spot’s only customer. The promise of increased productivity has attracted everyone from building inspectors in Japan to offshore oil riggers in Norway.
“One way customers are using Spot is for inspections with machine learning-powered insights in less-than-ideal environments for human workers,” Bonn said in his AWS blog post. “Captured imagery data can be processed by a computer vision machine-learning model.”
Bringing the Past into the Future
Pompeii was once so poorly maintained that several key structures collapsed in 2008, forcing the Italian government to declare a state of emergency. Over a decade later, Spot is part of a larger project to turn Pompeii into a “smart archeological park” where archaeologists use cutting-edge technology to more efficiently manage the endangered site.
“Technological advances in the world of robotics, in the form of artificial intelligence and autonomous systems, have produced solutions and innovations typically associated with the industrial and manufacturing world, but which until now had not found an application within archaeological sites due to the heterogeneity of environmental conditions, and the size of the site,” Zuchtriegel said.
The Pompeii robot dog isn’t just a novelty or man’s best-mechanized friend. It’s also a case study on the future of preservation. As tourists and criminals take away from them what time yet hasn’t, heritage sites around the globe could benefit from autonomous technology just like it. By combining meaningful data collection with timely analysis, Spot and other cloud-powered solutions are bringing the past into the future for generations of continued education, exploration and enjoyment.
Chase Guttman is a technology writer. He’s also an award-winning travel photographer, Emmy-winning drone cinematographer, author, lecturer and instructor. His book, The Handbook of Drone Photography, was one of the first written on the topic and received critical acclaim. Find him at chaseguttman.com or @chaseguttman.
© 2022 Nutanix, Inc. All rights reserved. For additional legal information, please go here.