Emotion detection from handwriting and drawing samples using an attention-based transformer model.

Emotion detection (ED) involves the identification and understanding of an individual's emotional state through various cues such as facial expressions, voice tones, physiological changes, and behavioral patterns. In this context, behavioral analysis is employed to observe actions and behaviors for emotional interpretation. This work specifically employs behavioral metrics like drawing and handwriting to determine a person's emotional state, recognizing these actions as physical functions integrating motor and cognitive processes. The study proposes an attention-based transformer model as an innovative approach to identify emotions from handwriting and drawing samples, thereby advancing the capabilities of ED into the domains of fine motor skills and artistic expression. The initial data obtained provides a set of points that correspond to the handwriting or drawing strokes. Each stroke point is subsequently delivered to the attention-based transformer model, which embeds it into a high-dimensional vector space. The model builds a prediction about the emotional state of the person who generated the sample by integrating the most important components and patterns in the input sequence using self-attentional processes. The proposed approach possesses a distinct advantage in its enhanced capacity to capture long-range correlations compared to conventional recurrent neural networks (RNN). This characteristic makes it particularly well-suited for the precise identification of emotions from samples of handwriting and drawings, signifying a notable advancement in the field of emotion detection. The proposed method produced cutting-edge outcomes of 92.64% on the benchmark dataset known as EMOTHAW (Emotion Recognition via Handwriting and Drawing).

An Efficient Robotic Pushing and Grasping Method in Cluttered Scene.

Pushing and grasping (PG) are crucial skills for intelligent robots. These skills enable robots to perform complex grasping tasks in various scenarios. These PG methods can be categorized into single-stage and multistage approaches. Single-stage methods are faster but less accurate, while multistage methods offer high accuracy at the expense of time efficiency. To address this issue, a novel end-to-end PG method called efficient PG network (EPGNet) is proposed in this article. EPGNet achieves both high accuracy and efficiency simultaneously. To optimize performance with fewer parameters, EfficientNet-B0 is used as the backbone of EPGNet. Additionally, a novel cross-fusion module is introduced to enhance network performance in robotic PG tasks. This module fuses and utilizes local and global features, aiding the network in handling objects of varying sizes in different scenes. EPGNet consists of two branches dedicated to predicting PG actions, respectively. Both branches are trained simultaneously within a Q -learning framework. Training data is collected through trial and error, involving the robot performing PG actions. To bridge the gap between simulation and reality, a unique PG dataset is proposed. Additionally, a YOLACT network is trained on the PG dataset to facilitate object detection and segmentation. A comprehensive set of experiments is conducted in simulated environments and real-world scenarios. The results demonstrate that EPGNet outperforms single-stage methods and offers competitive performance compared to multistage methods, all while utilizing fewer parameters. A video is available at https://youtu.be/HNKJjQH0MPc.

Event-Triggered Mechanism-Based Discrete-Time Nash Equilibrium Seeking for Graphic Game With Outlier-Resistant ESO.

In this article, we consider a discrete-time Nash equilibrium (NE) seeking problem for graphic game subject to disturbances. For the first-order dynamics, the discrete-time outlier-resistant extended state observer (ESO)-based game strategy is proposed to enable the players to estimate the disturbances under effect of anomaly measurements and then compensate them. An event-triggered mechanism is applied between adjacent players to reduce the frequency of communication. The convergence of the outlier-resistant ESO and control strategy is presented. Moreover, the upper bound of ϵ -NE solution deviating from the unique point of nominal system is given analytically. Then, the addressed issues are extended to high-order game systems. The NE seeking-based control strategy for each player is designed such that the equilibrium point converges to the ϵ -NE which is also analytically calculated. Finally, in order to verify the effectiveness of the proposed game strategy, an example of satellite system is given.

A Two Phases Multiobjective Trajectory Optimization Scheme for Multi-UGVs in the Sight of the First Aid Scenario.

