Yu Mei

Soft robots, with their remarkable advantages in various applications, face the critical challenge of embodied perception, encompassing proprioceptive sensing and perceiving unknown environments (exteroception). In this article, we achieve simultaneous continuous shape reconstruction and external force estimation for soft bending actuators using only a proprioceptive curvature sensor. We introduce a novel distributed inductive curvature sensor designed for capturing continuous shape through electromagnetic induction. In addition, we enhance an analytical static model based on the Euler–Bernoulli curved beam theory to predict the shape under pneumatic actuation and external forces. Furthermore, a model-based optimization algorithm is proposed to estimate external forces based on the measured shape. Extensive experimental validation supports the efficacy of the proposed sensor and algorithms.

Positive-negative pressure regulation is critical to soft robotic actuators, enabling large motion ranges and versatile actuation modes. However, achieving high-performance regulation across both pressure polarities remains challenging due to asymmetric inflation–deflation dynamics, valve nonlinearities, and switching-induced flow disturbances. This paper presents BiPneu, a compact and cost-efficient multi-channel bipolar-pressure pneumatic system for soft robots that enables wide-range, accurate, and responsive pressure regulation while providing seamless compatibility with high-level software ecosystems. A dual-mode sliding-mode controller (DM-SMC) with hysteresis-supervised mode selection is proposed based on a hybrid electro-pneumatic model. Extensive simulation and experiments demonstrate the superior performance of DM-SMC in tracking step and sinusoidal pressure references compared with both advanced model predictive controllers and well-tuned PID controllers. Experimental results show average absolute errors of 1.44 kPa in multi-step tests and 4.23 kPa in sinusoidal tracking, corresponding to reductions of 11.9% and 35.6% relative to PID control, along with improved control effort, valve switching rate, and transient response. Robustness of DM-SMC is further verified on a bellow actuator with pressure-dependent volume. Finally, BiPneu’s capability is demonstrated via two soft robotic examples, quick ball-maneuvering with a soft parallel manipulator and real-time finite element method (FEM)-based teleoperation of a soft bellows actuator.

Soft robots, distinguished by their inherent compliance and continuum structures, present unique modeling challenges, especially when subjected to significant external loads such as gravity and payloads. In this study, we introduce an innovative data-driven modeling framework leveraging an Euler spiral-inspired shape representations to accurately describe the complex shapes of soft continuum actuators. Based on this representation, we develop neural network-based forward and inverse models to effectively capture the nonlinear behavior of a fiber-reinforced pneumatic bending actuator. Our forward model accurately predicts the actuator’s deformation given inputs of pressure and payload, while the inverse model reliably estimates payloads from observed actuator shapes and known pressure inputs. Comprehensive experimental validation demonstrates the effectiveness and accuracy of our proposed approach. Notably, the augmented Euler spiral-based forward model achieves low average positional prediction errors of 3.38%, 2.19%, and 1.93% of the actuator length at the one-third, two-thirds, and tip positions, respectively. Furthermore, the inverse model demonstrates precision of estimating payloads with an average error as low as 0.72% across the tested range. These results underscore the potential of our method to significantly enhance the accuracy and predictive capabilities of modeling frameworks for soft robotic systems.

Data-driven model predictive control (MPC) has shown strong potential for improving control performance under model uncertainties. However, many existing approaches rely on extensive offline data collection and computationally expensive training, which limits their ability to adapt online. This paper presents a fast online adaptive MPC framework that integrates neural networks with Model-Agnostic Meta-Learning (MAML) to enable few-shot adaptation of residual dynamics. By capturing discrepancies between nominal and true system behavior using minimal online data and gradient steps, the proposed method achieves rapid model correction. The meta-learned residual models are embedded into a computationally efficient L4CasADi-based MPC pipeline, improving prediction accuracy and real-time control performance. Simulation studies on a cart-pole system and a 2D quadrotor demonstrate significant gains in adaptation speed and accuracy compared to nominal MPC and nominal MPC augmented with a freshly initialized neural network.

A soft continuum manipulator with tunable stiffness can not only take advantage of high compliance for safe adaptation in unknown environments, but also circumvent the drawbacks of instability and low loading capability. The high nonlinearity of soft manipulators and the strong coupling between actuation and stiffness-tuning make their simultaneous control challenging. In this work, a novel approach to simultaneous control of actuation and stiffness-tuning is proposed for soft pneumatic manipulators. With a piecewise-constant curvature assumption, a Lagrangian-based dynamic model with realistic approximation is used for control design, where the dynamics of the stiffness-tunable mechanism is incorporated. An extended Kalman filter (EKF) is proposed to estimate unmeasurable states including the stiffness and the velocity. A nonlinear model predictive control (NMPC) framework is developed first in the configuration space, and then extended to the task space, for simultaneous motion and stiffness control under inflation and vacuum pressure constraints. Simulation results are presented to support the efficacy of the proposed approach.

