MIT Finger-Shaped Sensor Lets Robots Grasp, Manipulate Objects

The camera-based sensor provides high-resolution tactile sensing and could expand robotic grasp and object-handling capabilities

Scarlett Evans, Assistant Editor, IoT World Today

October 17, 2023

2 Min Read
The GelSight Svelte sensor developed by MIT researchers.
MIT

MIT researchers have created a new finger-shaped sensor that can expand robotic tactile capabilities and enable more dexterous designs.

The GelSight Svelte sensor features two mirrors that reflect and refract light to a single camera at the base of the design, allowing it to “see” along the entire length of the finger.

The sensor is encased in a flexible, silicone “skin,” with the camera identifying objects that come into contact with the robotic hand by monitoring any deformations to the skin. 

“The camera views the back of the skin from the inside; based on the deformation, it can see where contact occurs and measure the geometry of the object’s contact surface,” the MIT team said. “The red and green LED arrays give a sense of how deeply the gel is being pressed down when an object is grasped, due to the saturation of color at different locations on the sensor.

“The researchers can use this color saturation information to reconstruct a 3D depth image of the object being grasped.”

In tests, the team integrated the GelSight Svelte sensors into a robotic hand, allowing it to grasp and handle objects, with the team noting increased manipulation capabilities with the novel design than with traditional models. 

“Because our new sensor is human finger-shaped, we can use it to do different types of grasps for different tasks,” said Alan (Jialiang) Zhao, lead author of a study on the design. “Our sensor really opens up some new possibilities on different manipulation tasks we could do with robots.”

Related:Toyota Revolutionizing How Robots Are Taught

Next, the researchers said they plan to make the GelSight Svelte design more human-like in its movements, allowing the sensor to bend at the joints and increase the scope of its handling capabilities.

The team’s research is supported, in part, by the Toyota Research Institute. The findings from the GelSight Svelte study will be presented at the IEEE Conference on Intelligent Robots and Systems.

About the Author

Scarlett Evans

Assistant Editor, IoT World Today

Scarlett Evans is the assistant editor for IoT World Today, with a particular focus on robotics and smart city technologies. Scarlett has previous experience in minerals and resources with Mine Australia, Mine Technology and Power Technology. She joined Informa in April 2022.

Sign Up for the Newsletter
The most up-to-date news and insights into the latest emerging technologies ... delivered right to your inbox!

You May Also Like