Timely delivery of first aid supplies is significant to saving lives when an accident happens. Among the promising solutions provided for such scenarios, the application of unmanned vehicles has attracted ever more attention. However, such scenarios are often very complex, while the existing studies have not fully addressed the trajectory optimization problem of multiple unmanned ground vehicles (multi-UGVs) against the scenario. This study focuses on multi-UGVs trajectory optimization in the sight of first aid supply delivery tasks in mass accidents. A two-stage completely decoupling fuzzy multiobjective optimization strategy is designed. On the first stage, with the proposed timescale involved tridimensional tunneled collision-free trajectory (TITTCT) algorithm, collision-free coarse tunnels are build within a tridimensional coordinate system, respectively, for the UGVs as the corresponding configuration space for a further multiobjective optimization. On the second stage, a fuzzy multiobjective transcription method is designed to solve the decoupled optimal control problem (OCP) within the configuration space with the consideration of priority constrains. Following the two-stage design, the computational time is significantly reduced when achieving an optimal solution of the multi-UGV trajectory planning, which is crucial in a first aid task. In addition, other objectives are optimized with the aspiration level reflected. Simulation studies and experiments have been curried out to testify the effectiveness and the improved computational performance of the proposed design.

Reinforcement Learning-Based Model Predictive Control for Discrete-Time Systems.

This article proposes a novel reinforcement learning-based model predictive control (RLMPC) scheme for discrete-time systems. The scheme integrates model predictive control (MPC) and reinforcement learning (RL) through policy iteration (PI), where MPC is a policy generator and the RL technique is employed to evaluate the policy. Then the obtained value function is taken as the terminal cost of MPC, thus improving the generated policy. The advantage of doing so is that it rules out the need for the offline design paradigm of the terminal cost, the auxiliary controller, and the terminal constraint in traditional MPC. Moreover, RLMPC proposed in this article enables a more flexible choice of prediction horizon due to the elimination of the terminal constraint, which has great potential in reducing the computational burden. We provide a rigorous analysis of the convergence, feasibility, and stability properties of RLMPC. Simulation results show that RLMPC achieves nearly the same performance as traditional MPC in the control of linear systems and exhibits superiority over traditional MPC for nonlinear ones.

The association of preconceptional folic acid supplementation with gestational age and preterm birth risk in twin pregnancies: a prospective cohort study in China.

PURPOSE: This study aims to explore the association of maternal preconceptional folic acid (FA) supplementation with gestational age and preterm birth in twin pregnancies, and whether the association varies by chorionicity or conception mode. METHODS: From November 2018 to December 2021, the information of FA supplementation and pregnancy outcomes were collected in twin pregnant women. The linear regression models and the logistic regression were used to test the association of preconceptional FA supplementation with gestational age at delivery and preterm birth and premature rupture of membranes (PROM). RESULTS: A total of 416 twin pregnancies were included. Compared with no use in twins, maternal preconceptional FA use was associated with a 0.385-week longer gestational age (95% CI 0.019-0.751) and lower risk of preterm birth < 36 weeks (adjusted OR 0.519; 95% CI 0.301-0.895) and PROM (adjusted OR 0.426; 95% CI 0.215-0.845). The protective effect on preterm birth < 36 weeks and PROM is similar whether taking FA supplements alone or multivitamins. However, the associations varied by chorionicity and conception mode of twins or compliance with supplementation. The positive associations between preconceptional FA use and gestational age only remained significant among twins via assisted reproductive technology or dichorionic diamniotic twins. Significant protective effects on preterm birth < 36 weeks and PROM were only found among women who took FA at least 4 times a week before conception. CONCLUSION: Maternal preconceptional FA supplementation was associated with longer gestation duration and lower risk of preterm birth < 36 weeks and PROM in twin pregnancies. To improve the success of their pregnancies, reproductive women should start taking FA supplements well before conception and with good compliance.

Category-Level 6-D Object Pose Estimation With Shape Deformation for Robotic Grasp Detection.

Category-level 6-D object pose estimation plays a crucial role in achieving reliable robotic grasp detection. However, the disparity between synthetic and real datasets hinders the direct transfer of models trained on synthetic data to real-world scenarios, leading to ineffective results. Additionally, creating large-scale real datasets is a time-consuming and labor-intensive task. To overcome these challenges, we propose CatDeform, a novel category-level object pose estimation network trained on synthetic data but capable of delivering good performance on real datasets. In our approach, we introduce a transformer-based fusion module that enables the network to leverage multiple sources of information and enhance prediction accuracy through feature fusion. To ensure proper deformation of the prior point cloud to align with scene objects, we propose a transformer-based attention module that deforms the prior point cloud from both geometric and feature perspectives. Building upon CatDeform, we design a two-branch network for supervised learning, bridging the gap between synthetic and real datasets and achieving high-precision pose estimation in real-world scenes using predominantly synthetic data supplemented with a small amount of real data. To minimize reliance on large-scale real datasets, we train the network in a self-supervised manner by estimating object poses in real scenes based on the synthetic dataset without manual annotation. We conduct training and testing on CAMERA25 and REAL275 datasets, and our experimental results demonstrate that the proposed method outperforms state-of-the-art (SOTA) techniques in both self-supervised and supervised training paradigms. Finally, we apply CatDeform to object pose estimation and robotic grasp experiments in real-world scenarios, showcasing a higher grasp success rate.

