Traditional robotic hands typically require precise environmental information and complex programming to successfully grasp objects. In contrast, humans can pick up items without needing exact positional data, largely thanks to the natural compliance of our hands.
The CREATE Lab at EPFL (École Polytechnique Fédérale de Lausanne) has taken inspiration from this human capability to develop the ADAPT hand—a robotic hand that uses compliant materials rather than complex algorithms to achieve dexterous manipulation.
"As humans, we don't really need too much external information to grasp an object, and we believe that's because of the compliant—or soft—interactions that happen at the interface between an object and a human hand," explains Kai Junge, a PhD student in the School of Engineering's Computational Robot Design & Fabrication (CREATE) Lab, led by Professor Josie Hughes.
The ADAPT hand's design is remarkably efficient. While traditional robotic hands would require a motor for each joint, the ADAPT hand uses only 12 motors housed in the wrist to control its 20 joints. The remaining mechanical control comes from springs that can be adjusted for stiffness and a silicone 'skin' that can be added or removed. This strategically distributed compliance allows the hand to adapt to various objects without additional programming.
In testing, the hand achieved a 93% success rate in grasping 24 different objects, from small bolts to bananas, with movements that mimicked human grasping patterns with 68% similarity. The researchers validated this robustness through over 300 grasp experiments, comparing the compliant hand against a rigid version.
The EPFL team is now building on this success by integrating closed-loop control elements, including pressure sensors in the silicone skin and artificial intelligence. "A better understanding of the advantages of compliant robots could greatly improve the integration of robotic systems into highly unpredictable environments, or into environments designed for humans," Junge summarizes.
This breakthrough, published in Nature Communications Engineering, demonstrates how biomimetic compliance can enable more intuitive and adaptable robotic manipulation without relying on complex programming—potentially transforming how robots interact with human environments.