MIT scientists use autonomous knitting to create soft assistive wearables

scientists streamline the design and fabrication of soft assistive wearables

Powered by compressed air, soft pneumatic actuators are the ideal candidate for assistive wearables and rehabilitative devices due to their light weight and sensing capabilities. However, due to a manual design and fabrication pipeline, the devices require time-consuming trial and error to see whether the designs will actually work.

A team of scientists from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has got past this hurdle with a pipeline called ‘PneuAct’ that uses an autonomous machine knitting process to design and digitally fabricate soft pneumatic actuators.

‘PneuAct uses a machine knitting process, not dissimilar to your grandma’s plastic needle knitting, but this machine operates autonomously,’ explain the CSAIL researchers in a recent press release. ‘A human designer simply specifies the stitch and sensor design patterns in software to program how the actuator will move, and it can then be simulated before printing. The textile piece is fabricated by the knitting machine, which can be fixed to an inexpensive, off-the-shelf rubber silicone tube to complete the actuator.’

images and main video courtesy of CSAIL

the applications

Using a yellow fabric, the scientists created tube-shaped actuator prototypes, which they likened to ‘banana fingers’. The prototypes included an assistive glove, an assistive sleeve, a soft hand, a sensorized gripper, an interactive robot, and a pneumatic quadrupedal robot that can walk forward and turn.

The knitted devices use conductive yarn for sensing, allowing them to ‘feel’ and respond to what they touch. For example, the team used the actuators to build a robot that sensed when it was touched specifically by human hands, and reacted to that touch.

Regarding the real-life applications of these actuators, the researchers say that the assistive glove could supplement finger muscle movement, minimizing the amount of muscle activity needed to complete tasks and motions. ‘This could hold a lot of potential for those with injury, limited mobility, or other trauma to the fingers,’ explains the team. Meanwhile, the assistive sleeve can help users bend joints such as their elbow or knee.

The actuators could also be scaled up to make a wearable robotic exoskeleton controlled by computer. ‘Using digital machine knitting, which is a very common manufacturing method in today’s textile industry, enables ‘printing’ a design in one go, which makes it much more scalable,’ says Yiyue Luo, MIT CSAIL PhD student and lead author of a new paper about the research. ‘Soft pneumatic actuators are intrinsically compliant and flexible, and combined with intelligent materials, have become the backbone of many robots and assistive technologies – and rapid fabrication with our design tool can hopefully increase ease and ubiquity.’

assistive sleeve

the next step

The prototypes from this study only explored tube shapes. For the next step in this research, the CSAIL team wants to explore actuators of different shapes. They will also investigate extending the tool to incorporate a task-driven, optimization-based design, where users can specify target poses and optimal stitch patterns that can be automatically synthesized.

‘Our software tool is fast and easy-to-use and accurately previews users’ designs, allowing them to quickly iterate virtually while only needing to fabricate once. But this process still requires some trial-and-error from humans. Can a computer reason about how textiles should be physically programmed in actuators to allow for rich, sensing-driven behavior? That’s the next frontier,’ says Andrew Spielberg, postdoctoral fellow in Materials Science and Mechanical Engineering at Harvard University, another author on the paper.

soft hand