Dynamic Event-Based Adaptive Fixed-Time Control for Uncertain Strict-Feedback Nonlinear Systems With State Constraints.

In this article, the event-triggered fixed-time tracking control is investigated for uncertain strict-feedback nonlinear systems involving state constraints. By employing the universal transformed function (UTF) and coordinate transformation techniques into backstepping design procedure, the proposed control scheme ensures that all states are constrained within the time-varying asymmetric boundaries, and meanwhile, the undesired feasibility condition existing in other constrained controllers can be removed elegantly. Different from the existing static event-triggered mechanism, a dynamic event-triggered mechanism (DETM) is devised via constructing a novel dynamic function, so that the communication burden from the controller to actuator is further alleviated. Furthermore, with the aid of adaptive neural network (NN) technique and generalized first-order filter, together with Lyapunov theory, it is proved that the states of closed-loop system converge to small regions around zero with fixed-time convergence rate. The simulation results confirm the benefits of developed scheme.

Switched Model Predictive Control for Nonholonomic Mobile Robots Under Adaptive Dwell Time.

In this article, switched model predictive control (MPC) is proposed for nonholonomic mobile robots with adaptive dwell time and a dual-terminal set. The dual-terminal set is used to reduce on-line complexity of the switched MPC for the nonholonomic mobile robots with multiple constraints. By a switched signal with the adaptive dwell time, cost functions are switched to improve control performance under multiple constraints. The switched MPC with feasibility and stability can adjust a tradeoff between control performance and computational complexity for the closed-loop system. Simulation results are given to illustrate superiority of the switched MPC for nonholonomic mobile robots.

Contrastive Multi-View Kernel Learning.

Kernel method is a proven technique in multi-view learning. It implicitly defines a Hilbert space where samples can be linearly separated. Most kernel-based multi-view learning algorithms compute a kernel function aggregating and compressing the views into a single kernel. However, existing approaches compute the kernels independently for each view. This ignores complementary information across views and thus may result in a bad kernel choice. In contrast, we propose the Contrastive Multi-view Kernel - a novel kernel function based on the emerging contrastive learning framework. The Contrastive Multi-view Kernel implicitly embeds the views into a joint semantic space where all of them resemble each other while promoting to learn diverse views. We validate the method's effectiveness in a large empirical study. It is worth noting that the proposed kernel functions share the types and parameters with traditional ones, making them fully compatible with existing kernel theory and application. On this basis, we also propose a contrastive multi-view clustering framework and instantiate it with multiple kernel k-means, achieving a promising performance. To the best of our knowledge, this is the first attempt to explore kernel generation in multi-view setting and the first approach to use contrastive learning for a multi-view kernel learning.

A Novel Robotic Pushing and Grasping Method Based on Vision Transformer and Convolution.

Robotic grasping techniques have been widely studied in recent years. However, it is always a challenging problem for robots to grasp in cluttered scenes. In this issue, objects are placed close to each other, and there is no space around for the robot to place the gripper, making it difficult to find a suitable grasping position. To solve this problem, this article proposes to use the combination of pushing and grasping (PG) actions to help grasp pose detection and robot grasping. We propose a pushing-grasping combined grasping network (GN), PG method based on transformer and convolution (PGTC). For the pushing action, we propose a vision transformer (ViT)-based object position prediction network pushing transformer network (PTNet), which can well capture the global and temporal features and can better predict the position of objects after pushing. To perform the grasping detection, we propose a cross dense fusion network (CDFNet), which can make full use of the RGB image and depth image, and fuse and refine them several times. Compared with previous networks, CDFNet is able to detect the optimal grasping position more accurately. Finally, we use the network for both simulation and actual UR3 robot grasping experiments and achieve SOTA performance. Video and dataset are available at https://youtu.be/Q58YE-Cc250.

