Researchers are developing a comfortable, form-fitting fabric that recognizes the activities of its wearer, such as walking, running and jumping

Using a new manufacturing process, MIT researchers have produced smart textiles that conform snugly to the body so they can sense the posture and movements of the wearer.

By incorporating a special type of plastic yarn and using heat to melt it slightly – a process called thermoforming – the researchers were able to dramatically improve the accuracy of pressure sensors woven into multi-layer knitted textiles, which they call 3DKnITS.

They used this process to create a “smart” shoe and mat, then built a hardware and software system to measure and interpret data from pressure sensors in real time. The machine learning system predicted the yoga movements and poses performed by an individual standing on the smart textile mat with approximately 99% accuracy.

Their manufacturing process, which takes advantage of digital knitting technology, allows for rapid prototyping and can be easily adapted for large-scale manufacturing, says Irmandy Wicaksono, research assistant at the MIT Media Lab and lead author of a paper presenting 3DKnITS.

The technique could have many applications, especially in health care and rehabilitation. For example, it could be used to produce smart shoes that track the gait of someone learning to walk again after an injury, or socks that monitor the pressure on a diabetic patient’s foot to prevent ulcers from forming. .

“With digital knitting, you have this freedom to design your own patterns and also to embed sensors into the structure itself, so it becomes seamless and comfortable, and you can develop it depending on the shape of your body,” says Wicaksono.

He co-authored the paper with MIT undergraduate students Peter G. Hwang, Samir Droubi, and Allison N. Serio under the Undergraduate Research Opportunity Program; Franny Xi Wu, a recent graduate of Wellesley College; Wei Yan, assistant professor at Nanyang Technological University; and lead author Joseph A. Paradiso, Alexander W. Dreyfoos Professor and Director of the Responsive Environments group within the Media Lab. The research will be presented at the IEEE Engineering in Medicine and Biology Society conference.

“Some of the first pioneering work on smart fabrics took place at the Media Lab in the late 90s. Materials, integrable electronics, and manufacturing machinery have advanced tremendously since then,” says Paradiso. “Now is the perfect time to see our research flow back into this area, for example through projects like Irmandy’s – they point to an exciting future where sensing and functions flow more fluidly into materials and opens up huge possibilities.”

Knitting know-how

To produce a smart textile, researchers use a digital knitting machine that weaves together layers of fabric with rows of standard and functional yarns. The multi-layer knitted textile is composed of two layers of conductive yarn knit sandwiched around a piezoresistive knit, which changes resistance when pressed. Following a pattern, the machine sews this functional thread all over the textile in horizontal and vertical rows. Where the functional fibers intersect, they create a pressure sensor, Wicaksono explains.

But the yarn is soft and supple, so the layers shift and rub against each other as the wearer moves. This generates noise and causes variability that makes pressure sensors much less accurate.

Wicaksono found a solution to this problem while working at a knitting factory in Shenzhen, China, where he spent a month learning how to program and maintain digital knitting machines. He observed workers making sneakers using thermoplastic yarns that would begin to melt when heated above 70 degrees Celsius, which slightly hardens the textile so it can retain a precise shape.

He decided to try integrating fiber fusion and thermoforming into the smart textile manufacturing process.

“Thermoforming really solves the noise problem because it hardens the multi-layered textile in a single layer by squeezing and melting the whole fabric, which improves precision. This thermoforming also allows us to create 3D shapes, such as a sock or shoe, which makes it fit the precise size and shape of the user,” he says.

Once he perfected the manufacturing process, Wicaksono needed a system to accurately process pressure sensor data. Since the fabric is knitted like a grid, he designed a wireless circuit that scans the rows and columns on the fabric and measures the resistance at each point. He designed this circuit to overcome artifacts caused by “ghost” ambiguities, which occur when the user presses two or more distinct points simultaneously.

Inspired by deep learning techniques for image classification, Wicaksono designed a system that displays pressure sensor data as a heatmap. These images are fed to a machine learning model, which is trained to detect the posture, pose, or movement of the user based on the heat map image.

Business Analysis

After the model was trained, it could classify the user’s activity on the smart mat (walking, running, doing push-ups, etc.) with 99.6% accuracy and recognize seven yoga poses with 99.6% accuracy. 98.7%.

They also used a circular knitting machine to create a form-fitting smart textile shoe with 96 pressure-sensing points distributed throughout the 3D textile. They used the shoe to measure the pressure exerted on different parts of the foot when the wearer kicked a soccer ball.

The high precision of 3DKnITS could make them useful for prosthetic applications, where precision is essential. A smart textile liner could measure the pressure exerted by a prosthetic limb on the socket, allowing a prosthetist to easily see how well the device fits, says Wicaksono.

He and his colleagues are also exploring more creative applications. In collaboration with a sound designer and a contemporary dancer, they developed a smart textile mat that pilots musical notes and soundscapes based on the dancer’s steps, to explore the two-way relationship between music and choreography. This research was recently presented at the ACM Creativity and Cognition conference.

“I learned that cross-disciplinary collaboration can create truly unique applications,” he says.

Now that the researchers have demonstrated the success of their fabrication technique, Wicaksono plans to refine the circuit and machine learning model. Currently, the model needs to be calibrated for each individual before it can rank actions, which is a time-consuming process. Removing this calibration step would make 3DKnITS easier to use. The researchers also want to run tests on smart shoes outside of the lab to see how environmental conditions such as temperature and humidity affect sensor accuracy.


This research was supported, in part, by the MIT Media Lab Consortium.

Title of the article: “3DKnITS: Three-dimensional digital knitting of a smart textile sensor for activity recognition and biomechanical monitoring”

Comments are closed.