We present a new approach to robot hand design specifically suited to enable robot learning methods and daily tasks in human environments. We introduce BaRiFlex, an innovative gripper design that alleviates the issues caused by unexpected contact and collisions during robot learning, offering collision mitigation, grasping versatility, task versatility, and simplicity to the learning processes. This achievement is enabled by the incorporation of low-inertia actuators, providing high Back-drivability, and the strategic combination of Rigid and Flexible materials which enhances versatility and the gripper’s resilience against unpredicted collisions. Furthermore, the integration of flexible Fin-Ray and rigid linkages allows the gripper to execute compliant grasping and precise pinching. We conducted rigorous performance tests to characterize the novel gripper’s compliance, durability, grasping and task versatility, and precision. We also integrated the BaRiFlex with a 7 Degree of Freedom (DoF) Franka Emika’s Panda robotic arm to evaluate its capacity to support a trial-and-error (reinforcement learning) training procedure. The results of our experimental study are then compared to those obtained using the original rigid Franka Hand and a reference Fin-Ray soft gripper, demonstrating the superior capabilities and advantages of our developed gripper system. More information and videos at https://robin-lab.cs.utexas.edu/bariflex

Exoskeleton robots are capable of safe torque-controlled interactions with a wearer while moving their limbs through predefined trajectories. However, affecting and assisting the wearer's movements while incorporating their inputs (effort and movements) effectively during an interaction re-mains an open problem due to the complex and variable nature of human motion. In this paper, we present a control algorithm that leverages task-specific movement behaviors to control robot torques during unstructured interactions by implementing a force field that imposes a desired joint angle coordination behavior. This control law, built by using principal component analysis (PCA), is implemented and tested with the Harmony exoskeleton. We show that the proposed control law is versatile enough to allow for the imposition of different coordination behaviors with varying levels of impedance stiffness. We also test the feasibility of our method for unstructured human-robot interaction. Specifically, we demonstrate that participants in a human-subject experiment are able to effectively perform reaching tasks while the exoskeleton imposes the desired joint coordination under different movement speeds and interaction modes. Survey results further suggest that the proposed control law may offer a reduction in cognitive or motor effort. This control law opens up the possibility of using the exoskeleton for training the participating in accomplishing complex multi-joint motor tasks while maintaining postural coordination.

Two distinct technologies have gained attention lately due to their prospects for motor rehabilitation: robotics and brain-machine interfaces (BMIs). Harnessing their combined efforts is a largely uncharted and promising direction that has immense clinical potential. However, a significant challenge is whether motor intentions from the user can be accurately detected using non-invasive BMIs in the presence of instrumental noise and passive movements induced by the rehabilitation exoskeleton. As an alternative to the straight-forward continuous control approach, this study instead aims to characterize the onset and offset of motor imagery during passive arm movements induced by an upper-body exoskeleton to allow for the natural control (initiation and termination) of functional movements. Ten participants were recruited to perform kinesthetic motor imagery (MI) of the right arm while attached to the robot, simultaneously cued with LEDs indicating the initiation and termination of a goal-oriented reaching task. Using electroencephalogram signals, we built a decoder to detect the transition between i) rest and beginning MI and ii) maintaining and ending MI. Offline decoder evaluation achieved group average onset accuracy of 60.7% and 66.6% for offset accuracy, revealing that the start and stop of MI could be identified while attached to the robot. Furthermore, pseudo-online evaluation could replicate this performance, forecasting reliable online exoskeleton control in the future. Our approach showed that participants could produce quality and reliable sensorimotor rhythms regardless of noise or passive arm movements induced by wearing the exoskeleton, which opens new possibilities for BMI control of assistive devices.