Fully Distributed Event-Triggered Anti-Windup Consensus of Heterogeneous Systems With Input Saturation and an Active Leader.

This article addresses the event-based fully distributed consensus problem for linear heterogeneous multiagent systems (MASs) subject to input saturation. A leader with unknown but bounded control input is also considered. Based on an adaptive dynamic event-triggered protocol, all the agents can reach output consensus without knowing any global knowledge. Moreover, by applying a multiple-level saturation technique, the input-constrained leader-following consensus control is achieved. The given event-triggered algorithm can be utilized for the directed graph containing a spanning tree with the leader as the root. One distinct feature compared with previous works is that the proposed protocol can achieve saturated control without any a priori condition, instead, the local information is needed. Finally, the numerical simulations are illustrated to verify the performance of the proposed protocol.

Physics-informed neural entangled-ladder network for inhalation impedance of the respiratory system.

BACKGROUND AND OBJECTIVES: The use of machine learning methods for modelling bio-systems is becoming prominent which can further improve bio-medical technologies. Physics-informed neural networks (PINNs) can embed the knowledge of physical laws that govern a system during the model training process. PINNs utilise differential equations in the model which traditionally used numerical methods that are computationally complex. METHODS: We integrate PINNs with an entangled ladder network for modelling respiratory systems by considering a lungs conduction zone to evaluate the respiratory impedance for different initial conditions. We evaluate the respiratory impedance for the inhalation phase of breathing for a symmetric model of the human lungs using entanglement and continued fractions. RESULTS: We obtain the impedance of the conduction zone of the lungs pulmonary airways using PINNs for nine different combinations of velocity and pressure of inhalation. We compare the results from PINNs with the finite element method using the mean absolute error and root mean square error. The results show that the impedance obtained with PINNs contrasts with the conventional forced oscillation test used for deducing the respiratory impedance. The results show similarity with the impedance plots for different respiratory diseases. CONCLUSION: We find a decrease in impedance when the velocity of breathing is lowered gradually by 20%. Hence, the methodology can be used to design smart ventilators to the improve flow of breathing.

Adaptive super-twisting sliding mode altitude trajectory tracking control for reentry vehicle.

This paper addresses the altitude trajectory tracking control problem of reentry vehicle subject to bounded uncertainty. A new continuous adaptive super-twisting sliding mode control (ASTSMC) method is developed based on conventional super-twisting sliding mode control (STSMC) and adaptive gain technique, which can improve tracking accuracy and achieve high control performance. Based on adaptive gain technique, the designed ASTSMC method requires no prior information on uncertainty and avoids the overestimation of control gain, then the unexpected chattering phenomenon is alleviated. By employing fast power rate reaching law and modified fast nonsingular terminal sliding mode (FNTSM) surface, the designed controller achieves faster convergence and stronger robustness than conventional STSMC methods. Furthermore, the finite-time stability of closed-loop system is proved through Lyapunov theory. Simulation results are executed to validate the superiority of the proposed controller.

Discrete-Time Control Barrier Function: High-Order Case and Adaptive Case.

This article proposes the novel concepts of the high-order discrete-time control barrier function (CBF) and adaptive discrete-time CBF. The high-order discrete-time CBF is used to guarantee forward invariance of a safe set for discrete-time systems of high relative degree. An optimization problem is then established unifying high-order discrete-time CBFs with discrete-time control Lyapunov functions to yield a safe controller. To improve the feasibility of such optimization problems, the adaptive discrete-time CBF is designed, which can relax constraints on system control input through time-varying penalty functions. The effectiveness of the proposed methods in dealing with high relative degree constraints and improving feasibility is verified on the discrete-time system of a three-link manipulator.

EMPC with adaptive APF of obstacle avoidance and trajectory tracking for autonomous electric vehicles.

In this paper, event-triggered model predictive control (EMPC) with adaptive artificial potential field (APF) is designed to realize obstacle avoidance and trajectory tracking for autonomous electric vehicles. An adaptive APF cost function is added to achieve obstacle avoidance and guarantee stability. The optimization problem for MPC is feasible by considering a special obstacle avoidance constraint. An event-triggered mechanism is proposed to reduce computational burden and ensure effectiveness of obstacle avoidance. Input and state constraints of autonomous electric vehicles are considered in both feasibility and stability by a robust terminal set. Effectiveness of both obstacle avoidance and trajectory tracking is shown by experimental results on autonomous electric vehicles.

