Animal musculoskeletal systems are renowned for their ability to dynamically regulate stiffness and achieve energy-efficient motion. Being inspired by the biological control structure, this study presents a hybrid control framework that utilizes two-stage learning processes for body movement planning and muscle force computation. This methodology simplifies the learning process under joint redundancy and muscle redundancy. Then it enhances the interpretability of the resultant generated behaviors. The framework incorporates a reinforcement learning (RL)-trained joint controller to optimize joint torques, in conjunction with an LSTM-based muscle controller that translates these torques into muscle activations. Two control variants are proposed: One is prioritizing energy efficiency and the other is enhancing adaptability to environmental perturbations through co-contraction control. Validation with MuJoCo physics simulations demonstrates the framework’s capacity to autonomously learn and refine different gait modes without dependence on external motion datasets. The second variant demonstrates superior robustness and energy efficiency compared to conventional motor-driven models. This framework contributes to the enhancement of adaptability in complex scenarios dealing with the redundancy problem of musculoskeletal system coordination and holds potential for the development of bio-inspired locomotion control through the optimization of muscle activity composition.

This paper proposes a fixture-free 2D sewing system using a dual-arm manipulator, i.e., the seam lines of the top and bottom fabric parts are the same. The proposed 2D sewing system sews two stacked fabric parts together along a desired seam line printed on the top fabric part without the use of a fixture. In the proposed system, the set of aligned and stacked fabric parts is held by the end-effectors of the dual-arm manipulator in coordination. The dual-arm manipulator controls the motion of the fabric parts on the flat sewing table stitch by stitch in coordination, while keeping the manipulated fabric parts flat using the internal force applied to the set of fabric parts. A novel vision-based seam line tracking control is proposed to control the motion of the set of fabric parts along the printed seam line on the top fabric part. The convergence of the tracking error is analyzed for sewing along both straight and curved seam lines and is shown to be specified by the control parameters. Sewing experiments show that the tracking error converges to zero as analyzed. The sewing experiments also show that the newly proposed trajectory generation method, which synchronizes the coordinated motion of the manipulators and the motion of the sewing needle, is essential for achieving accurate sewing.Note to Practitioners—Most semi-automatic sewing machines and pattern sewers on the market use fixtures to handle the stacked fabric parts. They require the user to customize the fixture depending on the shape, size, and material of the fabric parts to be sewn together. Users are required to redesign/reconfigure the fixture to sew different fabric parts. Our robotic sewing system is based on the concept of fixture-free sewing, i.e., the pose of the set of stacked fabric parts is controlled by the end-effectors without using the fixture. The internal force applied to the fabric parts by the end-effectors is used to keep the fabric parts flat, and the position of the fabric parts is controlled by the motions of the end-effectors in coordination with the proposed vision-based seam line tracking control. The proposed robotic sewing system provides practitioners with a new approach to fixture-free automatic sewing of fabric parts.

Collision avoidance is critical for ensuring the safe navigation of unmanned surface vehicles (USVs). This paper presents an end-to-end solution for local path planning of USVs, focusing on enhanced obstacle evasion and smoother navigation. By leveraging deep reinforcement learning (DRL), we enable direct translation of relative distance states into navigational actions, eliminating the need for cumbersome map maintenance and complex feature extraction. A novel observation modality, the “beam map”, is designed to accurately perceive obstacles in all directions, mimicking the functionality of an onboard LiDAR system. To further refine collision avoidance maneuver, a warning zone is introduced, adjusting the agent’s sensitivity to obstacles and allowing ample time and space for decision-making. Additionally, we propose a continuous-time short-distance constraint to calculate the International Regulations for Preventing Collision at Sea (COLREGs) adherence rewards, enabling legal and rational navigation without requiring prior knowledge of the encounter situation. Extensive experimental results, comparing various RL policies and classical methods, demonstrate the planner’s exceptional obstacle avoidance capability and adaptability to changing environments. Using real-world inland ship navigation data, four steering scenarios are designed to further validate the efficacy of the proposed method.

