Enabling robots to swiftly, robustly and efficiently interact with a dynamic environment remains a key challenge. The robotic community can draw inspiration from the co-adaptation and synergistic interplay between animals’ brains and bodies, which underpins embodied intelligence. Soft robots and neuromorphic technology offer a natural solution for such a challenge, enabling low-power, material-based and event-driven sensorimotor processing and control that seamlessly handles the continuous dynamic demands of embodied agents. In this Perspective, we propose a comprehensive framework for benchmarking neuromorphic computing (brain) that control soft robots (body), based on a suite of tasks, essential metrics and a reproducible robotic platform. The goal is to allow researchers to evaluate their embodied neuromorphic system with a physical robot, in real-world scenarios. The robotic platform is accessible, open-source, modular and scalable, so task complexity can be gradually increased, fostering a standardized approach. By coupling metrics with physical implementations, this framework will drive progress in soft robotics, neuromorphic computing and embodied intelligence. Combining soft robotics with neuromorphic engineering is a promising approach in embodied intelligence. Giulia d’Angelo et al. contribute to progress in this field by developing a framework for benchmarking neuromorphic controllers on soft robotic platforms.

The field of soft robotics has shown unprecedented growth in research efforts, scientific achievements, and technological advancements. Bioinspiration and biomimetics have played an instrumental role in the birth and growth of soft robotics. What is next for this field? To promote soft robotics research to the next level and have a broader impact in robotics and engineering fields, in this roadmap, we argue that two research directions should be strengthened (i) more structured, formal methods and tools for designing and developing soft robots and bioinspired robots (ii) more concrete applications of bioinspired soft robots in diverse sectors of human activities. This article provides a roadmap for the design of bioinspired soft robots, the integration of soft robot systems, and their applications in industry and services. Scientists and experts describe the state-of-the art and the perspectives of bioinspired, model-informed design of soft robots, outlining the challenges in developing complex soft robotic systems, and applications of soft robots in diverse fields.

Conventional instruments for minimally invasive surgery (MIS) face challenges in terms of miniaturization and compliance with soft tissues due to their tiny yet rigid structure. In abdominal surgery, rigid instruments increase the risk of bowel injury, as this tissue is extremely delicate and prone to peeling, stretching, or tearing. By leveraging the principles of origami, instruments can be designed and fabricated by folding 2D shapes, simplifying the manufacturing process. The foldability enables the creation of reconfigurable instruments capable of performing multiple functions, all while operating through tiny access ports and within narrow cavities with minimal invasiveness. This paper presents a deployable origami‐inspired instrument for robot‐assisted MIS, characterized by lightweight construction and tunable compliance. The foldable design supports multiple surgical functions, enabling the integration of additional tools at the tip in its unfolded configuration or functioning as a grasper for tissue manipulation once deployed. In grasper mode, the flexible structure is designed to deform upon contact with surrounding tissues, either during insertion into narrow cavities or when the grasper is actuated. This deformation ensures a secure and safe grasp of the tissues. The maximum pinch force achieved by the grasper is 4 N, while the pulling and lifting forces are within the range reported in literature for atraumatic manipulation of bowel tissue (0.18–1.21 N). The grasper‘s jaws were studied in terms of material selection and geometry to achieve a compromise between soft grasping and effective pulling force. Experimental tests demonstrated the grasper's capability not to apply excessive pressure on the tissue (well below the safety threshold of 329 kPa for bowel tissue), while maintaining a firm grasp during the manipulation of ex vivo porcine bowel tissue. Finally, the successful integration of the instrument into a da Vinci Research Kit robotic platform highlights its potential usability in surgical scenarios.

Vacuum-actuated muscle-inspired pneumatic structures (VAMPs) are a promising alternative to traditional pneumatic artificial muscles, offering uniform force distribution, reduced material fatigue, and improved reliability through the use of negative pressure; however, their design-performance relationship remains poorly understood, and current multi-step fabrication methods limit precision and complexity. To overcome these challenges, we developed a multi-parametric finite element analysis (FEA) framework exploring 100 parameter combinations to optimize axial strain, enabling application-specific actuator designs based on geometry, size, and contraction capacity. We also propose a cost-effective monolithic fabrication process that eliminates multi-step casting and allows for complex 3D structures. Validated by pressure-strain experiments with only 4% error, our approach achieves a 21% strain improvement over state-of-the-art VAMPs, broadening their potential in wearable robotics and biomedical applications.

