How the Computational Design Pipeline Works

Federico Casalegno, head of SDIC, describes the process as a loop built on three pillars: real people, digital twins, and robots .

1. 3D and 4D body scanning. SDIC captures high-precision anatomical scans of ears, wrists, and fingers from a diverse global population. The “4D” component adds the element of time, capturing how these body parts deform during motion .
2. Digital twin creation. Those scans are converted into high-fidelity virtual anatomical models that serve as the test environment .
3. AI-powered simulations. On those digital twins, researchers run thousands of AI-driven physics simulations, adjusting variables like earbud angle, sensor placement, and contact pressure. For the Galaxy Buds4 series, this meant over 10,000 simulations .
4. Robotic cross-validation. The simulation winners are physically verified using custom robotic testing rigs. This closes the loop, turning a traditionally subjective “how does this feel?” question into a measurable engineering metric .

How Computational Design Shaped Each New Wearable

Galaxy Buds4 Series: The “Blade Design” Was Engineered, Not Just Drawn

The earbuds are the most detailed case study for the new approach. Samsung analyzed hundreds of millions of ear data points—one official source pegs it at over 100 million global ear-shape data points—and ran more than 10,000 fit simulations to arrive at the new “Buds blade” identity .

The data told a clear story: the main earbud body needed to be slightly smaller, and the angle of rotation needed to shift by a few degrees. Those minor geometric changes produced a major gain in stability and all-day comfort across a much wider user base . The result is an ultra-sleek, ergonomic fit that stays secure even during vigorous movement, a claim now backed by objective robotic test data rather than a handful of subjective reviews .

Galaxy Watch8 Series: Fit Is a Health Sensor Problem

For a smartwatch, fit is not just about comfort; it determines sensor accuracy for heart rate, sleep, stress monitoring (including the new EDA sensor on the Watch8), and exercise tracking .

SDIC applied the same 4D scanning and AI simulation pipeline to optimize wrist contact. The data pushed the team to refine the cushion design across the entire Watch8 lineup. A key mechanical decision was extending the Dynamic Lug System—first introduced on the Galaxy Watch Ultra—to all Watch8 models, minimizing the gap between the watch body and the wrist to improve sensor reading consistency .

Galaxy Ring: A Universal Fit for Millions of Fingers

Rings are inherently tricky because a single rigid object must maintain precise sensor contact on fingers of vastly different shapes. Samsung’s computational design pipeline now builds digital twins of users’ fingers to optimize ring sizing, internal curvature, and PPG sensor placement for all-day health monitoring .

The goal is to ensure that biometric measurements such as heart rate and sleep staging remain accurate across the widest possible range of finger anatomies, without requiring users to become experts in ring sizing themselves .

What Samsung Plans Next: New Wearable Categories and AI Factories

Casalegno’s outlook, from Samsung’s official interview, points to three concrete directions .

• A self-reinforcing data advantage. As Samsung’s proprietary anatomical dataset grows, its custom AI tools will drive more accurate simulations and deeper insights, potentially widening its advantage over competitors that rely on smaller or less diverse training data .
• Entirely new wearable categories. Casalegno stated that expanding this methodology could “unlock exponential innovations down the line that lead to an entirely new category of wearables that can redefine the boundaries of user experience” . He did not specify the form, but the infrastructure—objective fit data on ears, wrists, and fingers—is now in place.
• From lab to factory. Separately, Samsung has announced a plan to transition all global manufacturing into fully AI-driven factories by 2030, with digital twin-based simulations integrated across the entire production chain . This suggests the same digital twin methodology that designs a Galaxy Bud today will eventually govern how it is manufactured on the line.

Samsung’s SDIC team also confirmed they are actively innovating the design process based on accumulated data and specialized AI, with the aim of introducing wearable products that combine ergonomics and AI more deeply than current products allow . For now, the Galaxy Buds4, Watch8, and Ring are the first physical proof that subjective fit panels are giving way to an objective, AI-verified standard.