The latest robot navigation methods for dynamic environments assume that the states of obstacles, including their geometries and trajectories, are fully observable. While it’s easy to obtain these states accurately in simulations, it’s exceedingly challenging in the real world. Therefore, a viable alternative is to directly map raw sensor observations into robot actions. However, acquiring skills from high-dimensional raw observations demands massive neural networks and extended training periods. Furthermore, there are discrepancies between simulated and real environments that impede real-world implementations. To overcome these limitations, we propose a Learning framework for robot Navigation in Dynamic environments that uses sequential Normalized LiDAR (LNDNL) scans. We employ long-short-term memory (LSTM) to propagate historical environmental information from the sequential LiDAR observations. Additionally, we customize a LiDAR-integrated simulator to speed up sampling and normalize the geometry of real-world obstacles to match that of simulated objects, thereby bridging the sim-to-real gap. Our extensive comparisons with state-of-the-art baselines and real-world implementations demonstrate the potentials of learning to navigate in dynamic environments using raw sensor observations and sim-to-real transfer.

Humans can generate and sustain a wide range of walking velocities while optimizing their energy efficiency. Understanding the intricate mechanisms governing human walking will contribute to the engineering applications such as energy-efficient biped robots and walking assistive devices. Reflex-based control mechanisms, which generate motor patterns in response to sensory feedback, have shown promise in generating human-like walking in musculoskeletal models. However, the precise regulation of velocity remains a major challenge. This limitation makes it difficult to identify the essential reflex circuits for energy-efficient walking. To explore the reflex control mechanism and gain a better understanding of its energy-efficient maintenance mechanism, we extend the reflex-based control system to enable controlled walking velocities based on target speeds. We developed a novel performance-weighted least squares (PWLS) method to design a parameter modulator that optimizes walking efficiency while maintaining target velocity for the reflex-based bipedal system. We have successfully generated walking gaits from 0.7 to 1.6 m/s in a two-dimensional musculoskeletal model based on an input target velocity in the simulation environment. Our detailed analysis of the parameter modulator in a reflex-based system revealed two key reflex circuits that have a significant impact on energy efficiency. Furthermore, this finding was confirmed to be not influenced by setting parameters, i.e., leg length, sensory time delay, and weight coefficients in the objective cost function. These findings provide a powerful tool for exploring the neural bases of locomotion control while shedding light on the intricate mechanisms underlying human walking and hold significant potential for practical engineering applications.

Central Pattern generators (CPG) are a biologically inspired, decentralized control architecture that enables model-free, but yet adaptively stable and computational lightweight locomotion capabilities on complex robots. Nevertheless, no unified design guidelines for closed-loop CPG controllers are available in the literature. Therefore, we propose a task-distributed, end-to-end trainable, closed-loop CPG control policy by generalizing and extending Tegotae control. The Tegotae approach modulates CPG activity by quantifying the discrepancy between internal belief states and environmental reactions. Spontaneous and adaptive gait formation towards situationally efficient locomotion patterns are intrinsic properties of Tegotae control. The Tegotae control policy is trained and benchmarked in simulation on a 1D hopping robot. We found that our approach can learn efficient and adaptive locomotion on minimal feedback information, while out-performing unstructured, classic reinforcement learning policies of equal complexity. To the best of our knowledge, this is the first study to fully generalize the Tegotae approach and construct unimpeded, end-to-end trainable Tegotae control policies.

Insects exhibit adaptive walking behavior in an unstructured environment, despite having only an extremely small number of neurons (105to 106). This suggests that not only the brain nervous system but also properties of the physical body, such as the morphological characteristics, play an essential role in generating such adaptive behavior. Our study aims at investigating the effect of body morphological characteristics on the walking performance in a robot model, which is designed to mimic an insect. To this end, we constructed an insect-like hexapod model in a simulation environment that implements a reflex-based intra-limb coordination control. Herein, for a set of walking parameters, which were optimized to maximize the energy efficiency at the target speed, we investigated the effects of changes in the standard posture of the two leg joints on the walking success rate for various initial conditions and cost of transport (CoT) as an index of energy efficiency. Simulation results indicated that robots with specific morphological characteristics similar to those of insects exhibited high gait stability and energetic efficiency. Because only the reflex-based control was employed, the inter-leg coordination occurred spontaneously, suggesting that our approach would lead to a useful design methodology from the perspective of computational cost in generating the walking locomotion.