We propose a novel multisection cable-driven soft robotic arm inspired by octopus tentacles along with a new modeling approach. Each section of the modular manipulator is made of a soft tubing backbone, a soft silicone arm body, and two rigid endcaps, which connect adjacent sections and decouple the actuation cables of different sections. The soft robotic arm is made with casting after the rigid endcaps are 3D-printed, achieving low-cost and convenient fabrication. To capture the nonlinear effect of cables pushing into the soft silicone arm body, which results from the absence of intermediate rigid cable guides for higher compliance, an analytical static model is developed to describe the relationship between the bending curvature and the cable lengths. The proposed model shows superior prediction performance in experiments over that of a baseline model, especially under large bending conditions. Based on the nonlinear static model, a kinematic model of a multisection arm is further developed and used to derive a motion planning algorithm. Experiments show that the proposed soft arm has high flexibility and a large workspace, and the tracking errors under the algorithm based on the proposed modeling approach are up to 52% smaller than those with the algorithm derived from the baseline model.

Soft robots offer a unique combination of flexibility, adaptability, and safety, making them well-suited for a diverse range of applications. However, the inherent complexity of soft robots poses great challenges in their modeling and control. In this letter, we present the mechanical design and data-driven control of a pneumatic-driven soft planar robot. Specifically, we employ a data-enabled predictive control (DeePC) strategy that directly utilizes system input/output data to achieve safe and optimal control, eliminating the need for tedious system identification or modeling. In addition, a dimension reduction technique is introduced into the DeePC framework, resulting in significantly enhanced computational efficiency with minimal to no degradation in control performance. Comparative experiments are conducted to validate the efficacy of DeePC in the control of the fabricated soft robot.

Accurate shape reconstruction is essential for precise control and reliable operation of soft robots. Compared to sensor-based approaches, vision-based methods offer advantages in cost, simplicity, and ease of deployment. However, existing vision-based methods often rely on complex camera setups, specific backgrounds, or large-scale training datasets, limiting their practicality in real-world scenarios. In this work, we propose a vision-based, markerless, and training-free framework for soft robotic shape reconstruction that directly leverages the natural surface appearance of the robot. These surface features act as implicit visual markers, enabling a hierarchical matching strategy that decouples local partition alignment from global kinematic optimization. Requiring only an initial 3D reconstruction and kinematic alignment, our method achieves real-time shape tracking across diverse environments while maintaining robustness to occlusions and variations in camera viewpoints. Experimental validation on a continuum soft robot demonstrates an average tip error of 2.6% during real-time operation, as well as stable performance in practical closed-loop control tasks. These results highlight the potential of the proposed approach for reliable, low-cost deployment in dynamic real-world settings.

Sea lamprey, a destructive invasive species in the Great Lakes in North America, is among very few fishes that rely on oral suction during migration and spawning. Recently, soft pressure sensors have been proposed to detect the attachment of sea lamprey as part of the monitoring and control effort. However, human decision is still required for the recognition of patterns in the measured signals. In this article, a novel automated soft pressure sensor array-based sea lamprey detection framework is proposed using object detection convolutional neural networks. First, the resistance measurements of the pressure sensor array are converted to mappings of relative change in resistance. These mappings typically show two different types of patterns under lamprey attachment: a high-pressure circular pattern corresponding to the mouth rim compressed against the sensor (“compression” pattern), and a low-pressure blob corresponding to the partial vacuum region of the sucking mouth (“suction” pattern). Three types of object detection algorithms, single-shot detector (SSD), RetinaNet, and YOLOv5s, are applied to the dataset of measurements collected in the presence of sea lamprey attachment, and the comparison of their performance shows that YOLOv5s model achieves the highest mean average precision (mAP) and the fastest inference speed. Furthermore, to improve the accuracy of the prediction model and reduce the false positive (FP) rate due to the sensor’s memory effect, a filter branch with different detection thresholds for the compression and suction patterns, respectively, is added to the original machine-learning algorithm. The trained model is validated and used to automatically detect sea lamprey attachments and locate the suction area on the sensor in real time.