To determine the most effective interventions for poststroke patients, it is imperative to monitor the recovery process. Robotic exoskeletons' built-in sensing capabilities enable accurate kinematic measurement with no additional setup time. Although position sensors used in exoskeletons are accurate, a mismatch between the robot's and the human's joints can lead to inaccurate measurements. In addition, the robot's residual dynamics can interfere with human's natural movements and the kinematic metrics assessed in the robot would not be representative of the human's movement in free-motion. So far, the accuracy of robotic exoskeletons in assessing upper-body kinematics has not been verified. The bilateral upper-body Harmony exoskeleton has features favorable to minimize joint misalignments and the robot's residual dynamics. In this study, we examined Harmony's ability to accurately assess Cartesian-space kinematic parameters associated with the wearer's movement quality. We analyzed data collected from eight healthy participants that executed point-to-point movements with and without the presence of the robot and at fast and slow speeds. Ground truth was acquired with an optical motion capture, and we extracted the kinematic parameters from the measured data. The results suggest that Harmony can accurately measure kinematic parameters associated with movement quality, and these parameters could appropriately reflect wearer's natural movements at a slow speed. Therefore, Harmony could aid the evaluation of the effectiveness of different interventions, which is more sensitive and efficient than currently adopted clinical outcomes. This allows for individualization of a treatment plan and a detailed follow-up.

While human-robot interaction studies are becoming more common, quantification of the effects of repeated interaction with an exoskeleton remains unexplored. We draw upon existing literature in human skill assessment and present extrinsic and intrinsic performance metrics that quantify how the human-exoskeleton system's behavior changes over time. Specifically, in this paper, we present a new performance metric that provides insight into the system's kinematics associated with ‘successful’ movements resulting in a richer characterization of changes in the system's behavior. A human subject study is carried out wherein participants learn to play a challenging and dynamic reaching game over multiple attempts, while donning an upper-body exoskeleton. The results demonstrate that repeated practice results in learning over time as identified through the improvement of extrinsic performance. Changes in the newly developed kinematics-based measure further illumi-nate how the participant's intrinsic behavior is altered over the training period. Thus, we are able to quantify the changes in the human-exoskeleton system's behavior observed in relation with learning.

How best to attach exoskeletons to human limbs is an open and understudied problem. In the case of upperbody exoskeletons, cylindrical handles are commonly used attachments due to ease of use and cost effectiveness. However, handles require active grip strength from the user and may result in undesirable flexion synergy stimulation, thus limiting the robot’s effectiveness. This paper presents a new design, the Eminence Grip, for attaching an exoskeleton to the hand while avoiding the undesirable consequences of using a handle. The ergonomic design uses inverse impedance matching and does not require active effort from the user to remain interfaced with the exoskeleton. We compare the performance of the Eminence Grip to the handle design in a healthy subject target reaching experiment. The results show that the Eminence Grip achieves similar performance to a handle in terms of relative motion between the user and the exoskeleton while eliminating the requirement of grip force to transfer loads to/from the exoskeleton and avoiding stimulation of the flexion synergy. Taken together, the kinematic equivalence and improvement in ergonomics suggest that the Eminence Grip is a promising exoskeleton-hand attachment interface supporting further experiments with impaired populations.

Robotic exoskeletons are promising devices capable of both administering therapeutic exercises and assessing human movement quality. Although assessing fatigue is crucial to informing effective strategies for rehabilitation, existing metrics for evaluating fatigue during robot-mediated exercise remain underdeveloped. Current techniques focus on monitoring localized muscle fatigue, but do not consider the complex relationship between changes in muscle activity and associated alterations in joint motion during dynamic movement. In this work, we propose a system-based monitoring paradigm for tracking fatigue-induced changes in performance. The method uses a time-series model to approximate the dynamics of a human-exoskeleton system by mapping muscle activity to movement variables. An index of performance is calculated from modeling errors to continuously track changes in this dynamic relationship over time. Results showed that the index effectively captured fatigue-induced degradation in performance over time during an exoskeleton-administered resistive exercise. The index outperformed a traditional indicator of fatigue that is typically used during robotic intervention, suggesting the proposed approach has the potential to improve fatigue monitoring efforts during robot-aided movement training.

Humans learn complex motor skills with practice and training. Though the learning process is not fully understood, several theories from motor learning, neuroscience, education, and game design suggest that curriculum-based training may be the key to efficient skill acquisition. However, designing such a curriculum and understanding its effects on learning are challenging problems. In this paper, we define the Human-skill Curriculum Markov Decision Process (H-CMDP) to systematize the design of training protocols. We also identify a vocabulary of performance features to enable the approximation for a human’s skill level across a variety of cognitive and motor tasks. A novel task domain is introduced as a testbed to evaluate the effectiveness of our approach. Human subject experiments show that (1) participants can learn to improve their performance in tasks within this domain, (2) the learning is quantifiable via our performance features, and (3) the domain is flexible enough to create distinct levels of difficulty. The long-term goal of this work is to systematize the process of curriculum-based training toward the design of protocols for robot-mediated rehabilitation.

