Insider Brief
- Funded by the National Research Foundation of Korea, KAIST researchers have created a programmable robotic folding sheet that can change shape in real time, potentially boosting robot adaptability in unpredictable environments.
- The thin polymer sheet is embedded with micro metal resistors that function as heaters and sensors, enabling autonomous folding, temperature monitoring, and reconfiguration without external equipment.
- Tests showed applications including an adaptive robotic hand and a crawling sheet, with potential uses in disaster-response, medical devices, and space exploration tools.
Funded by the National Research Foundation of Korea, researchers at the Korea Advanced Institute of Science and Technology have developed a “field-programmable robotic folding sheet” that can change its shape in real time, a step that could expand the adaptability of robots in unpredictable environments.
The work, led by Professors Jung Kim and Inkyu Park at KAIST’s Department of Mechanical Engineering, applies the concept of field programmability to folding structures, allowing users to direct where, how, and how much the sheet folds without physical redesign. According to researchers, the sheet is made of a thin polymer embedded with a network of micro metal resistors that act as both heaters and sensors, enabling it to heat, bend, and measure its own folding state without external equipment.
“This study brings us a step closer to realizing ‘morphological intelligence,’ a concept where shape itself embodies intelligence and enables smart motion,” Kim stated. “In the future, we plan to evolve this into a next-generation physical AI platform with applications in disaster-response robots, customized medical assistive devices, and space exploration tools—by improving materials and structures for greater load support and faster cooling, and expanding to electrode-free, fully integrated designs of various forms and sizes.”
Using software that combines genetic algorithms with deep neural networks, the system can take a user’s instructions and execute precise folding patterns through controlled heating and cooling cycles. Closed-loop temperature control helps maintain accuracy and compensates for environmental changes, addressing the slow response that has limited other heat-based folding systems, KAIST indicated.
Researchers report tests included an adaptive robotic hand that could adjust its grip for different object shapes and a sheet configured for crawling or walking, showing potential for disaster-response machines, medical aids, and space tools that must adapt to their surroundings. Because the folding can be reprogrammed instantly, the same hardware can be reused for new tasks, reducing the need for complex redesigns.
The study, co-led by Dr. Hyunkyu Park of Samsung Advanced Institute of Technology and Professor Yongrok Jeong of Kyungpook National University, was published in the August 2025 edition of Nature Communications.