The state-of-the-art reinforcement learning (RL) techniques have made innumerable advancements in robot control, especially in combination with deep neural networks (DNNs), known as deep reinforcement learning (DRL). In this article, instead of reviewing the theoretical studies on RL, which were almost fully completed several decades ago, we summarize some state-of-the-art techniques added to commonly used RL frameworks for robot control. We mainly review bioinspired robots (BIRs) because they can learn to locomote or produce natural behaviors similar to animals and humans. With the ultimate goal of practical applications in real world, we further narrow our review scope to techniques that could aid in sim-to-real transfer. We categorized these techniques into four groups: 1) use of accurate simulators; 2) use of kinematic and dynamic models; 3) use of hierarchical and distributed controllers; and 4) use of demonstrations. The purposes of these four groups of techniques are to supply general and accurate environments for RL training, improve sampling efficiency, divide and conquer complex motion tasks and redundant robot structures, and acquire natural skills. We found that, by synthetically using these techniques, it is possible to deploy RL on physical BIRs in actuality.

Soft robotics is an emerging technology with excellent application prospects. However, due to the inherent compliance of the materials used to build soft robots, it is extremely complicated to control soft robots accurately. In this paper, we introduce a data-based control framework for solving the soft robot underwater locomotion problem using deep reinforcement learning (DRL). We first built a soft robot that can swim based on the dielectric elastomer actuator (DEA). We then modeled it in a simulation for the purpose of training the neural network and tested the performance of the control framework through real experiments on the robot. The framework includes the following: a simulation method for the soft robot that can be used to collect data for training the neural network, the neural network controller of the swimming robot trained in the simulation environment, and the computer vision method to collect the observation space from the real robot using a camera. We confirmed the effectiveness of the learning method for the soft swimming robot in the simulation environment by allowing the robot to learn how to move from a random initial state to a specific direction. After obtaining the trained neural network through the simulation, we deployed it on the real robot and tested the performance of the control framework. The soft robot successfully achieved the goal of moving in a straight line in disturbed water. The experimental results suggest the potential of using deep reinforcement learning to improve the locomotion ability of mobile soft robots.

Brain-computer interface (BCI) requires calibration phase to learn user-specific decoder that translates brain signals into desired commands. Calibration phase can be lengthy and exhausting for motor imagery-based (MI) BCI, and can potentially reduce the effectiveness of BCI system. Transfer learning (TL) approaches have been implemented in the field of BCI to tackle this problem. Transfer learning based on domain adaptation reduces domain discrepancy between two domains. Transfer component analysis (TCA) is one domain adaptation technique that maps features of both domains into a new space while simultaneously reducing their domain discrepancy. Recently, Euclidean alignment (EA) is used as transfer learning technique in BCI preprocessing step to align electroencephalography (EEG) trials between subjects. This paper proposed a combination of both EA and TCA (EA-TCA) as a TL approach for inter-subject transfer learning. This paper also proposed TCA method that can reuse existing projection matrix to transform new target data (TCA-W). The efficacy of EA to this method is also observed (EA-TCA-W). Results indicate that EA-TCA and EA-TCA-W outperform classification accuracy of those without EA by 3.32% and 6.50%, respectively. This concludes that EA can improve performance of both conventional TCA and proposed TCA-W.

Motor imagery (MI)-based brain-computer interface (BCI) is a system that allows users to control computer devices by imaging body part movements or MI tasks. In BCI applications, the classification of MI using electroencephalogram (EEG) is challenging because EEG is highly susceptible to noise and artifacts. The latency and length of MI period also vary between subjects and sessions; however, many conventional applications tend to empirically define time windows for feature extraction. This can lead to lower MI-BCI performance. This paper proposes two mutual information-based time window adaptation (MT) algorithms; sliding window MT (SWMT) and genetic algorithm MT (GAMT). Both algorithms used optimized reference signals and mutual information analysis to constantly adjust the time window starting point and length. Reference signals were optimized based on mutual information analysis and performance evaluation. Feature extraction and classification algorithms were finally applied to evaluate SWMT and GAMT performance. The results indicate that SWMT and GAMT were able to improve the conventional approach by increasing the classification accuracy by 6.00% and 6.37%, respectively.

