Customize Your Own 3D-Printable Robotic Hand

Watch how researchers at MIT craft customizable robotic hands using a new interactive design pipeline.

“One of the most exciting things about this pipeline is that it makes design accessible to a general audience. Rather than spending months or years working on a design, and putting a lot of money into prototypes, you can have a working prototype in minutes,” says lead author Lara Zlokapa  .

Transcript

00:00:00 SPEAKER: Robotic manipulators are used for a variety of tasks in all different fields, from picking and sorting, to assisting with more complex and detailed procedures. The problem? It can take months to manually design a custom manipulator. Each iteration could require new parts that must be designed and tested from scratch. That is, until now. Researchers from MIT have developed

00:00:22 a new interactive design pipeline that streamlines and simplifies the process of crafting a customized robotic hand. LARA ZLOKAPA: Part of the big question that we're answering is, is the human hand really the ideal hand for doing everything? And with this modular pipeline, we can make robot hands that resemble the human hand, but also robot hands that look like anything else. And then given some set of tasks,

00:00:47 we can answer the questions like, is the human hand with five fingers arranged this way, is that ideal? SPEAKER: Akin to building with LEGOs, the team designed and easy-to-use 3D interface for robotic hand design so that a user is able to construct a robotic manipulator from a set of modular components that can be adjusted and tweaked tailoring to a specific task and then easily integrate tactile sensors into the final design.

00:01:16 The tactile sensors needed for their pipeline to work are incorporated through a knitted glove that fits snugly over the robotic hand. These sensors enable the manipulator to perform complex tasks such as picking up delicate items or using tools. LARA ZLOKAPA: So this project has been a proof of concept that this sort of pipeline and modularity and incorporating the sensors works, and now we're working on improving the sensors.

00:01:39 So we have more accurate grasp and touch sensing. We're working on improving the manipulators to make them a little more precise in their motion. And we're also working on developing that algorithm that answers the question of, what is the most optimal hand? Is the human hand really the best one? [MUSIC PLAYING]