Barriers to the widespread adoption of robots often stem less from limitations in technical capability than from the social, cultural and interpretive contexts in which these systems are encountered. We therefore argue that aesthetics should be treated as a core design dimension, alongside functionality and safety, to support meaningful and situated human–robot interactions.

Medical robotics holds transformative potential for healthcare. Robots excel in tasks requiring precision, including surgery and minimally invasive interventions, and they can enhance diagnostics through improved automated imaging techniques. Despite the application potentials, the adoption of robotics still faces obstacles, such as high costs, technological limitations, regulatory issues, and concerns about patient safety and data security. This roadmap, authored by an international team of experts, critically assesses the state of medical robotics, highlighting existing challenges and emphasizing the need for novel research contributions to improve patient care and clinical outcomes. It explores advancements in machine learning, highlighting the importance of trustworthiness and interpretability in robotics, the development of soft robotics for surgical and rehabilitation applications, and the role of image-guided robotic systems in diagnostics and therapy. Mini, micro, and nano robotics for surgical interventions, as well as rehabilitation and assistive robots, are also discussed. Furthermore, the roadmap addresses service robots in healthcare, covering navigation, logistics, and telemedicine. For each of the topics addressed, current challenges and future directions to improve patient care through medical robotics are suggested.

Unilateral Cerebral Palsy (UCP) is a clinical condition which mainly involves the movement and muscle tone of one side of the body, often impacting the general manual function. While there are some clinical assessment tools aimed to quantify the Upper Limbs (UpLs) use and the manual abilities, acquiring information regarding the motor abilities outside the clinical environment, such as the UpLs use and their asymmetry during daily life, could provide a more complete evaluation of the child and open a new clinical reasoning. For this purpose, wearable sensors are one of the newest approaches for continuously monitoring UpLs functions without being invasive. The aim of this study was to use wearable sensors to compare spontaneous/daily UpLs usage and asymmetry with the Assisting Hand Assessment (AHA) test, as well as comparing the daily UpLs usage behavior of children with UCP with respect to Typical Developing (TD) peers. Eighty children (54 with UCP and 26 TD) wore an Actigraph sensor on each wrist during the AHA test and then at least for the following week of daily life. The amount of use of each hand and the asymmetry were analyzed during both the AHA and the following week of daily life using linear regression analysis and ANOVA models. Significant relationships were found between the asymmetry detected during the week and both the AHA scores and the asymmetry detected during the test. UCP and TD children week asymmetry distributions were significantly different; moreover, some differences were found when grouping them by MACS levels. This paper proposes a new and easy technological methodology for monitoring UpLs behavior in daily life. Through wearable sensor data analysis, we demonstrate a linear correlation between asymmetry measured during smi-structured assessments and daily life. Additionally, we provide evidence of distinct patterns of UpLs usage between typically developing children and children with UCP in daily life. Clinical Trials.gov (NCT03054441).

Strain sensors are gaining popularity in soft robotics for acquiring tactile data due to their flexibility and ease of integration. Tactile sensing plays a critical role in soft grippers, enabling them to safely interact with unstructured environments and precisely detect object properties. However, a significant challenge with these systems is their high non-linearity, time-varying behavior, and long-term signal drift. In this paper, we introduce a continual learning (CL) approach to model a soft finger equipped with piezoelectric-based strain sensors for proprioception. To tackle the aforementioned challenges, we propose an adaptive CL algorithm that integrates a Long Short-Term Memory (LSTM) network with a memory buffer for rehearsal and includes a regularization term to keep the model's decision boundary close to the base signal while adapting to time-varying drift. We conduct nine different experiments, resetting the entire setup each time to demonstrate signal drift. We also benchmark our algorithm against two other methods and conduct an ablation study to assess the impact of different components on the overall performance.

