This study introduces a novel approach to swarm leader identification (SLI) in multi-agent robot systems by employing a physical adversary interacting with the swarm in the same environment. We develop a new simulation environment to study the SLI problem and train an adversary, which we term the prober, to solve the SLI problem using forceful interactions with the swarm as its guiding information source. The prober's policy is modeled using the simplified structure state space sequence (S5) model and trained with the Proximal Policy Optimization (PPO) algorithm. The prober only has access to the information on the relative positions of the other agents. We evaluate our approach through extensive simulations using two performance metrics and validate the sim-to-real transfer through robot experiments. Results on evaluating the performance in 10,000 different testing scenarios demonstrate that our method finds the leader's identity in the vast majority (95.7%) of the cases, regardless of the initial leader selection during training. The proposed system represents the first instance of learning-based automatic identification of leader agents in a swarm. This capability is crucial for enabling efficient and robust human-swarm interaction, understanding artificial swarm behaviors, and analyzing latent behaviors in biological swarms in nature.

We present a control framework specifically for physical human-humanoid collaboration involving the transportation and manipulation of heavy objects. Using this framework, the humanoid can exhibit desired levels of compliance with the object to be co-transported. This desired compliance is achieved through an admittance model. A Model Predictive Control (MPC) problem, based on a novel Interaction Linear Inverted Pendulum (I-LIP) model, generates footstep patterns that facilitate this desired compliant behavior while keeping the robot stable. Subsequently, we have an object-informed low-level quadratic program (QP) that sends control input to realize the high-level plans on the robot. The stiffness parameters of the I-LIP are modulated in real time for better compliance tracking performance of the robot. We verify all the results through simulation on the humanoid platform, the Digit, showing the prowess of the framework in collaboratively transporting heavy objects with a human.

Trust is an essential building block of human civilization. However, when it relates to artificial systems, it has been a barrier to intelligent technology adoption in general. This article addresses the gap in determining levels of trust in scenarios that include humans interacting with a swarm of robots. Electroencephalography (EEG) recordings of the human observers of the different swarms allow for extracting specific EEG features related to different trust levels. Feature selection and machine learning methods comprise a classification system that would allow recognition of different levels of human trust in those human–swarm interaction scenarios. The results of this study suggest that EEG correlates of swarm trust exist and are distinguishable in machine learning feature classification with very high accuracy. Moreover, comparing common EEG features across all human subjects used in this study allows for the generalization of the classification method, providing solid evidence of specific areas and features of the human brain where activations are related to levels of human–swarm trust. This work has direct implications for effective human–machine teaming with applications to many fields, such as exploration, search and rescue operations, surveillance, environmental monitoring, and defense. In these applications, quantifying levels of human trust in the deployed swarm is of utmost importance because it can lead to swarm controllers that adapt their output based on the human's perceived trust level.

Human gait is quite complex, especially when considering the irregular and uncertain environments that humans are able to walk in. While unperturbed gait in a controlled environment is understood to a large degree, gait in more unique environments, such as asymmetric compliant terrain, is not understood to the same degree. In this study, we build upon a neuromuscular gait model and extend it to allow for walking on unilaterally compliant (soft) surfaces. This model is then compared to and verified by experimental human data. The model can successfully walk with step length trends similar to human data. Additionally, the model shows similar behaviors with respect to kinematics and muscle activity. We believe this work contributes significantly to a better understanding of the control of human gait and could lead to model-informed, patient-specific rehabilitation strategies that can advance the field of rehabilitation robotics, as well as the development of bio-inspired controllers for bipedal robots that would be able to traverse through dynamic and complaint terrains.

Substantial research and development on the design and control of robotic ankle-foot prostheses have aimed to restore normal function and movement capacity for people with gait impairments and lower limb amputations. However, prostheses controllers usually fail to incorporate information pertaining to the properties of the walking terrain, such as ground stiffness. There is therefore a need for a framework that adjusts the prostheses parameters according to the user's intent to transition to a variable impedance terrain. To achieve this, we need to incorporate the human wearer in the control loop of the prosthesis. This work proposes an advanced, high-level controller framework for powered ankle-foot prostheses that combines subject-specific pattern recognition (PR) and classification strategies to predict whether the next step will be on a rigid or compliant surface. Comparing the Support Vector Machine (SVM) and k-Nearest Neighbors (k-NN) classification algorithms for this task, we conclude that by combining a k-NN implementation with a Pattern Recognition Neural Network (PR NN), our method can accurately forecast upcoming surface stiffness transitions in time to allow for prompt adaptation to the new walking terrain. We also show that the sensor fusion of kinematic and surface electromyographic (EMG) data outperforms single-source inputs producing the best prediction results for all subjects with an accuracy of up to 87.5%.