The UA Doppler Index, Plasma HCY, and Cys C in Pregnancies Complicated by Congenital Heart Disease of the Fetus.

Background: Congenital heart disease/defect (CHD) is one of the most common congenital disabilities. Early diagnosis of CHD can improve the prognosis of newborns with CHD. The aim of this study was to evaluate the relationship between the factors and the onset of fetal congenital heart disease by measuring fetal umbilical artery (UA) Doppler index, maternal HCY, and Cys C levels during pregnancy. Methods: This retrospective study analyzed 202 fetuses with CHD, including 77 cases (39.1%) of simple CHD and 120 cases (60.9%) of complex CHD. Singleton pregnant women who were examined at the same time and whose malformation screening did not suggest any structural abnormalities in the fetus were assigned to the control group (n = 400). The UA Doppler index, plasma HCY, and Cys C levels were compared among the pregnant women across the three groups, and logistic regression analysis was performed on statistically significant markers. The ROC of UA S/D, PI, RI, HCY, and Cys C were plotted, and the area under the ROC (AUC) was calculated. Results: The UA S/D, PI, and RI in the complex CHD group were significantly higher than those in the control group (p < 0.05). The levels of HCY and Cys C in the CHD group were significantly higher than those in the control group (p < 0.05). HCY and S/D revealed a positive correlation (r = 0.157), and the difference was statistically significant (p < 0.001). Cys C and S/D were positively correlated (r = 0.131), and the difference was statistically significant (p < 0.05). The levels of UA Doppler indices, maternal plasma HCY, and Cys C were elevated in fetuses with CHD. The AUC of the combined test of the UA index, HCY, and Cys C was higher than that of each individual test. Conclusions: Elevated levels of the UA doppler indices, HCY, and Cys C during pregnancy are positively associated with the development of congenital heart disease in offspring. The combination of HCY and Cys C was the most efficient test for the diagnosis of CHD. We are the first to report that plasma Cys C levels of women pregnant with fetuses with CHD were higher than those of women pregnant with normal fetuses.

The associations of chronotype and social jetlag with prosocial behavior problems among Chinese adolescents.

Potential relevance between the circadian rhythm and behavioral health has got raising attention in recent years. This study aimed to examine chronotype, social jetlag and their associations with prosocial behavior problems among Chinese adolescents. A total of 4,666 middle school students aged 12-18 years were enrolled in study. Sleep characteristics were collected by the modified Chinese version of Adolescent Sleep Hygiene Scale (M-ASHS); MSFsc and mid-sleep point were calculated to determine chronotypes and social jetlag. Prosocial behavior problems were assessed by the Strength and Difficult Questionnaire (SDQ). Multivariate logistic regression was applied to analyze the relationships between chronotype and social jetlag with prosocial behavior problems. Evening chronotype was associated with higher risk of prosocial behavior problems, whether among male (OR = 1.82, 95%CI:1.27-2.61, P = .001) or female adolescents (OR = 1.83, 95%CI:1.15-2.91, P = .011). Female adolescents with social jetlag of 1-2 hours had 1.60 times the risk of prosocial behavior problems than their peers whose social jetlag was <1 h (P = .028); social jetlag ≥ 2 h was positively associated with prosocial behavior problems in both male and female adolescents (OR = 1.79 and 2.45, respectively, both P < .05). Further, the combination of intermediate chronotype and social jetlag ≥ 2 h was correlated with prosocial behavior problems only in female adolescents (OR = 3.24, 95%CI = 1.40-9.21, P = .004). Evening chronotype and higher social jetlag were risk factors for prosocial behavior problems in adolescents, especially for the female. For the promotion of prosocial behavior in adolescents, the importance of circadian rhythm should be addressed.

Correlation analysis of adverse outcomes for the selective reduction of twin pregnancies.