Soft robotic grippers enable the safe manipulation of delicate objects, guaranteeing their integrity when handled and collected. Integrating sensors into these grippers can enable their proprioception but must avoid compromising flexibility or functionality. This study presents a pneumatic finger‐based soft gripper with a novel piezoresistive sensor made of laser‐induced graphene (LIG) embedded in dragon skin (DS), an elastomer matrix, offering continuous bending angle measurement. The LIG/DS composite is studied to confirm minimal impact on the gripper's stiffness. Mechanical and electromechanical characterizations are performed for two sensor designs, n 1 and n 2 . Design n 1 exhibits superior performance, with a gauge factor , a linear response of up to 30% strain, and durability exceeding 10 000 cycles. A finite‐element method analysis identifies the fingers’ neutral bending plane, guiding optimal sensor placement. Experimental validation confirms theoretical predictions and finds the ideal sensor location, achieving a linear response up to 110° with low hysteresis (8%). The sensor enables real‐time monitoring of finger bending during grasping tasks, with a calibration curve linking resistance changes to bending angles. This cost‐effective, stretchable, and durable sensor demonstrates high potential for soft robotic applications, offering precise and reliable proprioception without compromising the gripper's soft properties.

BACKGROUND:In cardiovascular engineering, the recent introduction of soft robotic technologies sheds new light on the future of implantable cardiac devices, enabling the replication of complex bioinspired architectures and motions. To support human heart function, assistive devices and total artificial hearts have been developed. However, the system's functionality, hemocompatibility, and overall implantability are still open challenges. METHODS:Here, the design of a soft robotic artificial cardiac wall is presented: the action of a bioinspired myocardium of pneumatic McKibben actuators in a double helix is coupled with an engineered passive and deformable endocardial layer made of silicone. The correlation between the helix angle of the actuators and the ejection fraction of the artificial cardiac wall was preliminarily studied with a simplified analytical model. A FEM model was introduced to represent the complex deformation of the endocardial layer during the actuation of the cardiac wall. RESULTS:Experimental tests report an ejection fraction of 68%, i.e., 77.2 ± 0.4 mL against 90 mmHg, satisfying the minimum physiological requirements and, therefore, proving the concept's functionality. CONCLUSIONS:The conceived device paves the way for a new generation of innovative approaches where engineered bioinspiration might be the key to future artificial cardiac pumps that could support or even substitute the human failing heart.

This paper presents a multi-physics model for phase-change-driven actuation in soft robotics, focusing on untethered systems that autonomously generate pressure through liquid evaporation. The model integrates electrothermal, thermo-fluidic, and mechanical domains, coupling Peltier-based heating, vapor generation, and soft material deformation. By operating in a pre-boiling regime, the approach minimises thermal gradients, enhances responsiveness, and reduces energy consumption. The governing equations are integrated into a multiphysics model, providing an innovative tool for designing efficient, safe, and controllable actuators with applications in robotics, biomedical devices, and adaptive materials. Copyright (c) 2025 The Authors. This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0/)

3D‐printed human‐inspired hands, while visually similar to their biological counterparts, often lack key features that enable the unique capabilities of human hands. In this research, a framework for desktop 3D printing patient‐specific human hands with a high functional level of biomimicry is presented. Magnetic resonance imaging (MRI) data are used to create computer aided design (CAD) models replicating key features of the skeletal system, including soft joints, ligaments, and volar plates, which are critical for mimicking the motions and functions of natural hands. The entire hand, consisting of rigid and soft segments, is monolithically 3D‐printed using a commercial, inexpensive (≈€ 500) desktop multimaterial printer, eliminating the need for assembly and expensive 3D printers. The proposed MRI to Desktop 3D printing approach contrasts with the state of the art, where high biomimicry is achieved through a multistage assembly process and expensive 3D printing setups. The resulting hand shows several unique behaviors of natural hands, including an opposable thumb moving across the palm, improved resistance at bone–joint interfaces, high life cycle, constrained bending, absorption of perpendicular loads, high range of coordinated, bioinspired motion, and grasping capabilities. The proposed approach can be potentially used to 3D print prosthetic hands tailored to individual needs, leveraging patient‐specific digitally created MRI data.

Soft robots are promising in biomedical applications thanks to their inherent structural compliance and distributed large deformations. However, integrating a sensory system that maintains the robot's dexterity while offering accurate state estimation remains an open challenge for their widespread adoption. This letter presents SoftTex, a small-scale soft robotic arm built with textile fabrics. SoftTex redesigns the STIFF-FLOP soft manipulator to favor affordable, rapid, and repeatable fabrication methods, facilitating the integration of a proprioceptive system based on piezoresistive textile strips preserving the soft arm compliance. First, we characterized the bending and stretching capabilities of the soft robotic arm and its workspace. The force tests demonstrated effectiveness for potential biomedical applications, revealing pulling forces ranging from 3.4-7.4 N and pushing forces from 2-7.5 N. Finally, we leveraged actuation, motion, and proprioceptive data collected with an open-loop controller to develop a position state estimator using a parallel recurrent neural network trained with supervised curriculum learning. The proprioceptive network achieves an average prediction error of 2.0 +/- 1.8 mm (3.4 +/- 2.9%L, where L is module length). The findings are promising for closed-loop control, addressing the demand for low-cost, sensor-equipped soft robotic arms in the medical field and enhancing their potential for confined space exploration.