Despite significant advances in the design of robotic lower-limb prostheses for individuals with impaired mobility, there is a need for further progress in improving the robustness, safety, and stability of these devices in a wide range of activities of daily living. Although powered prostheses have been able to adapt to different speeds, conditions, and rigid terrains, no control strategies have been proposed for addressing walking over compliant surfaces. This work proposes a continuous admittance controller that adjusts the ankle quasistiffness of a powered ankle-foot prosthesis and improves gait stability during locomotion over compliant terrain. The proposed controller is evaluated with walking experiments on an instrumented treadmill that can accurately change the walking surface stiffness. In these experiments, the proposed controller accurately changes the prosthesis ankle quasi-stiffness across a wide range of$10-20\frac{Nm}{deg}-($while improving local dynamic stability compared to a standard phase-variable controller. The proposed controller can significantly improve the performance of lower-limb prostheses in dynamic and compliant environments frequently encountered in daily activities, resulting in improved quality of life for people with lower-limb amputation.

Due to hemiparesis, stroke survivors frequently develop a dysfunctional gait that is often characterized by an overall decrease in walking speed and a unilateral decrease in step length. With millions currently affected by this dys-functional gait, robust and effective rehabilitation protocols are needed. Although robotic devices have been used in numerous rehabilitation protocols for gait, the lack of significant afteref-fects that translate to effective therapy makes their application still questionable. This paper proposes a novel type of robot-assisted intervention that results in significant aftereffects that last much longer than any other previous study. With the utilization of a novel robotic device, the Variable Stiffness Treadmill (VST), the stiffness of the walking surface underneath one leg is decreased for a number of steps. This unilateral stiffness perturbation results in a significant aftereffect that is both useful for stroke rehabilitation and often lasts for over 200 gait cycles after the intervention has concluded. More specifically, the aftereffect created is an increase in both left and right step lengths, with the unperturbed step length increasing significantly more than the perturbed. These effects may be helpful in correcting two of the most common issues in post-stroke gait: overall decrease in walking speed and a unilateral shortened step length. The results of this work show that a robot-assisted therapy protocol involving repeated unilateral stiffness perturbations can lead to a more permanent and effective solution to post-stroke gait.

With over 10 million people currently suffering from significant long-term gait disability in the United States only, robot-assisted rehabilitation and wearable devices are increasingly gaining attention as a mean to regain functional mobility. Since these devices work collaborative and synchronously with the human gait, it is necessary to be able to detect gait events, such as heel-strikes, in real-time. Although many algorithms have been proposed for detecting heel-strikes with either wearable (e.g. Inertial Measurement Units (IMUs)) or non-wearable (e.g. force plates) sensors, there is a great need for employing less obtrusive and reliable sensors that rely only on recording the kinematics of the leg motion. This work proposes a novel and efficient kinematic algorithm, called the Foot VErtical & Sagittal Position Algorithm (F-VESPA), which has several advantages over existing methods. First, it accurately estimates heel-strike events using kinematic data without requiring access to future data points, rendering it the first to our knowledge kinematic algorithm capable of real-time implementation during treadmill walking. Moreover, it does not require tuning of the utilized parameters, rendering it robust to different subjects, conditions and equipment. The algorithm is tested in a large set of subjects across various treadmill speeds, and it is shown to outperform online and offline implementations of existing prominent kinematic algorithms. Using a 150 Hz data collection system, the F-VESPA achieved a total true error of 33 ms (median) in detecting heel-strike. The F-VESPA is the first to our knowledge kinematic algorithm that can detect heel-strike events during treadmill walking in real-time, with high accuracy, robustness and fast response, enabling real-time control of a variety of assistive platforms and devices, among others.

