May 15 2018
Touching and grasping objects are remarkably complex tasks, an area where present-day robots are still inept. Chief investigator Jukka Häkkinen, PhD, and post-doctoral researcher Jussi Hakala, DSc (Tech), have formulated an imaging technique for measuring human touch.
“When humans grasp something, a very complicated subliminal calculation takes place about which muscles are needed in the process, as well as which neural pathways are used to control them and at what intensity. In the field of psychology, these brain mechanisms have been extensively studied,” says Jukka Häkkinen, a psychologist and chief investigator at the University of Helsinki. He is one half of the pair behind the Grasp Sense technique.
With the assistance of depth and thermal cameras, Grasp Sense can be used to measure the heat signature remaining on the surface of objects after being touched by humans. Data gathered on human touch can be exploited in robotics. So far, grasping and touching has been a challenging area for the development of robots to be used, for instance, in healthcare and logistics.
“Robots need to know exactly the object’s three-dimensional structure, material and weight distribution, whereas humans have the ability of intuitive grasp. Our goal is to transfer human skills to robots,” says Jussi Hakala, a post-doctoral researcher and the other developer of the Grasp Sense. Hakala’s research has concentrated on 3D imaging and display technologies.
Challenges in robotics are linked to whether a robot can keep its grip on an object and, on the other hand, not crush the object. From the standpoint of the care robots of the future, this aspect is becoming progressively important.
“Their grip must be pleasant, unwavering and reliable,” notes Häkkinen.
Origins in Eye Tracking
Previously, Häkkinen led a research project funded by the Academy of Finland that concentrated on measuring eye movements while doing grasping tasks.
I examined how various grasping tasks impact the orientation of eye movements. The term 'just in time selection' is used in connection with eye movements. In other words, the eyes are focused on collecting the exact information required for the next 500 milliseconds.
Jukka Häkkinen
This resulted in the idea of also measuring the manually accomplished actions during grasping tasks.
“Video-based methods are not accurate enough, so my first thought was to use finger paint,” Häkkinen laughs.
Later, he thought about using heat signatures left by touch, and the numerous applications for the technique.
Support for Designing Utility Articles & Promoting Hospital Hygiene
Besides robotics, the Grasp Sense technique could be applied to developing numerous utility articles. Touch data might be beneficial in designing objects that must be ergonomic, pleasant, and precise to use.
According to Häkkinen, the same technology could also be used to develop models for hospital hygiene by fixing cameras on hospital ceilings. With the aid of thermal cameras, models revealing the most touch-intensive surfaces could be produced, making it easier and gradually more effective to keep them clean.
Researchers teach robots to touch | University of Helsinki
Video credit: Helena Hiltunen