New robot handles with care
Don’t you just hate it when your personal robot makes a mess instead of an omelet, crushing the eggs when it tries to pick them up? Well, a new five-digit, human-size robotic hand prototype could put an end to all that.
Thanks to optical and other sensors as well as background work on image processing, the robo-hand is dexterous and smart enough to pick up and turn a credit card around, politely accept a pen from a person and even grasp an egg without breaking the shell.
Today, robots typically man the factory floor, but future robots, envisioned for domestic duties, will require higher levels of manipulation and autonomy; this new development could help make that happen.
A robotic hand gently holds an egg. Developments in dexterity and cognition could help bring robots
from the factory floor into the home.
After all, manipulation has long been a major problem in robotics. The prototype is not simply an upgraded gripper, said Bruno Siciliano of the University of Naples in Italy. “Industry robots are pretty good at picking things up and putting them down,” he added. “If robots are to really transform life and work alongside humans, then they must be able to handle items just as humans can with their hands.”
As coordinator of the European Union-funded Dexmart project (Dexterous and autonomous dual-arm/hand robotic manipulation with smart sensory-motor skills: A bridge from natural to artificial cognition), Siciliano leads the team of robotics researchers from Saarland University in Saarbrücken, Germany, and the University of Bologna in Italy.
Capable of both powerful and delicate maneuvers, the Dexmart hand can touch, grasp and lift diverse objects and place them gently in a new position. The anthropomorphic device incorporates an innovative actuator system in which strong polymer strings in the handling apparatus are twisted by high-speed motors located in the “forearm” area.
Sensors were developed to measure joint angles, tendon forces and tactile interactions with objects. The device’s control system takes input from the optoelectronic sensors, then works out the synergies and actuates the finger movements.
Within the tactile sensor, advanced computational analysis of the captured light intensity inside a number of sensitive elements makes it possible to calculate the forces exerted on the object by the fingers and also whether the object is slipping out of the robot’s grasp.
“The success of the Dexmart hand is based on the integration of all these novel technologies and concepts – the sensors, the actuators, the control and learning mechanisms,” Siciliano said.
To give the robot its cognitive power, scientists from Karlsruhe University in Germany, Second University of Naples in Italy and UK technology firm OMG initially used advanced image processing technology to study the fine details of human hand movement.
Robots also must respond to situations appropriately and in ways that are not preprogrammed, Siciliano noted. “One of the goals of robotics, especially for companion and helper robots in society, is their ability to behave autonomously,” he said.
MORE FROM PHOTONICS MEDIA