The role of various types of robot assistance in post-stroke gait rehabilitation has gained much attention in recent years. Furthermore, there is increased popularity to use more than one rehabilitation method in order to utilize the different advantages of each. Naturally, this results in the need to study how the different robot-assisted interventions affect the various underlying sensorimotor mechanisms involved in rehabilitation. To answer this important question, this paper combines a virtual reality experience with a unique robotic rehabilitation device, the Variable Stiffness Treadmill (VST), as a way of understanding interactions across different sensorimotor mechanisms involved in gait. The VST changes the walking surface stiffness in order to simulate real-world compliant surfaces while seamlessly interacting with a virtual environment. Through the manipulated visual and proprioceptive feedback, this paper focuses on the muscle activation patterns before, during, and after surface changes that are both visually informed and uninformed. The results show that there are predictable and repeatable muscle activation patterns both before and after surface stiffness changes, and these patterns are affected by the perceived visual and proprioceptive feedback. The interaction of feedback mechanisms and their effect on evoked muscular activation can be used in future robot-assisted gait therapies, where the intended muscle responses are informed by deterministic models and are tailored to a specific patient's needs.

The purpose of this work is to optimize the stiffness of a novel parallel-actuated robotic exoskeleton designed to offer a large workspace. This is done in an effort to help provide a solution to the issue wearable parallel actuated robots face regarding a tradeoff between stiffness and workspace. Presented in the form of a shoulder exoskeleton, the device demonstrates a new parallel architecture that can be used for wearable hip, ankle and wrist robots as well. The stiffness of the architecture is dependent on the placement of its actuated substructures. Therefore, it is desirable to place these substructures effectively so as to maximize dynamic performance for any application. In this work, an analytical stiffness model of the device is created and validated experimentally. The model is then used, along with a method of bounded nonlinear multi-objective optimization to configure the parallel actuators so as to maximize stiffness for the entire workspace. Furthermore, it is shown how to use the same technique to optimize the device for a particular task, such as lifting in the sagittal plane.

Human Swarm Interaction (HSI) is a new field which relates to the effective control of robotic swarms by human operators. The iterature has shown that the control of swarms can become quite complicated. On the other hand, Brain Machine Interfaces (BMI) can offer intuitive control in a plethora of applications where other interfaces alone (e.g. joysticks) are inadequate or impractical, e.g. for people with motor disabilities. There are multiple types of BMI, but most of them rely on the analysis of ElectroEncephaloGraphic (EEG) signals. The authors have previously shown that swarm behaviors elicit specific brain activity on human subjects that observe them. Motivated by this result, in this work, we present preliminary results of a hybrid BMI that combines information from the brain and an external device. An algorithm for extracting information from the frequency domain of EEG signals that allows integration with the manual task of using a joystick is presented. The hybrid interface shows high accuracy and robustness when used as a brain-robot interface. Moreover, it allows for continuous control variables extracted from the EEG signals. Finally, its efficacy is proven across multiple subjects, while its performance is also demonstrated in the real-time control of a swarm of quadrotors.

Gait impairment due to neurological disorders has become an important problem of the 21st century. Stroke is a leading cause of long-term disability with approximately 90% of stroke survivors having some functional disability, with mobility being a major impairment. Despite the growing interest in using robotic devices for rehabilitation of sensorimotor function, their widespread use remains somewhat limited, as results so far in gait rehabilitation do not generally show improved outcomes over traditional treadmill-based therapy. This work focuses on understanding the mechanisms of inter-leg coordination, and based on that, proposing novel methods for gait rehabilitation. Using a novel robotic device, the Variable Stiffness Treadmill (VST), we apply walking surface stiffness perturbations to one leg, and analyze the response of the human nervous system in both low- (muscle) and high- (brain) levels, focusing on the mechanisms involved in the response of the other (unperturbed) leg. We show that the unperturbed leg uniquely responds to unilateral stiffness perturbations, while we provide solid evidence that the brain is involved in this observed inter-leg coordination. From a clinical prospective, the results of this study can be disruptive since they suggest that supraspinal neural activity can be evoked by altering the stiffness of the walking surface. Moreover, our methods provide a safe and targeted way to provide gait rehabilitation in hemiparesis since direct manipulation of the paretic side is not required. The present work provides for the first time evidence that specific robotic intervention in gait rehabilitation can have direct and predictable effects on the brain, opening a new avenue of research on targeted robot-assisted gait rehabilitation.

