Engineers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed X-Hinges, design software capable of creating and 3D printing objects with interactive functionality. Thanks to built-in sensors, these objects can detect human touch. It is this touch that triggers a reaction.
We already know how to integrate sensors and conductive traces into 3D printed objects. A common problem, however, is that these sensors and the objects themselves are often made of the same material. As a result, they emit very similar signals, making communication very difficult. The risk of error is therefore high.
The glove on the right was 3D-printed and communicates with the robotic hand on the left
To address this issue, engineers at MIT CSAIL developed X-Hinges, which allow two different materials to be integrated into the object in question. One filament is used for the sensors and is optimized to transmit the strongest possible signal. A second filament is used for the conductive traces. This ensures that there is no interference.
X-Hinges, An Easy-to-Use Design Solution
The software is designed to be very user-friendly. You can assemble an object using geometric shapes (cylinder, rectangle, thin outline, etc.) and then choose the movements of certain parts along three axes (compression, up-down, or side-to-side). The object in question is not limited to a single movement.
Jiaji Li, a postdoctoral researcher in electrical engineering and computer science (EECS) at MIT and a researcher at CSAIL, explains: “It’s kind of like adding a conscious element to everyday objects. In the same way an AI agent is programmed to make certain decisions based on our instructions, these creations have built-in sensing to adaptively react to human touch.”
The software is easy to use: you can select from several shapes to design an object
Initial Conclusive Results
Engineers have 3D printed several objects designed using X-Hinges, and the results are positive. For example, they created a glove that conforms to the hand and transmits finger movements in real time to a humanoid hand, allowing a robot to learn how to grasp objects. In one demonstration, the hand is seen stacking wooden cubes.
They’ve also designed a foldable lamp whose brightness changes when you pinch it, as well as a type of scale that recognizes the object placed on it.
The idea is that our everyday objects can perform a specific task when we interact with them. It’s hard to imagine a water bottle doing anything other than holding liquid, but why not?
This stand can detect an object placed on it
Challenges to Overcome
In the meantime, the team continues to face certain obstacles. The most significant one involves calibration. The layout of the electrical components varies with each print. This means that two identical objects cannot yet provide the same sensor readings. Currently, the engineers use a computer vision system to recalibrate the parameters.
Ultimately, they want to integrate this calibration directly into the object. The next step, Jiaji Li explains, is to combine the two into a single print: “it’s actuation and sensing born together in the same fabrication process, opening the door to new physical platforms for embodied intelligence and AI agents.”
You can find more information about this project HERE. What do you think of X-Hinges? Let us know in a comment below or on our LinkedIn or Facebook pages! Plus, don’t forget to sign up for our free weekly Newsletter to get the latest 3D printing news straight to your inbox. You can also find all our videos on our YouTube channel.
*All photo credits: CSAIL/MIT