In this study, we address the inverse kinematics problem for an upper-limb exoskeleton by presenting a novel method that guarantees the satisfaction of joint-space constraints, and solves closed-chain mechanisms in a serial robot configuration. Starting from the conventional differential kinematics method based on the inversion of the Jacobian matrix, we describe and test two improved algorithms based on the Projected-Gradient method, that take into account joint-space equality constraints. We use the Harmony exoskeleton as a platform to demonstrate the method. Specifically, we address the joint constraints that the robot maintains in order to match anatomical shoulder movement and the closed-chain mechanisms used for the robot's joint control. Results show good performances of the proposed algorithms, which are confirmed by the ability of the robot to follow the desired task-space trajectory while ensuring the fulfilment of joint-space constraints, with a maximum error of about 0.05 degrees.

Robotic exoskeletons open up promising interventions during post-stroke rehabilitation by assisting individuals with sensorimotor impairments to complete therapy tasks. These devices have the ability to provide variable assistance tailored to individual-specific needs and, additionally, can measure several parameters associated with the movement execution. Metrics representative of movement quality are important to guide individualized treatment. While robots can provide data with high resolution, robustness, and consistency, the delineation of the human contribution in the presence of the kinematic guidance introduced by the robotic assistance is a significant challenge. In this paper, we propose a method for assessing voluntary effort from an individual fitted in an upper-body exoskeleton called Harmony. The method separates the active torques generated by the wearer from the effects caused by unmodeled dynamics and passive neuromuscular properties and involuntary forces. Preliminary results show that the effort estimated using the proposed method is consistent with the effort associated with muscle activity and is also sensitive to different levels, indicating that it can reliably evaluate user's contribution to movement. This method has the potential to serve as a high resolution assessment tool to monitor progress of movement quality throughout the treatment and evaluate motor recovery.

Much effort has been placed into the development of robotic devices to support, rehabilitate, and interact with humans. Despite these advances, reliably modeling the neuromuscular changes in human motion resulting from a robotic intervention remains difficult. This paper proposes a method to uncover the relationship between robotic intervention and human response by combining surface electromyography (sEMG), the musculoskeletal modeling platform OpenSim, and artificial neural networks (ANNs). To demonstrate the method, a one degree of freedom (DOF) elbow flexion-extension motion is performed and analyzed. Preliminary results show that while the robot provides assistance to the subject, it also appears to produce other unexpected responses in the movement. Further investigation using the new method reveals the neuromuscular effect of an unintended resistance to the subject's motion applied by the robot as it enforces a speed slower than the subject selects. The characterization of the differences in expected and actual interaction is enabled by the method presented in this paper. Thus, the method uncovers previously obscured aspects of human robot interaction, and creates possibilities for new training modalities.

Dexterous manipulation with robotic hands can be achieved using object-level impedance control strategies, which allow intuitive regulation of object position, external environmental interactions, and grasp forces. However, for grasp stability, object stiffness gains are limited by the inherent compliance of the robotic system, object size/shape, and applied grasp forces, which can lead to restricted manipulation capabilities. In this work, we first use analytical modeling techniques to explore the theoretical passivity bounds on object stiffness control gains to ensure grasp stability. Then, an object-space stiffness control algorithm is developed for the Anatomically Correct Testbed (ACT) hand, a robotic hand designed to replicate the complex tendon and joint structure of the human hand, and grasp stability bounds are experimentally tested for various task scenarios. Finally, inspired by the hierarchical structure of the human neuromuscular system, we develop a novel control strategy that implements low-level stiffness in muscle-space, while also emulating a separately defined object-space stiffness in quasi-static conditions. Experimental results demonstrate that this control strategy increases achievable object stiffness without sacrificing grasp stability, leading to significantly increased manipulation capabilities.