Myoelectric control has seen decades of research as a potential interface between human and machines. High-density surface electromyography (HDsEMG) non-invasively provides a rich set of signals representing underlying muscle contractions and, at a higher level, human motion intent. Many pattern recognition techniques have been proposed to predict motions based on these signals. However, control schemes incorporating pattern recognition struggle with long-term reliability due to signal stochasticity and transient changes. This study proposes an alternative approach for HDsEMG-based interfaces using concepts of motor skill learning and muscle synergies to address long-term reliability. Muscle synergy-inspired decomposition reduces HDsEMG into control inputs robust to small electrode displacements. The novel control scheme provides simultaneous and proportional control, and is learned by the subject simply by interacting with the device. In a multiple-day experiment, subjects learned to control a virtual 7-DoF myoelectric interface, displaying performance learning curves consistent with motor skill learning. On a separate day, subjects intuitively transferred this learning to demonstrate precision tasks with a 7-DoF robot arm, without requiring any recalibration. These results suggest that the proposed method may be a practical alternative to pattern recognition-based control for long-term use of myoelectric interfaces.

Robotic devices have been used in a variety of rehabilitation protocols, including gait rehabilitation after stroke. However, robotic intervention in gait therapy has only produced moderate results compared to conventional physiotherapy. We suggest a novel approach to robotic interventions which takes advantage of inter-limb coordination mechanisms. We hypothesize the existence of a mechanism of inter-leg coordination that may remain intact after a hemiplegic stroke that may be utilized to obtain functional improvement of the impaired leg. One of the most significant advantages of this approach is the safety of the patient, since this does not require any direct manipulation of the impaired leg. In this paper, we focus on designing and applying unilateral perturbations that evoke contralateral leg motions through mechanisms of inter-leg coordination. Real-time control of floor stiffness is utilized to uniquely differentiate force and kinematic feedback, creating novel perturbations. We present results of repeatable and scalable evoked muscle activity of the contralateral tibialis anterior muscle through unilateral stiffness perturbations. We also present a mathematical model that accurately describes the relationship between the magnitude of the stiffness perturbation and the evoked muscle activity, that could result in model-based rehabilitation strategies for impaired walkers. The novel methods and results presented in this paper set the foundation for a paradigm shift of robotic interventions for gait rehabilitation.

As the expansion of the field of robotics has continued, the physical interaction between robots and humans has become an increasingly important area of study. Many of these physical interactions can be seen as a cooperative task conducted by both the robot and the human. Often, when two humans are interacting, one of them will act as the leader of some aspect of the task and the other will act as a follower. This cooperation may require the switching of roles between leader and follower. This can be further complicated by the fact that different participants may be the leaders of different aspects of the task. Previous research in human-robot cooperation focused on the switching of only a single role. In this paper, we investigate a novel method for the simultaneous switching of two roles between a robot and a human participant. This switching method was examined using both fixed and adaptive parameters that control role switching. Overall, human-robot cooperation was successful in the task 85% of the time when using a non-adaptive method and 95% when using an adaptive control method.

Proportional myoelectric control has been proposed for user-friendly interaction with prostheses, orthoses, and new human-machine interfaces. Recent research has stressed intuitive controls that mimic human intentions. However, these controls have limited accuracy and functionality, resulting in user-specific decoders with upper-bound constraints on performance. Thus, myoelectric controls have yet to realize their potential as a natural interface between humans and multifunctional robotic controls. This study supports a shift in myoelectric control schemes toward proportional simultaneous controls learned through the development of unique muscle synergies. A multiple day study reveals natural emergence of a new muscle synergy space as subjects identify the system dynamics of a myoelectric interface. These synergies correlate with long-term learning, increasing performance over consecutive days. Synergies are maintained after one week, helping subjects retain efficient control and generalize performance to new tasks. The extension to robot control is also demonstrated with a robot arm performing reach-to-grasp tasks in a plane. The ability to enhance, retain, and generalize control, without needing to recalibrate or retrain the system, supports control schemes promoting synergy development, not necessarily user-specific decoders trained on a subset of existing synergies, for efficient myoelectric interfaces designed for long-term use.

