Robotic Hand Can Operate In the Dark

Columbia University engineers have designed a highly dexterous robotic hand with advanced tactile sensitivity that allows it to handle objects without needing to see them. 

The new system was designed to emulate the sensitivity and dexterity of human hands, basing its capabilities on touch rather than visual understanding. By combining touch sensors with motor learning algorithms, the team’s system was able to achieve high dexterity levels in trials.

To demonstrate the design’s efficacy, the team had the hand rotate an uneven object while maintaining a secure hold. The robotic hand showed successful results, capable of completing the task solely using touch and without needing any visual feedback. 

Creating robotic hands with “true” dexterity has typically proven challenging for researchers. Current designs include suction cups or grippers to pick up and handle items, though there is a desire for designs to allow robots to undertake more detailed, complex tasks. 

The new design’s capability to operate in low, or no, lighting could also prove useful for applications throughout industries, and expands its potential use cases.

“While our demonstration was on a proof-of-concept task, meant to illustrate the capabilities of the hand, we believe that this level of dexterity will open up entirely new applications for robotic manipulation in the real world,” said Matei Ciocarlie, study author. “Some of the more immediate uses might be in logistics and material handling, helping ease up supply chain problems like the ones that have plagued our economy in recent years, and in advanced manufacturing and assembly in factories.”