Robust and dexterous manipulation is identified as one of the critical challenges in the field of robotic hand design and control. A key requirement of dexterous manipulation is the ability to modulate fingertip force directions and magnitudes. Cartesian stiffness control is a strategy to generate position dependent fingertip forces. However the stability conditions for the Cartesian stiffness controllers vary nonlinearly because of dependency on the manipulator's configuration and loading forces. The challenge is enhanced in case of tendon-driven robotic hands due to passive joint coupling. In this work, we derive a generalized passivity based stability boundary for Cartesian stiffness. We then present a methodology to analyze the stability boundaries of Cartesian stiffness controlled series elastic tendon-driven robotic fingers. We also present a solution to improve stability by optimizing the arrangement of optimized passive compliance in parallel to the actuators based on the stability criteria. Our analysis not only allows for informed design of new robotic hands but also applies to improving performance of existing robotic hands.

A critical question to be answered to improve robotic rehabilitation is what is the optimal rehabilitation environment for a subject that will facilitate maximum recovery during therapy? Studies suggest that task variability, nature and degree of assistance or error-augmentation and type of feedback play a critical role in motor (re)-learning. In this work, we present a framework for robot-assisted motor (re)-learning that provides subject-specific training by allowing for simultaneous adaptation of task, assistance and feedback based on the performance of the subject on the task. We model a continuous and coordinated multi-joint task using a learning-from-demonstration approach, which allows the task to be modeled in a generative manner such that the challenge-level of the task could be modulated in an online manner. To train the subjects for dexterous manipulation, we present a torque-based task that requires the subject to dynamically regulate their joint torques. Finally, we carry out a pilot study with healthy human subjects using our previously developed hand exoskeleton to test a hypothesis and the results suggest that training under simultaneous adaptation of task, assistance and feedback positively affects motor learning.

The primary contribution of this work is the development of a generalized modeling methodology for complex tendon systems toward a long-term goal of modeling the mechanical structure of the human finger. The key feature of this model is its ability to predict how muscle forces will transmit through an interconnected tendon network based on tendon kinematics and the current joint posture, so that the transformation from input muscle forces to output joint torques and fingertip forces is accurately represented. The feasibility of this model is evaluated by using a tendon-driven robotic finger testbed. Moreover, we utilize the validated model to explore unique features of the extensor mechanism.

The mechanical design of robotic hands has been converging towards low-inertia, tendon-driven strategies. As tendon driven robotic fingers are serial chain systems, routing strategies with compliant tendons lead to multi-articular coupling between the degrees of freedom. We propose a generalized analysis of such serial chain linkages with coupled passive joint stiffnesses. We analyze the effect of such coupling on maximum achievable stiffness control boundaries while maintaining passivity at the actuators by analytically deriving the boundaries. We believe that we can use this information to form mechanical design guidelines for intelligently selecting arrangements of compliance elements (mechanical springs) and transmission strategies, i.e. tendon routing and pulley radii, to provide intrinsic stability and customizable controller stiffness limits for high performance manipulation in robotic hands.

In this paper, we present an electromyography (EMG)-driven assistive hand exoskeleton for spinal-cord-injury (SCI) patients. We developed an active assistive orthosis, called Maestro, which is light, comfortable, compliant, and capable of providing various hand poses. The EMG signals are obtained from a subject's forearm, post-processed, and classified for operating Maestro. The performance of Maestro is evaluated by a standardized hand function test, called the Sollerman hand function test. The experimental results show that Maestro improved the hand function of the SCI patients.

The torque control of finger joints is important for effective hand rehabilitation after neural disorders such as stroke. This paper presents an approach for accurate torque control of finger joints with UT hand exoskeleton. We present (1) how we obtained an accurate kinematics model, (2) how we built the torque actuation model with Bowden cable SEA, and (3) how we controlled the torque of finger joints with the kinematic model and the Bowden cable SEA. We have validated our approach with a testbed finger and results show that the UT hand exoskeleton accurately controls the torque of finger joints.

We present a novel statistical model based control algorithm, called Control in the Reliable Region of a Statistical model (CRROS). First, CRROS builds a statistical model with Gaussian process regression, which provides a prediction function and uncertainty of the prediction. Then, CRROS avoids high-uncertainty regions of the statistical model by regulating the null space of the pseudo inverse solution. The simulation results demonstrate that CRROS drives the states toward high-density and low-noise regions of training data, ensuring high reliability of the model. The experiments with a robotic finger, called Flex-finger, show the potential of CRROS to control robotic systems that are difficult to model, contain constrained inputs, and exhibit heteroscedastic noise output.