Locomotion is one of the human's most important functions that serve survival, progress and interaction. Gait requires kinematic and dynamic coordination of the limbs and muscles, multi-sensory fusion and robust control mechanisms. The force stimulus generated by the interaction of the foot with the walking surface is a vital part of the human gait. Although there have been many studies trying to decipher the load feedback mechanisms of gait, there is a need for the development of a versatile system that can advance research and provide new functionality. In this paper, we present the design and characterization of a novel system, called Variable Stiffness Treadmill (VST). The device is capable of controlling load feedback stimulus by regulating the walking surface stiffness in real time. The high range of available stiffness, the resolution and accuracy of the device, as well as the ability to regulate stiffness within the stance phase of walking, are some of the unique characteristics of the VST. We present experiments with healthy subjects in order to prove the concept of our device and preliminary findings on the effect of altered stiffness on gait kinematics. The developed system constitutes a uniquely useful research tool, which can improve our understanding of gait and create new avenues of research on gait analysis and rehabilitation.

Myoelectric controlled interfaces are a vital component for advancing applications in prostheses, exoskeletons, and robot teleoperation. Current methods search for optimal neural decoders for enhanced initial user performance. However, recent studies demonstrate learning an inverse model of abstract decoders to improve performance over time. This paper proposes a paradigm shift on myoelectric interfaces by embedding the human as controller of a system and allowing the human to learn how to control it via control tasks with similar mapping functions. The method is tested using two different control tasks and four different abstract mappings of upper limb myoelectric signals to control actions for those tasks. The results confirm that all subjects are able to learn the mappings and improve performance efficiency over time. A cross-trial evaluation reveals a significant learning transfer when a new control task is presented using the same mapping as a previous task, resulting in enhanced initial performance with the new task. Comparison of EMG signal evolution across subjects indicates a significant population-wide muscle synergy development that results from learning and implementing the inverse model of the mapping function to complete the tasks. This suggests that efficient performance may be achieved by learning a constant, arbitrary mapping function applied to multiple control tasks rather than dynamic subject- or task-specific functions. Moreover, this method can be used for the neural control of any device or robot, without restricting them to anthropomorphic or human-related counterparts.

The etymology of the word “Anthropos”, the Greek word for Human, includes one of the defining characteristics of human beings, which is the ability to stand upright and walk. Locomotion is one of the human's most important functions that serve survival, progress and interaction. The force stimulus generated by the interaction of the foot with the walking surface is a vital part of human gait. Although there have been many studies trying to decipher the load feedback mechanisms of gait, there is a need for the development of a versatile system that can advance research and provide new functionality. Moreover, the role of the load feedback in inter-leg coordination during walking is still not well understood. In this paper, we present a series of studies that attempt to shed light on the role of load feedback on inter-leg coordination using a novel system, called Variable Stiffness Treadmill (VST). The device is capable of controlling load feedback stimulus by regulating the walking surface stiffness in real time. We first present the main functionality of the VST, focusing on the real-time closed-loop control of stiffness. Using perturbations of the treadmill stiffness on one leg of healthy subjects, we investigate the inter-leg coordination mechanisms, in body-weight-supported gait. Results show that ipsilateral stiffness perturbations, affect the contralateral (unperturbed) leg in body-weight-supported gait, while their effect is dependent on the timing of the induced stiffness perturbations. The developed system and experimental protocols are uniquely useful for gait research, can improve our understanding of gait, and create new avenues of research on gait analysis, walking robots and gait rehabilitation.

In this paper a comparative analysis between the human and three robotic hands is conducted. A series of metrics are introduced to quantify anthropomorphism and assess robot's ability to mimic the human hand. In order to quantify anthropomorphism we choose to compare human and robot hands in two different levels: comparing finger phalanges workspaces and comparing workspaces of the fingers base frames. The final score of anthropomorphism uses a set of weighting factors that can be adjusted according to the specifications of each study, providing always a normalized score between 0 (non-anthropomorphic) and 1 (human-identical). The proposed methodology can be used in order to grade the human-likeness of existing and new robotic hands, as well as to provide specifications for the design of the next generation of anthropomorphic hands. Those hands can be used for human robot interaction applications, humanoids or even prostheses.

In this paper teleoperation and telemanipulation with a robot arm (Mitsubishi PA-10) and a robot hand (DLR/HIT 2) is performed, using a human to robot motion mapping scheme that guarantees anthropomorphism. Two position trackers are used to capture position and orientation of human end-effector (wrist) and human elbow in 3D space and a dataglove to capture human hand kinematics. Then the inverse kinematics (IK) of the Mitsubishi PA-10 7-DoF robot arm are solved in an analytical manner, in order for the human's and the robot artifact's end-effectors to achieve same position and orientation in 3D space (functional constraint). Redundancy is handled in the solution space of the robot arm's IK, selecting the most anthropomorphic solution computed, with a criterion of “Functional Anthropomorphism”. Human hand motion is transformed to robot hand motion using the joint-to-joint mapping methodology. Finally in order for the user to be able to detect contact and “perceive” the forces exerted by the robot hand, a low-cost force feedback device, that provides a mixture of sensory information (visual and vibrotactile), was developed.

