Robots are rapidly becoming an integral part of daily life. The mechanizing of routine tasks has been underway for decades, with development making particularly remarkable progress over the past several years. Now, with the development robots that can closely interact with humans, sensing users’ needs and often relieving people of dangerous tasks, robotic technology is entering a new phase of intimacy and practicality.

Robots are rapidly becoming an integral part of daily life. The mechanizing of routine tasks has been underway for decades, with development making particularly remarkable progress over the past several years. Now, with the development robots that can closely interact with humans, sensing users’ needs and often relieving people of dangerous tasks, robotic technology is entering a new phase of intimacy and practicality.

The Robotic Touch

Cornell University engineers say they have developed a relatively inexpensive way to create soft, deformable robots that can be used to detect a variety of physical interactions, ranging from pats to punches to hugs. By deploying a USB camera within a robot, shadow movements created by hand gestures can be captured on the robot’s skin and classified with machine learning software. The ShadowSense technology offers a tactile sensing method that can be incorporated into many types of robots, particularly soft robots with translucent skin. The system detects human touch by capturing hand shadows on its surface. “Contrary to force/capacitive sensing arrays that are normally used for touch sensing, ShadowSense is a low-tech alternative that requires minimal hardware while achieving high-resolution sensing on different shape, material, deformable skin types,” explained Yuhan Hu, a Ph.D. candidate in Cornell’s mechanical engineering department.