A research team led by Professor Keehoon Kim and Ph.D. candidate Jaehyun Park from Pohang University of Science and Technology (POSTECH) has developed groundbreaking haptic technology that could revolutionize industrial safety and efficiency.
The team's innovation addresses a critical challenge in high-risk industrial environments such as factories and steel mills. While robotic automation continues to advance, many complex tasks still require human intervention. However, operating robots remotely can be challenging, with even minor mistakes potentially leading to accidents.
To solve this problem, the researchers created two specialized haptic devices: the POstick-KF (Kinesthetic Feedback) and POstick-VF (Visuo-tactile Feedback). These tools allow operators to literally feel what the robot experiences through their fingertips while controlling machines from a safe distance.
The POstick-KF transmits precise force changes experienced by the robot, while the POstick-VF combines visual and touch-based cues for broader workspace applications. Both devices are shaped like familiar tools, making them intuitive even for first-time users.
Simulation experiments demonstrated impressive results, with users achieving higher manipulation accuracy and significantly fewer collisions compared to conventional control methods. The POstick-VF particularly excelled as a training tool, with users showing marked improvement in proficiency over time.
The system further enhances safety through integration with digital twin technology, allowing operators to rehearse complex operations in virtual environments before executing them in real-world settings. Augmented reality features provide additional visual cues that improve user immersion and concentration.
"Our technology enables tasks requiring human dexterity to be performed more safely and precisely in collaboration with robots," said Professor Kim. "We hope this will enhance safety in industrial sites and reduce the burden on workers."
The research, supported by POSCO Holdings, was recently published in IEEE Transactions on Industrial Informatics and represents a significant advancement in human-robot collaboration for hazardous industrial environments.