Skelmet focuses on developing 3D Custom-fit technologies. If you are interested in collebration and investment, please contact us. We’d like to share more information with you.
Table of Contents
Why We Started This Project
This section serves as the background explaining why we started this project.
First, you have to know the fact that everybody is unique. Here the uniqueness refers to the 3D body shapes. Although this is quite obvious to naked eyes, there’s also a science behind it, called Anthropometry, which is dedicated to studying the measurements and proportions of the human body. Researchers have been using 3D scanners to take more accurate body measurements since the 2000s. They collect 3D models of human bodies and run statistical analysis. These quantified results help designers and manufacturers improve the comfort and functionality of their wearable gear products.
Smartphones with 3D scanning capability are becoming popular. Apple published iPhone X in 2017. It’s the first iPhone that has the FaceID function. FaceID uses the TrueDepth camera (a 3D scanner) to authenticate user ID. And later Apple opened the API to developers so that we could develop the 3D scan App with it. Now all the iPhones after the iPhone X, as well as iPad Pro, have 3D scan capability. 3D scanning is not limited to labs anymore, and everybody could use it on a daily basis.
Industrial 3D printing technologies have become good enough for production. There are many types of 3D printing technologies. Previously, people use 3D printing as prototyping tools or maker tools. After years of development, more companies have published revolutionary production-focused 3D printing solutions. People begin to use 3D printers to make final products because it’s stronger, faster, and cheaper.
We think why not use the 3D scanner to take the 3D measurement and use 3D printers to manufacture custom-fitted products? However, when we re-examine the existing systems for solving fitting problems, we think the current way of design, manufacturing, and sales out-of-date. Most designers don’t have any experience or resources to design based on the 3D model. They still rely on their feels and experiences. Only big brands could afford the cost of making serious anthropometry study and maintain a database. And the manufacturing process and sale are also not compatible with our idea. So we decide to found Skelmet to change this.
We want to build a new business model that uses 3D scanning and 3D printing as tools for mass-customization. Customers would use their smartphone to take a 3D scan and send their 3D body scan to our cloud server. Then they could order custom-fitted wearable products, such as sunglasses, goggles, etc., on our website and shopping App. We will develop algorithms that automatically design the 3D CAD model of the custom-fitted product for each user. And we will build systems control all the 3D printers to manufacture these products.
Mass-customization is very different from mass-production in the way of design, manufacture, and sale. Here’s the comparison:
|Mass-customization (Skelmet)||Mass-production (others)|
|Design||Designers and Engineers create algorithms that design the custom-fitted product||Designers create industrial designs, sketches, and conceptual drawings|
|The algorithms produce 3D models for printing every time customer place an order||Engineers create 3D models in CAD Software, which do not change until the next version came out.|
|Make design decisions based on statistical data and each user’s 3D data.||Make design decisions based on experience or use standard body models as reference.|
|Guarantee perfect fit for most users (between 2 sigma to 3 sigma)||Only guarantee perfect fit for the standard user (statistical average)|
|MFG||Use 3D printing as the standard manufacturing process.||Use injection molding as the standard manufacturing process.|
|Change the design by changing the algorithms, which can be updated at any time.||Can not change design unless the mold is changed, which cost a lot of money and time|
|Made-to-order, no minimum order quantity required to initiate production||Mass-production requires MOQ to initiate production for each batch.|
|Require much less deposit for new products. Only store parts that are not 3D printed||Require a large amount of money to create new products. Must prepare every part to sell|
|Do not occupy much storage space.||Need large inventory storage space|
|Send directly to end-user||Need distributor networks to handle inventory and deposit|
|Require fewer workers because 3D printers simplified the process||Require much more workers to operate the machines for every simple process|
|Set up local 3D printing factories, creating jobs for local communities||Job and factory locate at other countries, damaging local job opportunities|
|Sales||Sell products directly to customers, reduce the cost of extra layers||Usually rely on distributor networks, adding additional cost|
|No need to try on in-store because the product will actively fit the customer, not vice versa||Big brands spend billions on maintaining stores for try-on purposes, which is paid by customer’s money.|
|Almost no return because every pair is custom-fitted for the user||Online sales suffer a high return rate due to poor fitting.|
|Produce high-quality sunglasses at affordable prices||Amazon is selling cheap foreign-made sunglasses with low qualities|
“3D Custom-fit” is the term we created to refer to the technologies we are using during the mass-customization process. For your better understanding, we divide it into several parts:
3D Scanning and 3D Model Analysis Algorithms
The 3D scanning module contains three parts, the laser gird projector, the receiver, and the RGB camera. They produce point cloud data and the RGB video stream. When you hold the scanner and move it around the object, the scanner records multiple frames of these data at different locations and angles. And SLAM (simultaneous localization and mapping) algorithm is used to stitch all the frames together, giving us a 3D mesh model with texture.