Transcranial direct current stimulation (tDCS) has been shown to evoke hemodynamics response; however, the mechanisms have not been investigated systematically using systems biology approaches. Our study presents a grey-box linear model that was developed from a physiologically detailed multi-compartmental neurovascular unit model consisting of the vascular smooth muscle, perivascular space, synaptic space, and astrocyte glial cell. Then, model linearization was performed on the physiologically detailed nonlinear model to find appropriate complexity (Akaike information criterion) to fit functional near-infrared spectroscopy (fNIRS) based measure of blood volume changes, called cerebrovascular reactivity (CVR), to high-definition (HD) tDCS. The grey-box linear model was applied on the fNIRS-based CVR during the first 150 seconds of anodal HD-tDCS in eleven healthy humans. The grey-box linear models for each of the four nested pathways starting from tDCS scalp current density that perturbed synaptic potassium released from active neurons for Pathway 1, astrocytic transmembrane current for Pathway 2, perivascular potassium concentration for Pathway 3, and voltage-gated ion channel current on the smooth muscle cell for Pathway 4 were fitted to the total hemoglobin concentration (tHb) changes from optodes in the vicinity of 4x1 HD-tDCS electrodes as well as on the contralateral sensorimotor cortex. We found that the tDCS perturbation Pathway 3 presented the least mean square error (MSE, median <2.5%) and the lowest Akaike information criterion (AIC, median -1.726) from the individual grey-box linear model fitting at the targeted-region. Then, minimal realization transfer function with reduced-order approximations of the grey-box model pathways was fitted to the ensemble average tHb time series. Again, Pathway 3 with nine poles and two zeros (all free parameters), provided the best Goodness of Fit of 0.0078 for Chi-Square difference test of nested pathways. Therefore, our study provided a systems biology approach to investigate the initial transient hemodynamic response to tDCS based on fNIRS tHb data. Future studies need to investigate the steady-state responses, including steady-state oscillations found to be driven by calcium dynamics, where transcranial alternating current stimulation may provide frequency-dependent physiological entrainment for system identification. We postulate that such a mechanistic understanding from system identification of the hemodynamics response to transcranial electrical stimulation can facilitate adequate delivery of the current density to the neurovascular tissue under simultaneous portable imaging in various cerebrovascular diseases.

The development of algorithms for motion discrimination in home rehabilitation sessions poses numerous challenges. Recent studies have used the concept of synergies to discriminate a set of movements. However, the discrimination depends on the correlation of the reconstructed movement with the online data, and the training data requires well-defined movements. In this paper, we introduced the concept of a synergy probe, which makes a direct comparison between synergies and online data. The system represents synergies and movements in the same space and monitors their behavior. The results indicated that conventional methods are influenced by the segmentation of training data, and even though the reconstructed movement is similar to the ground-truth, it does not provide sufficient information to evaluate the data in real time. The synergy probes were used to discriminate and evaluate the performance of natural whole-body exercises without segmentation or previous determination of movements. An analysis of the results also demonstrated the possibility to identify the strategies used by the subjects for movement. Such information aids in gaining a better insight and can prove beneficial in home rehabilitation.

Differentiating muscle fatigue induced hand tremor of surgeons into different discernible levels is important in laparoscopic surgery. Systematic clustering can be used as a method to assess the risk of hand tremor which can largely affect the surgical performance. The prime challenges lying here are the detection of fatigue onset and classification of fatigue induced tremor level in dynamic laparoscopic tool manipulation. Conventionally, muscle fatigue is assessed with frequency domain analysis of the surface electromyography (sEMG) signal, where the detection process is predominantly valid only for isometric contraction of muscles. Conventional methods cannot be used for assessment of fatigue level in case of dynamic activities as the task itself modulates the frequency content of the myoelectric response. In this paper, we have proposed a novel polynomial Hammerstein model-based clustering of fatigue induced tremor, employing sEMG, and joint torques. The sEMG signal, containing muscle fatigue information, gets fused in this model dynamically through a Kalman filter. Model parameter-based clustering of the fatigue induced tremor level was implemented on eight subjects. Optimal number of cluster centers were found to be appropriately coherent with the fatigue inducing task epochs of the experiment. In spite of the subjective variations, the model parameter-based clustering method was able to differentiate among the fatigue-inducing tasks for all the subjects. We have concluded that this model-based clustering can successfully differentiate between different levels of the fatigue induced tremor in dynamic activity of laparoscopic tool manipulation.