A learning scheme based on random forests is used to discriminate between different reach to grasp movements in 3-D space, based on the myoelectric activity of human muscles of the upper-arm and the forearm. Task specificity for motion decoding is introduced in two different levels: Subspace to move toward and object to be grasped. The discrimination between the different reach to grasp strategies is accomplished with machine learning techniques for classification. The classification decision is then used in order to trigger an EMG-based task-specific motion decoding model. Task specific models manage to outperform "general" models providing better estimation accuracy. Thus, the proposed scheme takes advantage of a framework incorporating both a classifier and a regressor that cooperate advantageously in order to split the task space. The proposed learning scheme can be easily used to a series of EMG-based interfaces that must operate in real time, providing data-driven capabilities for multiclass problems, that occur in everyday life complex environments.

Studying human motor control has received increased attention during the past decades. Both the design and control of robotic artifacts may benefit from observation of human behavior. In this paper a novel method for capturing the dynamic behavior of the human hand is presented. The low dimensional kinematics of the human hand, including the wrist, and the low dimensional representation of the muscular activations were correlated through a linear time invariant (LTI) state space model. A linear output regulation controller was used in order to drive a simulated hand and the resulting trajectories were compared with the experimentally captured trajectories.

This paper proposes a method to construct Navigation Functions (NF) from experimental trajectories in an unknown environment. We want to approximate an unknown obstacle function and then use it within an NF. When navigating the same destinations with the experiments, this NF should produce the same trajectories as the experiments. This requirement is equivalent to a partial differential equation (PDE). Solving the PDE yields the unknown obstacle function, expressed with spline basis functions. We apply this new method to anthropomorphic grasping, producing automatic trajectories similar to the observed ones. The grasping experiments were performed for a set of different objects, Principal Component Analysis (PCA) allows reduction of the configuration space dimension, where the learning NF method is then applied.

Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.

In this paper we propose a generic methodology for human to robot motion mapping for the case of a robotic arm hand system, allowing anthropomorphism. For doing so we discriminate between Functional Anthropomorphism and Perceptional Anthropomorphism, focusing on the first to achieve anthropomorphic solutions of the inverse kinematics for a redundant robot arm. Regarding hand motion mapping, a “wrist” (end-effector) offset to compensate for differences between human and robot hand dimensions is applied and the fingertips mapping methodology is used. Two different mapping scenarios are also examined: mapping for teleoperation and mapping for autonomous operation. The proposed methodology can be applied to a variety of human robot interaction applications, that require a special focus on anthropomorphism.

Walking impairments are a common sequela of neurological injury, severely affecting the quality of life of both adults and children. Gait therapy is the traditional approach to ameliorate the problem by re-training the nervous system and there have been some attempts to mechanize such approach. We have recently presented the MIT-Skywalker; a novel device to deliver gait therapy, which, in contrast to previous approaches, takes advantage of the concept of passive walkers and the natural dynamics of the lower extremity in order to deliver more "ecological" therapy. In this paper we present a control scheme for the MIT-Skywalker, which is based on an artificial potential field applied at the foot workspace. It is used to improve sensory feedback to the patient, as well as to increase to normal the range of motion of the paretic leg. Simulation results prove the efficiency of the proposed controller.

Coupling the human upper limbs with robotic devices is gaining increasing attention in the last decade, due to the emerging applications in orthotics, prosthetics and rehabilitation devices. In the cases of every-day life tasks, force exertion and generally interaction with the environment is absolutely critical. Therefore, the decoding of the user's force exertion intention is important for the robust control of orthotic robots (e.g. arm exoskeletons). In this paper, the human arm manipulability is analyzed and its effect on the recruitment of the musculo-skeletal system is explored. It was found that the recruitment and activation of muscles is strongly affected by arm manipulability. Based on this finding, a decoding method is built in order to estimate force exerted in the three-dimensional (3D) task space from surface ElectroMyoGraphic (EMG) signals, recorded from muscles of the arm. The method is using the manipulability information for the given force task. Experimental results were verified in various arm configurations with two subjects.