BACKGROUND: Due to the extensive development of assisted reproductive technology, the number of twin pregnancies has increased significantly over recent decades. Twin pregnancy is the most representative type of multiple pregnancies and is associated with high infant morbidity and mortality. Perinatal complications of twin pregnancy are also markedly increased compared with those of single pregnancy. Transabdominal selective reduction (SR) is a remedial intervention. This study aimed to research the adverse outcomes of transabdominal selective reduction of twin pregnancy and the correlation between the reduction week and pregnancy outcomes. OBJECTIVE: The purpose of this study was to examine the adverse outcomes of the transabdominal selective reduction of twin pregnancy and the correlation between the reduction week and pregnancy outcomes. METHODS: A retrospective cohort study of the transabdominal reduction of twin pregnancy was conducted in a single prenatal diagnosis medical centre from September 2012 to October 2020. According to chorionicity, women with twin pregnancies were divided into 2 groups: dichorionic (DC) twin pregnancies and monochorionic (MC) twin pregnancies. Women with DC twin pregnancies underwent potassium chloride reduction, and those with MC twin pregnancies underwent radiofrequency ablation (RFA). The reduction indications included pregnancy complications, foetal abnormalities, and maternal factors. The perinatal outcomes of different chorionic twins after reduction were analysed. Each foetus with an adverse outcome was included. The relative relationship between the reduction weeks and delivery weeks of twins was examined by correlation analysis. RESULTS: A total of 161 women were included in this study. A total of 112 women had DC twin pregnancies, and 49 women had MC twin pregnancies. Preterm delivery rates were significantly higher in the MC twin reduction group than in the DC twin reduction group prior to 37 weeks (53.1% vs. 29.5%, P = 0.004). The mean gestational age at delivery of the foetuses in the DC twin group that underwent SR was significantly older than that of those in the MC twin group that underwent SR (36.9 ± 4.0 vs. 33.5 ± 6.6 weeks, P = 0.001). The number of DC twins that underwent SR and were delivered after 37 weeks was obviously greater than that of the MC twins that underwent SR (70.5% vs. 46.9%, P = 0.004). The foetal survival rate was 95.5% in the DC twin reduction group and 77.6% in the MC twin reduction group. If the indication of TTTS was not included, there was no significant difference in the foetal survival rate of the DC and MC twin reduction groups (95.5% vs. 86.2%, P = 0.160). Cotwin death 1 week after reduction was greater in the MC group (6.1% vs. 0%, P = 0.027). Compared to other indications, this finding indicated that a significantly lower proportion of women remained undelivered after selective reduction with the indication of TTTS. There was a significant negative correlation between the reduction weeks and delivery weeks of the two groups (P < 0.01), and the best opportunity for reduction was before 22 weeks of gestation. CONCLUSION: These findings highlighted an obviously negative correlation between the reduction week and delivery week. The transabdominal selective reduction of twin pregnancy should be considered for a lower rate of miscarriage or premature delivery if the reduction week takes place earlier in pregnancy. The rate of preterm delivery was the lowest when transabdominal selective reduction was completed before 22 weeks of gestation. Compared with other RFA indications, a higher rate of premature delivery was shown for MC twins with a reduction indication of TTTS. TTTS with sIUGR might be one of the reasons for the adverse outcomes of reduction for MC twin pregnancy.

Electrically Controlled Aquatic Soft Actuators with Desynchronized Actuation and Light-Mediated Reciprocal Locomotion.

Soft-bodied aquatic invertebrates can overcome hydrodynamic resistance and display diverse locomotion modes in response to environmental cues. Exploring the dynamics of locomotion from bioinspired aquatic actuators will broaden the perspective of underwater manipulation of artificial systems in fluidic environments. Here, we report a multilayer soft actuator design based on a light-driven hydrogel and a laser-induced graphene (LIG) actuator, minimizing the effect of the time delay by a monolithic hydrogel-based system while maintaining shape-morphing functionality. Moreover, different time scales in the response of actuator materials enable a real-time desynchronization of energy inputs, holding great potential for applications requiring desynchronized stimulation. This hybrid design principle is ultimately demonstrated with a high-performance aquatic soft actuator possessing an underwater walking speed of 0.81 body length per minute at a relatively low power consumption of 3 W. When integrated with an optical sensor, the soft actuator can sense the variation in light intensity and achieve mediated reciprocal motion. Our proposed locomotion mechanism could inspire other multilayer soft actuators to achieve underwater functionalities at the same spatiotemporal scale. The underwater actuation platform could be used to study locomotion kinematics and control mechanisms that mimic the motion of soft-bodied aquatic organisms.