KAIST

<(From left) Prof. Inkyu Park from KAIST,  Prof. Yongrok Jeong from Kyungpook National University, Dr. Hyunkyu Park from KAIST and Prof.Jung Kim from KAIST>

Folding structures are widely used in robot design as an intuitive and efficient shape-morphing mechanism, with applications explored in space and aerospace robots, soft robots, and foldable grippers (hands). However, existing folding mechanisms have fixed hinges and folding directions, requiring redesign and reconstruction every time the environment or task changes. A Korean research team has now developed a “field-programmable robotic folding sheet” that can be programmed in real time according to its surroundings, significantly enhancing robots’ shape-morphing capabilities and opening new possibilities in robotics.

KAIST (President Kwang Hyung Lee) announced on the 6th that Professors Jung Kim and Inkyu Park of the Department of Mechanical Engineering have developed the foundational technology for a “field-programmable robotic folding sheet” that enables real-time shape programming.

This technology is a successful application of the “field-programmability” concept to foldable structures. It proposes an integrated material technology and programming methodology that can instantly reflect user commands—such as “where to fold, in which direction, and by how much”—onto the material's shape in real time.

The robotic sheet consists of a thin and flexible polymer substrate embedded with a micro metal resistor network. These metal resistors simultaneously serve as heaters and temperature sensors, allowing the system to sense and control its folding state without any external devices.

Furthermore, using software that combines genetic algorithms and deep neural networks, the user can input desired folding locations, directions, and intensities. The sheet then autonomously repeats heating and cooling cycles to create the precise desired shape.

In particular, closed-loop control of the temperature distribution enhances real-time folding precision and compensates for environmental changes. It also improves the traditionally slow response time of heat-based folding technologies.

The ability to program shapes in real time enables a wide variety of robotic functions to be implemented on the fly, without the need for complex hardware redesign.

In fact, the research team demonstrated an adaptive robotic hand (gripper) that can change its grasping strategy to suit various object shapes using a single material. They also placed the same robotic sheet on the ground to allow it to walk or crawl, showcasing bioinspired locomotion strategies. This presents potential for expanding into environmentally adaptive autonomous robots that can alter their form in response to surroundings.

Professor Jung Kim stated, “This study brings us a step closer to realizing ‘morphological intelligence,’ a concept where shape itself embodies intelligence and enables smart motion. 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.”

This research, co-led by Dr. Hyunkyu Park (currently at Samsung Advanced Institute of Technology, Samsung Electronics) and Professor Yongrok Jeong (currently at Kyungpook National University), was published in the August 2025 online edition of the international journal Nature Communications.
 ※ Paper title: Field-programmable robotic folding sheet
 ※ DOI: 10.1038/s41467-025-61838-3

This research was supported by the National Research Foundation of Korea (Ministry of Science and ICT). (RS-2021-NR059641, 2021R1A2C3008742)

Video file:
 https://drive.google.com/file/d/18R0oW7SJVYH-gd1Er_S-9Myar8dm8Fzp/view?usp=sharing