Visual feedback in a brain computer interface (BCI) influences significantly in its performance; but when this BCI will be applied in a rehabilitation therapy for post stroke patients, it will be a determining factor to enhance the neuroplasticity process. Many studies have demonstrated the efficiency of virtual reality (VR) in a BCI, motor cortex increases its activation levels due to be an immersive environment for the subject; specifically, a BCI based on motor imagery (MI) with VR feedback has positive effects in patients. This work proposes to apply a BCI with VR to support an upper limb rehabilitation therapy for post stroke patients, but it has been tested with eighteen healthy subjects, they performed MI tasks of flexion and extension of their arms, then they could see a virtual arm in 3D performing the same requested movement. Comparison of power spectral density (PSD) estimation is done during MI tasks in training and online test sessions, and feedback in online test sessions; and it is possible to observe the brain activity in alpha and beta bands remained during online sessions, topographic map shows activated premotor and motor cortex areas, it is significant evidence for the application of this system to motor disable patients.

Functional Electrical Stimulation (FES) stimulates the affected region of the human body thus providing a neuroprosthetic interface to non-recovered muscle groups. FES in combination with Brain-computer interfacing (BCI) has a wide scope in rehabilitation because this system can directly link the cerebral motor intention of the users with its corresponding peripheral mucle activations. Such a rehabilitative system would contribute to improve the cortical and peripheral learning and thus, improve the recovery time of the patients. In this paper, we examine the effect of electrical stimulation by FES on the electroencephalography (EEG) during learning of a motor imagery task. The subjects are asked to perform four motor imagery tasks over six sessions and the features from the EEG are extracted using common spatial algorithm and decoded using linear discriminant analysis classifier. Feedback is provided in form of a visual medium and electrical stimulation representing the distance of the features from the hyperplane. Results suggest a significant improvement in the classification accuracy when the subject was induced with electrical stimulation along with visual feedback as compared to the standard visual one.

This paper proposes a novel brain-machine interfacing (BMI) paradigm for control of a multijoint redundant robot system. Here, the user would determine the direction of end-point movement of a 3-degrees of freedom (DOF) robot arm using motor imagery electroencephalography signal with co-adaptive decoder (adaptivity between the user and the decoder) while a synergetic motor learning algorithm manages a peripheral redundancy in multi-DOF joints toward energy optimality through tacit learning. As in human motor control, torque control paradigm is employed for a robot to be adaptive to the given physical environment. The dynamic condition of the robot arm is taken into consideration by the learning algorithm. Thus, the user needs to only think about the end-point movement of the robot arm, which allows simultaneous multijoints control by BMI. The support vector machine-based decoder designed in this paper is adaptive to the changing mental state of the user. Online experiments reveals that the users successfully reach their targets with an average decoder accuracy of over 75% in different end-point load conditions.

Human movement is produced resulting from synergetic combinations of multiple muscle contractions. The resultant joint movement can be estimated through the related multiple-muscle activities, which is formulated as the forward problem. Neuroprosthetic applications may benefit from cocontraction of agonist and antagonist muscle pairs to achieve more stable and robust joint movements. It is necessary to estimate the activation of each individual muscle from desired joint torque(s), which is the inverse problem. A synergy-based solution is presented for the inverse estimation of multiple muscle activations from joint movement, focusing on one degree-of-freedom tasks. The approach comprises muscle synergy extraction via the nonnegative matrix factorization algorithm. Cross validation is performed to evaluate the method for prediction accuracy based on experimental data from ten able-bodied subjects. The results demonstrate that the approach succeeds to inversely estimate the multiple muscle activities from the given joint torque sequence. In addition, the other one's averaged synergy ratio was applied for muscle activation estimation with leave-one-out cross-validation manner, which resulted in 9.3% estimation error over all the subjects. The obtained results support the common muscle synergy-based neuroprosthetics control concept.