Human-robot control interfaces have received increased attention during the last decades. These interfaces increasingly use signals coming directly from humans since there is a strong necessity for simple and natural control interfaces. In this paper, electromyographic (EMG) signals from the muscles of the human upper limb are used as the control interface between the user and a robot arm. A switching regime model is used to decode the EMG activity of 11 muscles to a continuous representation of arm motion in the 3-D space. The switching regime model is used to overcome the main difficulties of the EMG-based control systems, i.e., the nonlinearity of the relationship between the EMG recordings and the arm motion, as well as the nonstationarity of EMG signals with respect to time. The proposed interface allows the user to control in real time an anthropomorphic robot arm in the 3-D space. The efficiency of the method is assessed through real-time experiments of four persons performing random arm motions.

Humans perform a wide range of skillful and dexterous motion by adjusting the dynamic characteristics of their musculoskeletal system during motion. This capability is based on the non-linear characteristics of the muscles and the motor control architecture that can control motion and exerted force independently. Mechanical impedance (i.e. stiffness, viscosity and inertia) constitutes the most solid characteristic for describing the dynamic behavior of human movements. This paper presents a method for estimating upper limb impedance characteristics in the three-dimensional (3D) space, covering a wide range of the arm workspace. While subjects maintained postures, a seven-degrees-of-freedom (7-DoFs) robot arm was used to produce small displacements of subjects' hands along the three Cartesian axes. The end-point dynamic behavior was modeled using a linear second-order system and the impedance characteristics in the 3D space were identified using the measured forces and motion profiles. Experimental results were confirmed with two subjects.

Human motor control has always acted as an inspiration in both robotic manipulator design and control. In this paper, a modeling approach of anthropomorphism in human arm movements during every-day life tasks is proposed. The approach is not limited to describing static postures of the human arm but is able to model posture transitions, in other words, dynamic arm movements. The method is based on a novel structure of a Dynamic Bayesian Network (DBN) that is constructed using motion capture data. The structure and parameters of the model are learnt from the motion capture data used for training. Once trained, the proposed model can generate new anthropomorphic arm motions. These motions are then used for controlling an anthropomorphic robot arm, while a measure of anthropomorphism is defined and utilized for assessing resulted motion profiles.

Human-robot control interfaces have received increased attention during the past decades. With the introduction of robots in everyday life, especially in providing services to people with special needs (i.e., elderly, people with impairments, or people with disabilities), there is a strong necessity for simple and natural control interfaces. In this paper, electromyographic (EMG) signals from muscles of the human upper limb are used as the control interface between the user and a robot arm. EMG signals are recorded using surface EMG electrodes placed on the user's skin, making the user's upper limb free of bulky interface sensors or machinery usually found in conventional human-controlled systems. The proposed interface allows the user to control in real time an anthropomorphic robot arm in 3-D space, using upper limb motion estimates based only on EMG recordings. Moreover, the proposed interface is robust to EMG changes with respect to time, mainly caused by muscle fatigue or adjustments of contraction level. The efficiency of the method is assessed through real-time experiments, including random arm motions in the 3-D space with variable hand speed profiles.

As robots come closer to humans, an efficient human-robot-control interface is an utmost necessity. In this paper, electromyographic (EMG) signals from muscles of the human upper limb are used as the control interface between the user and a robot arm. A mathematical model is trained to decode upper limb motion from EMG recordings, using a dimensionality-reduction technique that represents muscle synergies and motion primitives. It is shown that a 2-D embedding of muscle activations can be decoded to a continuous profile of arm motion representation in the 3-D Cartesian space, embedded in a 2-D space. The system is used for the continuous control of a robot arm, using only EMG signals from the upper limb. The accuracy of the method is assessed through real-time experiments, including random arm motions.

