Inspired by living organisms, soft robots are developed from intrinsically compliant materials, enabling continuous motions that mimic animal and vegetal movement¹. In soft robots, the canonical hinges and bolts are replaced by elastomers assembled into actuators programmed to change shape following the application of stimuli, for example pneumatic inflation^2,3,4,5. The morphing information is typically directly embedded within the shape of these actuators, whose assembly is facilitated by recent advances in rapid prototyping techniques^{6,7,8,9,10,11}. Yet, these manufacturing processes have limitations in scalability, design flexibility and robustness. Here we demonstrate a new all-in-one methodology for the fabrication and the programming of soft machines. Instead of relying on the assembly of individual parts, our approach harnesses interfacial flows in elastomers that progressively cure to robustly produce monolithic pneumatic actuators whose shape can easily be tailored to suit applications ranging from artificial muscles to grippers. We rationalize the fluid mechanics at play in the assembly of our actuators and model their subsequent morphing. We leverage this quantitative knowledge to program these soft machines and produce complex functionalities, for example sequential motion obtained from a monotonic stimulus. We expect that the flexibility, robustness and predictive nature of our methodology will accelerate the proliferation of soft robotics by enabling the assembly of complex actuators, for example long, tortuous or vascular structures, thereby paving the way towards new functionalities stemming from geometric and material nonlinearities.

受生物体的启发，软体机器人由本质上兼容的材料开发而成，能够模仿动物和植物的运动¹进行连续运动。在软体机器人中，标准铰链和螺栓被组装到执行器中的弹性体取代，执行器被编程为在施加刺激后改变形状，例如气动充气^2,3,4,5。变形信息通常直接嵌入这些执行器的形状中，这些执行器的组装得益于快速原型技术的最新进展^{6,7,8,9,10,11}. 然而，这些制造工艺在可扩展性、设计灵活性和稳健性方面存在局限性。在这里，我们展示了一种用于软机器制造和编程的全新一体式方法。我们的方法不依赖于单个零件的组装，而是利用逐渐固化的弹性体中的界面流动来稳健地生产整体式气动执行器，其形状可以轻松定制以适应从人造肌肉到抓手等各种应用。我们合理化了执行器组装过程中发挥作用的流体力学，并对它们随后的变形进行了建模。我们利用这种定量知识对这些软机器进行编程并产生复杂的功能，例如从单调刺激中获得的顺序运动。我们期望灵活性，