A human's center of mass (CoM) trajectory is useful to evaluate the dynamic stability during daily life activities such as walking and standing up. To estimate the subject-specific CoM position in the home environment, we make use of a statically equivalent serial chain (SESC) developed with a portable measurement system. In this paper we implement a constrained Kalman filter to achieve an online estimation of the SESC parameters while accounting for the human body's bilateral symmetry. This results in constraining SESC parameters to be consistent with the human skeletal model used. The proposed identification method can inform the subject or the therapist, in real-time, about the quality of the on-going CoM estimation. This information can be helpful to reduce the identification time and establish a personalized protocol. A Kinect is used as a markerless motion capture system for measuring limb orientations while the Wii board is used to measure the subject's center of pressure (CoP) during the identification phase. CoP measurements and Kinect data were recorded for four able-bodied subjects. The recorded data was then given to the proposed recursive algorithm to identify the parameters of the SESC online. A cross-validation test was performed to verify the identification performance. The results for these subjects are shown and discussed.

Center of mass (CoM) estimation can be used to evaluate human stability during rehabilitation. A personalized estimation can be obtained using the serial equivalent static chain (SESC) method, calibrated using a series of static postures. The estimation accuracy is dependent on the number and quality of poses used during calibration. Currently, this limits the method's application to unimpaired individuals. We present a preliminary study of a SESC identified in a multi-contact scenario during a Sit-to-Stand task. Stanford's SAI (Simulation and Active Interface) platform was used to emulate motion and predict relevant reaction forces. The CoM estimation obtained is valid for motions similar to those used during identification. Using a three-dimensional model, the estimated mean error was less than 26 millimetres for a Sit-to-Stand task involving displacements along all axes. As such, personalized CoM estimation can be available for patients with a limited range of whole body motion.

Center of mass (CoM) trajectory is important during standing and walking since it can be used as an index for stability and fall prediction. Unfortunately current methods for CoM estimation require the use of specialized equipment (such as motion capture and force platforms) in controlled environments. This paper aims at applying the statically equivalent serial chain (SESC) method to obtain CoM position using widely available and portable hardware; a Microsoft's Kinect and a Nintendo's Wii balance board. During identification, CoM is approximated by CoP measurements and the virtual chain is created for able-bodied subjects. The result demostrates that the SESC method can be applied outside the laboratory environment using a Kinect. Cross-validation of the identified model was performed to evaluate the accuracy of the method. Results obtained of five subjects are shown and discussed.

Functional electrical stimulation (FES) is able to restore motor function of spinal cord injured (SCI) patients. To make adaptive FES control taking into account the actual muscle state with muscular feedback information, torque estimation and prediction are important to be provided beforehand. Evoked EMG (eEMG) has been found to be highly correlated with FES-induced torque under various muscle conditions, indicating that it can be an useful tool for torque/force prediction. To better construct the relationship between eEMG and stimulated muscular torque, nonlinear-arx-type (NARX-type) model is preferred. This paper presents and exploits a NARX-type recurrent neural network (NARX-RNN) model for identification and prediction of FES-induced muscular dynamics with eEMG. Such NARX-RNN model is with a novel architecture for prediction, with robust prediction performance. To make fast convergence for identification of such NARX-RNN, directly-learning pattern is exploited during the learning phase. Due to difficulty of choosing a proper forgetting factor of Kalman filter for predicting time-variant torque with eEMG, such NARX-RNN may be considered to be a better alternative as torque predictor. Data gathered from two SCI patients is used to evaluate the proposed NARX-RNN model. The NARX-RNN model shows promising estimation and prediction performance only based on eEMG.

Functional electrical stimulation (FES) is effective to restore movement in spinal cord injured (SCI) subjects. Unfortunately, muscle fatigue constrains the application of FES so that output torque feedback is interesting for fatigue compensation. Whereas, inadequacy of torque sensors is another challenge for FES control. Torque estimation is thereby essential in fatigue tracking task for practical FES employment. In this work, the Hammstein cascade with electromyography (EMG) as input is applied to model the myoelectrical mechanical behavior of the stimulated muscle. Kalman filter with forgetting factor is presented to estimate the muscle model and track fatigue. Fatigue inducing protocol was conducted on three SCI subjects through surface electrical stimulation. Assessment in simulation and with experimental data reveals that the muscle model properly fits the muscle behavior well. Moreover, the time-varying parameters tracking performance in simulation is efficient such that real time tracking is feasible with Kalman filter. The fatigue tracking with experimental data further demonstrates that the proposed method is suitable for fatigue tracking as well as adaptive torque prediction at different prediction horizons.