How the Computational Design Pipeline Works

Federico Casalegno, head of SDIC, describes the process as a loop built on three pillars: real people, digital twins, and robots .

1. 3D and 4D body scanning. SDIC captures high-precision anatomical scans of ears, wrists, and fingers from a diverse global population. The “4D” component adds the element of time, capturing how these body parts deform during motion .
2. Digital twin creation. Those scans are converted into high-fidelity virtual anatomical models that serve as the test environment .
3. AI-powered simulations. On those digital twins, researchers run thousands of AI-driven physics simulations, adjusting variables like earbud angle, sensor placement, and contact pressure. For the Galaxy Buds4 series, this meant over 10,000 simulations .
4. Robotic cross-validation. The simulation winners are physically verified using custom robotic testing rigs. This closes the loop, turning a traditionally subjective “how does this feel?” question into a measurable engineering metric .

How Computational Design Shaped Each New Wearable

Galaxy Buds4 Series: The “Blade Design” Was Engineered, Not Just Drawn

The earbuds are the most detailed case study for the new approach. Samsung analyzed hundreds of millions of ear data points—one official source pegs it at over 100 million global ear-shape data points—and ran more than 10,000 fit simulations to arrive at the new “Buds blade” identity .

The data told a clear story: the main earbud body needed to be slightly smaller, and the angle of rotation needed to shift by a few degrees. Those minor geometric changes produced a major gain in stability and all-day comfort across a much wider user base . The result is an ultra-sleek, ergonomic fit that stays secure even during vigorous movement, a claim now backed by objective robotic test data rather than a handful of subjective reviews .

Galaxy Watch8 Series: Fit Is a Health Sensor Problem

For a smartwatch, fit is not just about comfort; it determines sensor accuracy for heart rate, sleep, stress monitoring (including the new EDA sensor on the Watch8), and exercise tracking .

SDIC applied the same 4D scanning and AI simulation pipeline to optimize wrist contact. The data pushed the team to refine the cushion design across the entire Watch8 lineup. A key mechanical decision was extending the Dynamic Lug System—first introduced on the Galaxy Watch Ultra—to all Watch8 models, minimizing the gap between the watch body and the wrist to improve sensor reading consistency .

Galaxy Ring: A Universal Fit for Millions of Fingers

Rings are inherently tricky because a single rigid object must maintain precise sensor contact on fingers of vastly different shapes. Samsung’s computational design pipeline now builds digital twins of users’ fingers to optimize ring sizing, internal curvature, and PPG sensor placement for all-day health monitoring .

The goal is to ensure that biometric measurements such as heart rate and sleep staging remain accurate across the widest possible range of finger anatomies, without requiring users to become experts in ring sizing themselves .

What Samsung Plans Next: New Wearable Categories and AI Factories

Casalegno’s outlook, from Samsung’s official interview, points to three concrete directions .

• A self-reinforcing data advantage. As Samsung’s proprietary anatomical dataset grows, its custom AI tools will drive more accurate simulations and deeper insights, potentially widening its advantage over competitors that rely on smaller or less diverse training data .
• Entirely new wearable categories. Casalegno stated that expanding this methodology could “unlock exponential innovations down the line that lead to an entirely new category of wearables that can redefine the boundaries of user experience” . He did not specify the form, but the infrastructure—objective fit data on ears, wrists, and fingers—is now in place.
• From lab to factory. Separately, Samsung has announced a plan to transition all global manufacturing into fully AI-driven factories by 2030, with digital twin-based simulations integrated across the entire production chain . This suggests the same digital twin methodology that designs a Galaxy Bud today will eventually govern how it is manufactured on the line.

Samsung’s SDIC team also confirmed they are actively innovating the design process based on accumulated data and specialized AI, with the aim of introducing wearable products that combine ergonomics and AI more deeply than current products allow . For now, the Galaxy Buds4, Watch8, and Ring are the first physical proof that subjective fit panels are giving way to an objective, AI-verified standard.