While human-like series passive compliance has been used in previous robotic hand designs, little attention has been paid to parallel passive compliance due to the lack of understanding of its importance in grasping and manipulation. In this paper, we present a novel design of compliant finger inspired by biomechanical features and functionality of human hands. We develop a human-like compact joint by optimizing the geometry of a compliant material and mechanical elements. The joint exhibits a passive double exponential torque matching human-like compliance. We implement the compliant joint into a robotic finger design with human-like tendon routings. We carry out a series of experiments on the finger design with an open-loop control strategy in grasping and manipulation. The results show that the fingers perform reliable grasping and manipulation without feedback. We validate the trajectory tracking with a motion capture system. The human-like compliant fingers follow the desired trajectories with small errors (less than 1 cm). The innovative finger design realizes the human-like hand passive properties and achieves human-like grasping capability.

This paper presents a systematic method for experimental characterization of Bowden cable friction. A novel tension measurement method using a motion capture system and a spring is introduced. With the tension measurement method, the effects of nine variables on friction are investigated. Experimental results show that i) a combination of 7×19 FEP-coated stainless steel cable and double-sheaths has the highest force transmission efficiency; ii) smaller coefficient of friction material, smaller cable moving speed, shorter cable length, longer clamp distance, stiffer cable/sheath all help to increase the force transmission efficiency; and iii) the static friction pretension ratio only decreases as the coefficient of friction of cable/sheath decreases or as cable/sheath stiffness increases. We have generated guidelines for the Bowden cable performance which may help robotics researchers in choosing materials for the Bowden cables and designing control systems for actuation.

Dextrous object manipulation is a crucial task for the hands of the space humanoid Robonaut 2 (R2), and requires accurate control of fingertip positions and forces. We present a novel Cartesian control for the fingers and thumb of the R2 hand. The controller is designed such that the singularities in the fingers are avoided, and distal joint stiffness is added in the thumb for full controllability. We then present a higher-level object stiffness control law for explicit control of object position, orientation, and grasp forces. The complete algorithm is tested experimentally on the R2 hand, with results demonstrating tracking performance and robustness against disturbances.

We present a novel statistical model-based control algorithm, called Control in the Reliable Region of a Statistical Model (CRROS). A statistical model is unreliable when its state passes into a region where training data is sparse. CRROS drives the state away from such an unreliable region while pursuing the desired output by taking advantage of the redundancy in the input-output relationships. We validated the performance of CRROS by a simulation with a redundant manipulator and experiments with a robot. In the experiments, a manipulator called the Flex-finger, for which it is challenging to build an analytical model, is controlled to demonstrate the practical effectiveness of the proposed method.

Finger exoskeletons, haptic devices, and augmented reality applications demand an accurate, robust, and fast estimation of finger pose. We present a novel finger pose estimation method using a motion capture system. The method combines system identification and state estimation in a unified framework. The system identification stage investigates the accurate model of a finger, and the state estimation stage tracks the finger pose with the Extended Kalman Filter (EKF) algorithm based on the model obtained in the system identification stage. The algorithm is validated by simulation and experiment. The experimental results show that the method can robustly estimate the finger pose at a high frequency (greater than 1 Khz) in presence of measurement noise, occlusion of markers, and fast movement.

Human hands are capable of many dexterous grasping and manipulation tasks. To understand human levels of dexterity and to achieve it with robotic hands, we constructed an anatomically correct testbed (ACT) hand which allows for the investigation of the biomechanical features and neural control strategies of the human hand. This paper focuses on developing control strategies for the index finger motion of the ACT Hand. A direct muscle position control and a force-optimized joint control are implemented as building blocks and tools for comparisons with future biological control approaches. We show how Gaussian process regression techniques can be used to determine the relationships between the muscle and joint motions in both controllers. Our experiments demonstrate that the direct muscle position controller allows for accurate and fast position tracking, while the force-optimized joint controller allows for exploitation of actuation redundancy in the finger critical for this redundant system. Furthermore, a comparison between Gaussian processes and least squares regression method shows that Gaussian processes provide better parameter estimation and tracking performance. This first control investigation on the ACT hand opens doors to implement biological strategies observed in humans and achieve the ultimate human-level dexterity.