In current biomechanics approach, the assumptions are commonly used in body-segment parameters and muscle strength parameters due to the difficulty in accessing those subject-specific values. Especially in the rehabilitation and sports science where each subject can easily have quite different anthropometry and muscle condition due to disease, age or training history, it would be important to identify those parameters to take benefits correctly from the recent advances in computational musculoskeletal modeling. In this paper, Mass Distribution Identification to improve the joint torque estimation and Muscle Strength Identification to improve the muscle force estimation were performed combined with previously proposed methods in muscle tension optimization. This first result highlights that the reliable muscle force estimation could be extracted after these identifications. The proposed framework toward subject-specific musculoskeletal modeling would contribute to a patient-oriented computational rehabilitation.

Electrical stimulation (ES) is one of the solutions for drop foot correction. Conventional ES systems deliver predefined stimulation pattern to the affected muscles. However, time-variant muscle response may influence the gait performance as they are difficult to be taken into account in advance. Therefore, closed-loop ES control is important to obtain desired gait in presence of muscle response variation. In this work, a dual predictive control, which consists of two nonlinear generalized predictive controllers, is proposed to track desired torque. The stimulated muscle dynamics are modeled by Hammerstein cascades, with one representing stimulation to activation, the other representing activation to torque. Ankle dorsiflexion torque and ES-evoked EMG of tibialis anterior were recorded experimentally for model identification. The control scheme is validated by following desired torque trajectories with the identified model. The results show that the stimulation pattern obtained from the dual predictive control can produce good torque tracking according to the current muscle condition.

EMG-to-force estimation for voluntary muscle contraction has many applications in human-machine interaction, motion analysis, and rehabilitation robotics for prosthetic limbs or exoskeletons. EMG-based model can account for a subject's individual activation patterns to estimate muscle force. For the estimation, so-called Hill-type model has been used in most of the cases. It already has shown its promising performance, but it is still known as a phenomenological model considering only macroscopic physiology. We have already developed the physiological based muscle model for the use of functional electrical stimulation (FES) which can render the myoelectrical property also in microscopic scale. In this paper we discuss EMG-to-force estimation based on this full physiological based muscle model in voluntary contraction. In addition to Hill macroscopic structure, a microscopic physiology originally designed by Huxley is integrated. It has significant meaning to realize the same kind of EMG-to-force estimation with a physiological based model not with a phenomenological model, because it brings the understanding of the internal biophysical dynamics and new insights about neuromuscular activations. Using same EMG data of isometric muscle contraction, the force estimation results are shown by classical approach and new physiological based approach. Its interpretation is also discussed.

A model-based FES would be very helpful for the adaptive movement synthesis of spinal-cord-injured patients. For the fulfillment, we need a precise skeletal muscle model to predict the force of each muscle. Thus, we have to estimate many unknown parameters in the nonlinear muscle system. The identification process is essential for the realistic force prediction. We previously proposed a mathematical muscle model of skeletal muscle which describes the complex physiological system of skeletal muscle based on the macroscopic Hill-Maxwell and microscopic Huxley concepts. It has an original skeletal muscle model to enable consideration for the muscular masses and the viscous frictions caused by the muscle-tendon complex. In this paper, we present an experimental identification method of biomechanical parameters using Sigma-Point Kalman Filter applied to the nonlinear skeletal muscle model. Result of the identification shows its effective performance. The evaluation is provided by comparing the estimated isometric force with experimental data with the stimulation of the rabbit medial gastrocnemius muscle. This approach has the advantage of fast and robust computation, that can be implemented for online application of FES control.

Precise measurements of geometry should accompany robotic equipment in operating theatres, for greatest advantage. For deforming organs, including liver, intraoperative geometric measurements play an essential role in computer surgery in addition to pre-operative geometric information from CT, MRI and so on. We developed a laser-pointing endoscope using an optical galvano scanner and a 955 fps high-speed camera. The laser-pointing endoscope system acquires and visualizes the shape of the area of interest in a flash of time. Applications of the system also include the touch screen interface for nonmaster-slave operation of surgical robots, where the 3D coordinates of the touched point on screen are measured by the system and guide a robot. Results of in-vivo experiments on a liver of pig verify the effectiveness of the proposed system.