Magnetic soft robots have the potential to be used in biomedical applications, such as targeted drug delivery, minimally invasive surgery, and on-chip tissue manipulation, due to their untethered operation, rapid actuation, and physical adaptability. However, real-time control of these robots is challenging because of their inherent nonlinear dynamics, fabrication imperfections, and complex interactions with external magnetic fields. In this work, we present a model-free controller that uses Proximal Policy Optimization-collected experience and a hybrid architecture, EpisodicMemNet. A memory module returns stored actions for angle-matched states, while a multi-head network predicts actions when no match is found. In experimental validation on two magnetic soft robots, a four-legged dual-stem H-frame (6 × 10 mm) and a three-legged asymmetric variant (8 × 11 mm), an adaptive two-tier memory maintained a median lookup time of approximately 1.2 ms, and EpisodicMemNet achieved 87.4% balanced accuracy and 93.5% top-2 accuracy while sustaining 2-Hz real-time control. Furthermore, user-guided tasks such as target navigation, obstacle avoidance, and ramp climbing confirmed reliable performance and adaptability despite the system’s nonlinearities and data sparsity. The proposed method thus not only overcomes the limitations of traditional simulation-based and model-specific approaches but also paves the way for scalable, experience-driven control solutions in soft robotic applications.

PneuNet, consists of a series of interconnected chambers embedded within a soft elastomer material, can exhibit diverse deformations. 3D printing allows for precise control over both material combinations and geometrical configurations, enabling the fabrication of PneuNets with complicated structures and multifunctionality. However, the increased freedom in material and structures introduced by 3D printing also presents significant challenges for modeling and design, including material nonlinearities, complex cross-sections and varying initial curvatures. In this work, we develop 3D-printed PneuNets with varying initial curvatures and cross-sections demonstrating finite deformation with multiple complete turns. To model the helical shape, we establish a general nonlinear framework based on the minimum potential energy method. The model is validated by PneuNets with various material combinations and geometrical configurations across a range of constitutive models including Mooney-Rivlin, Ogden, Neo-Hookean and Yeoh models. Results show that the nonlinear model, especially the Mooney–Rivlin model, accurately captures the deformation without any fitting parameters, achieving an$R^{2}$value of 0.975, compared to 0.017 for the linear model. Based on the validated model, PneuNets are inverse-designed to achieve desired spatial deformations. Their dynamic responses and payload capacities are also evaluated. We design a 3D-printed octopus with tentacles composed of PneuNets, capable of mimicking the grasping and movement of a real octopus. Additionally, we demonstrate the multifunctional capabilities such as fluid transition and sensing. This study lays a solid foundation for the design and application of 3D-printed PneuNets.

Hard-magnetic soft robots can form diverse soft-body deformation modes and safely interact with their surrounding environment, offering great promise in performing complex functions. Although there have been significant theoretical developments of small-scale soft robots, the design of centimeter-scale soft robots with larger workspace and output forces remains elusive. In this paper, we develop an analytical model to automatically design centimeter-scale hard-magnetic soft robots that exhibit desired configurations, enabled by programming the magnetization profile. The model considers the varying magnetization profile, gravity effect and large deformation, and directly relates the material, geometric and loading parameters to the final configurations. We develop an inverse design method for configuration matching based on the theoretical model. We demonstrate soft robots designed by the theoretical model with the capability to pass through narrow channels and crawl over obstacles. We further demonstrate optimized soft grippers showing conformal grasping of complex objects. The proposed methodology paves the way to design centimeter-scale soft robots and broaden their applicationsNote to Practitioners—The motivation of this work is to analyze, predict, and control the centimeter-scale hard-magnetic soft robot under external magnetic fields. While smaller magnetic-driven soft robots have been extensively studied, the centimeter-scale soft robots offer larger workspace and output forces, making them more versatile for certain applications. This paper develops an analytical model for centimeter-scale hard-magnetic soft robots that takes into account the varying magnetization profile, gravity effect and large deformation. It allows magnetically driven soft robots to pass through narrow channels and crawl over obstacles. In addition, an optimization method is proposed by virtue of the analytical model, enabling the inverse design of soft robots with prescribed grasping postures. The analytical model and optimization method can be implemented for the dexterous locomotion and manipulation of magnetic soft robots with large workspace and output forces in medical and industrial settings.

Lattice metamaterials exhibit diverse functions and complex spatial deformations by rational structural design. Here, lattice metamaterials are exploited to design pneumatic soft robots with programmable bending, twisting, and elongation deformations. The system comprises an elastomeric tube reinforced by lattice metamaterials. We develop an analytical framework to model the twisting, bending, and elongation finite deformation taking into account the geometric orthotropy and nonlinear elasticity. We experimentally validate our modeling approach and investigate the effects of geometric patterns and input loading on the soft actuators' deformation. Theoretical guided design of lateral-climbing soft robots and exploration soft manipulators are demonstrated. The soft actuator could exhibit a combined twisting–bending–elongation deformation by lattice superimposition. The proposed structural design method paves the way for designing soft robots with complex and dexterous deformations.

In the normal lung, the dominant cable is an elastic "line element" composed of elastin fibers bound to a protein scaffold. The cable line element maintains alveolar geometry by balancing surface forces within the alveolus and changes in lung volume with exercise. Recent work in the postnatal rat lung has suggested that the process of cable development is self-organized in the extracellular matrix. Early in postnatal development, a blanket of tropoelastin (TE) spheres appear in the primitive lung. Within 7 to 10 days, the TE spheres are incorporated into a distributed protein scaffold creating the mature cable line element. To study the process of extracellular assembly, we used cellular automata (CA) simulations. CA simulations demonstrated that the intermediate step of tropoelastin self-aggregation into TE spheres enhanced the efficiency of cable formation more than 5-fold. Similarly, the rate of tropoelastin production had a direct impact on the efficiency of scaffold binding. The binding affinity of the tropoelastin to the protein scaffold, potentially reflecting heritable traits, also had a significant impact on cable development. In contrast, the spatial distribution of TE monomer production, increased Brownian motion and variations in scaffold geometry did not significantly impact simulations of cable development. We conclude that CA simulations are useful in exploring the impact of concentration, geometry, and movement on the fundamental process of elastogenesis.