Then we need to perform the face landmarks detection on the 3D mesh model so that the computer would understand where are the eyes and where is the nose etc. This will provide enough information for the parameter adjustment algorithm to control the parametric modeling algorithms. The are many options for the face landmarks detection, the most effective one is using deep learning, which is quite mature nowadays.
Parametric Modeling Algorithms
Parametric modeling algorithms refer to the algorithms that take several parameters as input and generate the complete 3D model of the product as the output. By changing the parameters, the product design will change accordingly. Building the parametric modeling algorithms is the most important part of the 3D Custom-fit workflow because the algorithm is the product itself that determines all the designs and specs of the product.
This concept of parametric modeling is very confusing because some other CAD software has occupied this phrase. However, the difference between them is huge. Our parametric modeling algorithms are designed to be adjusted primarily by computer, while the old one refers to CAD software that needs to be operated by engineers when changing the parameter values. In a nutshell, when we create parametric modeling algorithms, we focus on how to automate the design process, reducing human interference and letting the computers do the job.
Currently, we are developing these parametric modeling algorithms on the Grasshopper platform, which has been widely used by architects for programmatic modeling and generative design. Other CAD software companies begin to publish similar products like Grasshopper in recent years. We think this is a good trend because competition means improvement.
As a new way of making things, 3D printing offers much more freedom in the design, and it is also influencing the business model. Designers and engineers need to master new tools like the Grasshopper to build 3D Custom-fit projects. We hope, in the future, Skelmet could bring more attention to this field and more talented people could join us.
Parameter Adjustment Algorithms
After we create the parametric modeling algorithms, we need to give them the correct parameters so that the custom-designed product would fit perfectly for the user. This means we need to establish a mapping relation between the 3D scan and the parameters.
We solve this problem with three methods: 1. Let engineers manually set the right parameters according to their knowledge and experience. 2. Write simple and robust mapping functions without human interference. 3. Use end-to-end machine learning when having enough training sample sets. In practice, these methods are combined together to achieve an ideal fit for the user.
Finally, every product is different in terms of parametric modeling algorithms, and the same is true with the parameter adjustment algorithms. And the more orders we accumulated the more accurate the parameter adjustment algorithms will become. So we’ll constantly refine the parameter adjustment algorithms and collect feedback from users.
Order and Manufacturing Management System
From our experience, the order and manufacturing management system are also critical to build a successful mass-customization business. Because when hundreds of orders are being processed, you have to track the production process of every part so that they don’t turn into a mess.
AI and Data
AI refers to the phrase of artificial intelligence. Currently, the last AI technologies are deep learning, neural networks, etc. AI has been the focal point of the media and entrepreneur area, so I’m listing some examples of how we implement the AI in our workflow.
The first application of AI in our workflow is helping us detect head landmarks, such as eyes, ears, noses, etc. We use CNN to locate important facial landmarks on the 3D model. The second application is creating end-to-end parameter adjustment algorithms. We usually use machine learning algorithms to do the job. The third is to study the design and the aesthetical preference, for example creating algorithms that would produce a design that looks good on the customer’s face.
As we received orders, we accumulated a lot of 3D models from customers. We are building the data analysis pipeline of these 3D models. This will provide very useful insight into how to design better wearable gears.
In my opinion, products that could benefit from 3D Custom-fit technologies include the following categories:
- Glasses: sports sunglasses, fashion sunglasses, etc
- Sports goggles: ski goggles, motocross goggles, etc
- Respirators masks: mask for medical use, mask sealer, respirators, etc
- Helmets: cycling helmets, motorcycle helmets, skiing helmets, etc
- Work with other electronic systems: VR/AR goggles, helmet for aircraft pilots, EEG (electroencephalogram) devices, etc
The list is definitely not covering all the products that could use 3D Custom-fit technology. I only listed products worn on the head here because we focus on developing products and technologies around the head right now. And I am going to explain why 3D Custom-fit can help to solve the fitting problems and potentially adding new features in designing these products.
When people design these wearable gears, they usually solve the fitting problems by setting up a size system, offering S, M, L, XL size, etc. However, manufacturing multiple sizes and handling stocks and logistics require a large amount of money, especially for expansive electronic products like VR/AR goggles. So usually the seller only offers one or two sizes at most. In the end, customers often complain about the products of their sizes are out-of-stock.
Designers often create complicated adjustable structures so the users could adjust the products on their own. This increases the probability of failure and also additional costs for extra parts and assembly fees. And most importantly, this increases the weight of wearable gears, such as the thick foam on the skiing goggles. For some wearable gears, users are very sensitive to the weight.
When we use 3D Custom-fit technology to design wearable products, we can eliminate these problems by creating custom-fitted products. We could use a simpler structure and reduce weight dramatically. We could abandon the size system and adjust products in a stepless fashion. Customers will not be required to figure out what sizes they need.
In theory, 3D Custom-fit technologies should provide better comfort and increase the functionality of the wearable gear. But in practice, there’s a lot of restrictions and factors limit its application. Here, I’ll list some of the things you should consider when start using 3D Custom-fit into products.