digital twin
In plain wordsA detailed virtual copy of a real machine, factory, robot or city, kept in sync with live sensor data and used to monitor it, test changes safely and predict problems.
A computational model of a specific physical object, process or system — a jet engine, production line, robot, building, power grid or city — kept synchronized with its real counterpart through data from sensors and operations, and used to monitor its state, diagnose faults, predict behavior and test interventions before applying them. Strict usage requires this ongoing, often two-way, data link; a model without one is a simulation or 'digital model', and one fed by data but not feeding back is sometimes called a digital shadow. Digital twins combine physics-based simulation, CAD geometry and statistical or machine-learning models. In roboticsrobotics, n.: The science and engineering of building robots and making them work: designing their bodies, sensors and motors, and writing the software that lets them see, plan and move safely. and physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them., twins of factories and warehouses are built in physics simulatorsphysics simulator, n.: Software that imitates how real objects move, collide, bend and fall, so robots and their AI can be designed, trained and tested on a computer before touching the real world. to commission robot cells virtually, generate synthetic training datasynthetic data, n.: Data created by computer programs or AI models rather than collected from the real world — such as practice math problems written by a model, or simulated street scenes for self-driving cars., and train and evaluate policiespolicy, n.: An AI agent's strategy: the rule it follows to pick an action in each situation. Training in reinforcement learning means improving this rule until it earns high rewards. before deployment; real-to-sim pipelines reconstruct twins from scans or video. The term is also applied, more loosely, to models of people, such as patient twins in medicine or AI agents that imitate an individual.
We tested the new pallet layout in the plant's digital twin before moving a single robot.
Origin
The concept is usually traced to Michael Grieves's 2002 product-lifecycle-management presentations at the University of Michigan and the name to NASA engineer John Vickers, with NASA's 2010 technology roadmap giving an early formal definition. David Gelernter's Mirror Worlds (1991) anticipated the idea, and NASA's use of simulators during Apollo 13 (1970) is often cited as a precursor.
Usage note
A buzzword in industrial marketing, applied to anything from a static 3D model to a live, high-fidelity simulation; ask what data link and fidelity are meant.
Related
- physics simulatorphysics simulator, n.: Software that imitates how real objects move, collide, bend and fall, so robots and their AI can be designed, trained and tested on a computer before touching the real world.
- sim-to-real transfersim-to-real transfer, n.: Training a robot's AI in a computer simulation, where practice is fast, cheap and safe, and then making it work on the real robot despite the differences between simulation and reality.
- physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them.
- synthetic datasynthetic data, n.: Data created by computer programs or AI models rather than collected from the real world — such as practice math problems written by a model, or simulated street scenes for self-driving cars.
- world foundation modelworld foundation model, n.: A large AI model trained on vast amounts of video that can imagine how a scene will unfold, used to create realistic practice worlds for robots and self-driving cars.
- industrial robotindustrial robot, n.: A programmable robot arm used in factories for jobs such as welding, painting, assembling and moving parts, traditionally working inside a safety cage.
Sources
- Grieves, M. & Vickers, J. (2017). Digital twin: Mitigating unpredictable, undesirable emergent behavior in complex systems. In Kahlen, F.-J., Flumerfelt, S. & Alves, A. (eds.), Transdisciplinary Perspectives on Complex Systems. Springer.
Mentioned in
physical AIphysical AI, n.: AI built to work in the physical world rather than on a screen: the intelligence inside robots, self-driving cars, drones and other machines that must sense real surroundings and move through them., 3D reconstruction3D reconstruction, n.: Building a 3D model of an object or place, its shape and often its colors, from photos, video or depth-sensor scans., Gaussian splattingGaussian splatting, n.: A way of turning photos of a real place into a 3D scene made of millions of tiny, soft, colored blobs that can be viewed from any angle in real time, even on a phone or headset., physics simulatorphysics simulator, n.: Software that imitates how real objects move, collide, bend and fall, so robots and their AI can be designed, trained and tested on a computer before touching the real world., sim-to-real transfersim-to-real transfer, n.: Training a robot's AI in a computer simulation, where practice is fast, cheap and safe, and then making it work on the real robot despite the differences between simulation and reality., dark factorydark factory, n.: A way of building software in which AI agents write, test and ship all the code and no human writes or reads it, like a factory run with the lights off., Genesis MissionGenesis Mission, prop. n.: A US government program launched in 2025 to speed up science with AI, using the national laboratories' supercomputers and data to build AI tools for research., world foundation modelworld foundation model, n.: A large AI model trained on vast amounts of video that can imagine how a scene will unfold, used to create realistic practice worlds for robots and self-driving cars.