Fingerprints primarily enhance grasping by modulating friction, as the surface pattern affects the friction needed for effective grasping and manipulation. A versatile gripper was developed with a more realistic distal phalange inspired by the human index finger for improved berry gripping performance. The soft pneumatic gripper was fabricated out of a Diels-Alder-based self-healing polymer, leveraging its thermally reversible nature for introducing interchangeable fingertips. Various fingertips were developed with different patterns for optimized grasping of fruits of different shape, size, and stiffness, depending on the type of fruit, level of ripeness, and variations in weather and climate conditions of each harvest season. The fingertips can be mounted and removed easily from the distal phalange of the pneumatic finger by welding and manual disassembly. The gripper was optimized for picking raspberries, exploiting the innovative interchangeable fingertips. The same gripper could successfully harvest berries of different levels of ripeness thanks to three types of interchangeable fingertips with different patterns. The performance of the different fingertips was evaluated in the lab on a physical twin of a raspberry and a 67% success rate was obtained in the field by switching them on the spot to optimize the grasp to the different ripeness level of the berries. The GraspBerry paves the way for the design of versatile grippers with adaptable grasping performance by switching the fingertips for accurate and reliable grasp on different types of crops throughout the various harvesting seasons all year round.

Soft robots promise inherent safety via their material compliance for seamless interactions with humans or delicate environments. Yet, their development is challenging because it requires integrating materials, geometry, actuation, and autonomy into complex mechatronic systems. Despite progress, the field struggles to balance task-specific performance with broader factors like durability and manufacturability - a difficulty that we find is compounded by traditional sequential design processes with their lack of feedback loops. In this perspective, we review emerging co-design approaches that simultaneously optimize the body and brain, enabling the discovery of unconventional designs highly tailored to the given tasks. We then identify three key shortcomings that limit the broader adoption of such co-design methods within the soft robotics domain. First, many rely on simulation-based evaluations focusing on a single metric, while real-world designs must satisfy diverse criteria. Second, current methods emphasize computational modeling without ensuring feasible realization, risking sim-to-real performance gaps. Third, high computational demands limit the exploration of the complete design space. Finally, we propose a holistic co-design framework that addresses these challenges by incorporating a broader range of design values, integrating real-world prototyping to refine evaluations, and boosting efficiency through surrogate metrics and model-based control strategies. This holistic framework, by simultaneously optimizing functionality, durability, and manufacturability, has the potential to enhance reliability and foster broader acceptance of soft robotics, transforming human-robot interactions.

Soft robots actively interact with their environment, exhibiting large distributed deformations due to their structural compliance. These features make them ideal for applications in wearable robotics, medical devices, and assistive technologies. However, a major challenge in their development is integrating sensory systems that do not constrain their movements while enabling accurate estimation of the end-effector position. This work focuses on addressing this limitation in the context of a soft robotic arm. Commercial piezoresistive textile Electrolycra was identified as a suitable candidate for strain sensing. Following electromechanical characterization, Electrolycra sensors were integrated into the soft arm. Using a derived calibration curve and the constant curvature approximation, the system's performance in position tracking was evaluated. The sensing system and estimation method successfully tracked the end-effector's position with errors of 13.1 mm, 13.7 mm, and 4.8 mm in the x, y, and z coordinates, respectively, within a global reference frame during workspace operation. These results demonstrate the potential of Electrolycra-based sensing for soft robotic applications and open avenues for further development, particularly in closed-loop control systems.Clinical Relevance— A sensorized soft robot with enhanced closed-loop control can significantly impact the clinical field by enabling precise and adaptive interactions with patients, improving safety, efficacy, and personalization in rehabilitation, assistive technologies, and motor assessment.

The fresh food industry significantly depends on manual labor, which can make up to 40