Fresh juice

2024-05-21

MIT's GelPalm brings a softer, more human-like touch to robotic gripping

In an ingenious reimagining of how robotic hands could grip and manipulate objects, researchers at MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) have developed a novel design that emphasizes the oft-overlooked palm. Their creation, dubbed GelPalm, features a gel-based flexible sensor that draws inspiration from the soft, deformable nature of human hands to achieve a highly sensitive, adaptive touch.

 

 

"We draw inspiration from human hands, which have rigid bones surrounded by soft, compliant tissue," explained Sandra Q. Liu, Ph.D., the lead designer and recent MIT graduate who developed GelPalm as a CSAIL affiliate and mechanical engineering doctoral student. "By combining rigid structures with deformable, compliant materials, we can better achieve that same adaptive talent as our skillful hands."

At the core of the GelPalm design is an advanced color illumination sensor embedded in the flexible, gel-based palm. Using red, green, and blue LEDs to illuminate objects combined with a camera to capture reflections, this sensor generates detailed 3D surface models that allow precise robotic interactions and envelopment of items.

But a palm is incomplete without its enablers – the fingers. To complement GelPalm, Liu's team developed robotic fingers called ROMEO (RObotic Modular Endoskeleton Optical) with similar flexible, sensor-integrated designs manufactured as single monolithic 3D-printed structures for cost-effectiveness.

A key aspect is the fingers' "passive compliance" – their ability to naturally adjust to forces without needing motors or extra control mechanisms. This passive compliance increases surface area contact to better envelop objects fully, a critical goal for robotic grasping.

"A major advantage is that we don't need extra motors or mechanisms to actuate the palm's deformation—the inherent compliance allows it to automatically conform around objects, just like our human palms do so dexterously," Liu said.

The researchers put GelPalm's capabilities to the test, comparing tactile sensing using different LED illumination systems and examining how well various palm configurations could grasp and stably hold objects. Slathering objects in paint and pressing them against rigid, structurally compliant, gel compliant, and the dual-compliant GelPalm design yielded clear results.

"Visually, and by analyzing the painted surface area contacts, it was clear having both structural and material compliance in the palm provided significantly more grip than the others," Liu stated. "It's an elegant way to maximize the palm's role in achieving stable grasps."

While integrating extensive tactile sensing into a flexible, compact palm remains a challenge, the potential applications are vast – from human-robot collaboration and biomedical uses to prosthetics with human-like sensing capabilities.

"The palm is almost completely overlooked in the development of most robotic hands," noted Matei Ciocarlie, Associate Professor at Columbia University. "This work is remarkable because it introduces a purposefully designed, useful palm that combines two key features, articulation and sensing, whereas most robot palms lack either."

For Liu, GelPalm represents crucial progress toward more advanced robotic hands that seamlessly blend soft and rigid elements with the tactile sensitivity seen in natural human hands.

"I hope we're moving toward more advanced robotic hands that blend soft and rigid elements with tactile sensitivity, ideally within the next five to 10 years," she said. "In developing GelPalm and the ROMEO fingers, I focused on modularity and transferability to encourage a wide range of designs. Making this technology low-cost and easy to manufacture allows more people to innovate and explore."

"As just one lab and one person in this vast field, my dream is that sharing this knowledge could spark advancements and inspire others," Liu added.

Ted Adelson, the John and Dorothy Wilson Professor of Vision Science and CSAIL member, is the senior author on the paper detailing this groundbreaking robotic hand design. With GelPalm, MIT has introduced a novel way for robots to handle objects with greater dexterity and sensitivity than ever before – bringing them one step closer to the remarkable grasping talents of the human hand.

Share with friends:

Write and read comments can only authorized users