Human-robot control interfaces have received increased attention during the last decades. With the introduction of robots in every-day life, especially in developing services for people with special needs (i.e. elderly or impaired persons), there is a strong necessity of simple and natural control interfaces. In this paper, electromyographic (EMG) signals from muscles of the human upper limb are used as the control interface between the user and a robot arm. EMG signals are recorded using surface EMG electrodes placed on the userpsilas skin, letting the userpsilas upper limb free of bulky interface sensors or machinery usually found in conventional human-controlled systems. The proposed interface allows the user to control in real-time an anthropomorphic robot arm in three dimensional (3D) space, by decoding EMG signals to motion. However, since EMG changes due to muscle fatigue are present in this kind of control interface, a probabilistic framework has been developed, which can detect in real-time the muscle fatigue level. By complying to those fatigue-related signal changes, the proposed method can provide accurate decoding of motion through long periods of time. The system is used for the continuous control of a robot arm in 3D space, using only EMG signals from the upper limb. The method is tested for a long period of operation, proving that muscle fatigue does not affect the decoder accuracy. The efficiency of the method is assessed through real-time experiments including random arm motions in 3D space.

There is a great effort during the last decades towards building robotic devices that are worn by humans. These devices, called exoskeletons, are used mainly for support and rehabilitation, as well as for augmentation of human capabilities. Providing a control interface for exoskeletons, that would guarantee comfort and safety, as well as efficiency and robustness, is still an issue. This paper presents a methodology for estimating human arm motion and force exerted, using electromyographic (EMG) signals from muscles of the upper limb. The proposed method is able to estimate motion of the human arm as well as force exerted from the upper limb to the environment, when the motion is constrained. Moreover, the method can distinguish the cases in which the motion is constrained or not (i.e. exertion of force versus free motion) which is of great importance for the control of exoskeletons. Furthermore, the method provides a continuous profile of estimated motion and force, in contrast to other methods used in the literature that can only detect initiation of movement or intention of force. The system is tested in an orthosis-like scenario, during planar movements, through various experiments. The experimental results prove the system efficiency, making the proposed methodology a strong candidate for an EMG-based control scheme applied in robotic exoskeletons.

In robot teleoperation scenarios, the interface between the user and the robot is undoubtedly of high importance. In this paper, electromyographic (EMG) signals from muscles of the human upper limb are used as the control interface between the user and a remote robot arm. The proposed interface consists of surface EMG electrodes, placed at the user's skin at several locations on the arm, letting the user's upper limb free of bulky interface sensors or machinery usually found in conventional teleoperation systems. The motion of the human upper limb entails the activation of a large number of muscles (i.e. more than 30 muscles, not including finger movements). Moreover, the human arm has 7 degrees of freedom (DoFs) suggesting a wide variety of motions. Therefore, the mapping between these two high-dimensional data (i.e. the muscles activation and the motion of the human arm), is an extremely challenging issue. For this reason, a novel methodology is proposed here, where the mapping between the muscles activation and the motion of the user's arm is done in a low-dimensional space. Each of the high-dimensional input (muscle activation) and output (arm motion) vectors, is transformed into an individual low-dimensional space, where the mapping between the two low-dimensional vectors is then feasible. A state-space model is trained to map the low-dimensional representation of the muscles activation to the corresponding motion of the user's arm. After training, the state-space model can decode the human arm motion in real time with high accuracy, using only EMG recordings. The estimated motion is used to control a remote anthropomorphic robot arm. The accuracy of the proposed method is assessed through real-time experiments including motion in two-dimensional (2D) space.

This paper presents a methodology of teleoperating a robot arm, using electromyographic (EMG) signals and a trajectory monitoring technique based on human motion analysis. EMG signals from the flexor and extensor muscles of the elbow joint are used to predict the human elbow joint angle, using an auto-regressive moving average with exogenous output (ARMAX) model. A position tracker is attached in the user upper arm, before the elbow joint. It has been identified from previous works on human physiology that the trajectory of the human hand during planar catching tasks lays on a straight line. This motion law is used in order to monitor and refine the trajectory of the human hand that is predicted through EMG and the ARMAX model. The experimental results show that the ARMAX model estimation for the elbow angle, in conjunction with the trajectory monitoring technique, is able to predict the user motion with high accuracy, within different target points unknown to the system, and various hand velocities

A methodology for a robotic manipulator teleoperation is presented. The proposed method can realize a new master-slave manipulator system that uses no mechanical master controller but electromyographic (EMG) signals from the muscles of a human arm. EMG signals are acquired from biceps brachii, main responsible muscle for elbow flexion. The robot elbow is controlled using joint angle computed from EMG signal during smooth forearm motion, while the shoulder of the robot is controlled by a position tracker placed on the user's arm. Identification techniques are used to approximate the user-dependent parameters of the model used to compute the elbow angle based on EMG signals.