Ashish D. Deshpande

Dexterous teleoperation requires precise arm-hand coordination, low-latency feedback, and robust interaction in real-world contact-rich environments. This paper presents a modular bilateral teleoperation framework that integrates operator-side input interfaces with a robot-side dexterous hand and compliant robotic arm in a unified control architecture. The system supports position-based hand retargeting, differential arm control, multi-scale haptic feedback, and shared control for stable manipulation. We validate the framework through a real-world dexterous manipulation task, highlighting coordinated arm-hand control and contact-aware interaction. Beyond feasibility, we identify key design insights related to cross-embodiment mismatch, haptic feedback granularity, and shared control. The proposed platform provides a practical teleoperation system and a foundation for collecting high-quality demonstrations for future learning-from-demonstration research.

Dexterous teleoperation requires precise arm-hand coordination, low-latency feedback, and robust interaction in real-world contact-rich environments. This paper presents a modular bilateral teleoperation framework that integrates operator-side input interfaces with a robot-side dexterous hand and compliant robotic arm in a unified control architecture. The system supports position-based hand retargeting, differential arm control, multi-scale haptic feedback, and shared control for stable manipulation. We validate the framework through a real-world dexterous manipulation task, highlighting coordinated arm-hand control and contact-aware interaction. Beyond feasibility, we identify key design insights related to cross-embodiment mismatch, haptic feedback granularity, and shared control. The proposed platform provides a practical teleoperation system and a foundation for collecting high-quality demonstrations for future learning-from-demonstration research.

We introduce SoftAct, a framework for teaching soft robot hands to perform human-like manipulation skills by explicitly reasoning about contact forces. Leveraging immersive virtual reality, our system captures rich human demonstrations, including hand kinematics, object motion, dense contact patches, and detailed contact force information. Unlike conventional approaches that retarget human joint trajectories, SoftAct employs a two-stage, force-aware retargeting algorithm. The first stage attributes demonstrated contact forces to individual human fingers and allocates robot fingers proportionally, establishing a force-balanced mapping between human and robot hands. The second stage performs online retargeting by combining baseline end-effector pose tracking with geodesic-weighted contact refinements, using contact geometry and force magnitude to adjust robot fingertip targets in real time. This formulation enables soft robotic hands to reproduce the functional intent of human demonstrations while naturally accommodating extreme embodiment mismatch and nonlinear compliance. We evaluate SoftAct on a suite of contact-rich manipulation tasks using a custom non-anthropomorphic pneumatic soft robot hand. SoftAct's controller reduces fingertip trajectory tracking RMSE by up to 55 percent and reduces tracking variance by up to 69 percent compared to kinematic and learning-based baselines. At the policy level, SoftAct achieves consistently higher success in zero-shot real-world deployment and in simulation. These results demonstrate that explicitly modeling contact geometry and force distribution is essential for effective skill transfer to soft robotic hands, and cannot be recovered through kinematic imitation alone. Project videos and additional details are available at https://soft-act.github.io/.

We introduce SoftAct, a framework for teaching soft robot hands to perform human-like manipulation skills by explicitly reasoning about contact forces. Leveraging immersive virtual reality, our system captures rich human demonstrations, including hand kinematics, object motion, dense contact patches, and detailed contact force information. Unlike conventional approaches that retarget human joint trajectories, SoftAct employs a two-stage, force-aware retargeting algorithm. The first stage attributes demonstrated contact forces to individual human fingers and allocates robot fingers proportionally, establishing a force-balanced mapping between human and robot hands. The second stage performs online retargeting by combining baseline end-effector pose tracking with geodesic-weighted contact refinements, using contact geometry and force magnitude to adjust robot fingertip targets in real time. This formulation enables soft robotic hands to reproduce the functional intent of human demonstrations while naturally accommodating extreme embodiment mismatch and nonlinear compliance. We evaluate SoftAct on a suite of contact-rich manipulation tasks using a custom non-anthropomorphic pneumatic soft robot hand. SoftAct's controller reduces fingertip trajectory tracking RMSE by up to 55 percent and reduces tracking variance by up to 69 percent compared to kinematic and learning-based baselines. At the policy level, SoftAct achieves consistently higher success in zero-shot real-world deployment and in simulation. These results demonstrate that explicitly modeling contact geometry and force distribution is essential for effective skill transfer to soft robotic hands, and cannot be recovered through kinematic imitation alone. Project videos and additional details are available at https://soft-act.github.io/.

Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling goal-directed reaches to be both initiated and terminated directly from non-invasive EEG. Eight participants used EEG to initiate assistance and then volitionally halt the robot mid-trajectory. Across two online sessions, group-mean hit rates were 61.5% for onset and 64.5% for offset, demonstrating reliable start-stop command delivery despite instrumental noise and passive arm motion. Methodologically, we reveal a systematic, class-driven bias induced by common task-based recentering using an asymmetric margin diagnostic, and we introduce a class-agnostic fixation-based recentering method that tracks drift without sampling command classes while preserving class geometry. This substantially improves threshold-free separability (AUC gains: onset +56%, p = 0.0117; offset +34%, p = 0.0251) and reduces bias within and across days. Together, these results help bridge offline decoding and practical, intention-driven start-stop control of a rehabilitation exoskeleton, enabling precisely timed, contingent assistance aligned with neuroplasticity goals while supporting future clinical translation.

Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling goal-directed reaches to be both initiated and terminated directly from non-invasive EEG. Eight participants used EEG to initiate assistance and then volitionally halt the robot mid-trajectory. Across two online sessions, group-mean hit rates were 61.5% for onset and 64.5% for offset, demonstrating reliable start-stop command delivery despite instrumental noise and passive arm motion. Methodologically, we reveal a systematic, class-driven bias induced by common task-based recentering using an asymmetric margin diagnostic, and we introduce a class-agnostic fixation-based recentering method that tracks drift without sampling command classes while preserving class geometry. This substantially improves threshold-free separability (AUC gains: onset +56%, p = 0.0117; offset +34%, p = 0.0251) and reduces bias within and across days. Together, these results help bridge offline decoding and practical, intention-driven start-stop control of a rehabilitation exoskeleton, enabling precisely timed, contingent assistance aligned with neuroplasticity goals while supporting future clinical translation.

Hand exoskeletons are critical tools for dexterous teleoperation and immersive manipulation interfaces, but achieving accurate hand tracking remains a challenge due to user-specific anatomical variability and donning inconsistencies. These issues lead to kinematic misalignments that degrade tracking performance and limit applicability in precision tasks. We propose a subject-specific calibration framework for exoskeleton-based hand tracking that estimates virtual link parameters through residual-weighted optimization. A data-driven approach is introduced to empirically tune cost function weights using motion capture ground truth, enabling accurate and consistent calibration across users. Implemented on the MAESTRO hand exoskeleton with seven healthy participants, the method achieved substantial reductions in joint and fingertip tracking errors across diverse hand geometries. Qualitative visualizations using a Unity-based virtual hand further demonstrate improved motion fidelity. While demonstrated on the MAESTRO exoskeleton, the framework may be extended in principle to other hand exoskeleton systems that provide comparable kinematic constraints and sensing capabilities.

Background Stroke is a leading cause of long-term adult disability, with approximately 80% of survivors experiencing upper extremity (UE) motor impairments. Conventional tools like the Fugl-Meyer Assessment (FMA) are widely used but limited by ordinal scales and subjective visual observation. While wearable robotics offer high-resolution data, their clinical translation is hindered by a lack of standardized protocols and limited interpretability for clinical decision-making. Objective This study aimed to develop an objective, standardized, and clinically interpretable method to quantify UE motor qualities by integrating wearable robotic technology with traditional clinical assessment tasks. Methods Ten healthy individuals and ten stroke survivors performed seven standardized tasks (six from the FMA-UE and one additional elbow task) while wearing the HARMONY exoskeleton. We developed a “trajectory pattern similarity score” based on the root mean square error between individual joint trajectories and normative averages. Additionally, kinematic synergy analysis was performed using non-negative matrix factorization to evaluate alterations in multi-joint coordination. Results The trajectory pattern similarity score showed a strong negative correlation with clinical FMA-UE scores (r = −0.93, p < 0.01) and demonstrated excellent test-retest reliability (ICC = 0.98). The number of identified kinematic synergies decreased significantly as motor impairment severity increased (r = 0.79, p < 0.01). Furthermore, kinematic synergy analysis provided a mechanistic explanation for reduced individual joint control. Post-stroke synergies could be explained through the merging (linear combinations of healthy kinematic patterns), preservation, or loss of healthy kinematic synergies, reflected as pathological joint coupling and loss of specific individual joint control. Conclusions This study presents a novel, standardized assessment framework that integrates wearable robotic technology with conventional clinical tasks. By bridging the gap between objective robotic data and clinical interpretability, this approach would enable robust motor impairment assessment and intuitive phenotyping of motor characteristics to guide personalized rehabilitation strategies.

Robot-assisted therapy has long promised to advance stroke rehabilitation by delivering intensive and personalized training, yet its clinical impact remains limited. Closing the sensorimotor loop with brain-computer interfaces offers a better strategy than passive mobilization, directly linking user intent to robotic assistance and potentially driving neuroplasticity. However, a brain-computer interface requires subject-specific calibration that is time-consuming and often impractical. Moreover, brain decoding remains error-prone due to variability of neural signals, thus resulting in unintended robot actions that could reduce engagement during closed-loop control. Here, we demonstrate that a decoder trained on an expert subject can be transferred to naïve users for online control of a rehabilitation exoskeleton in a rest-versus-reaching paradigm, a functional task with clinical relevance. We then characterize error-related potentials arising from expectation mismatches between brain commands and robot actions during closed-loop control. Finally, we show that these mismatches can be reliably decoded in a subject-independent framework (mean area under the receiver operating characteristic curve: 0.77), a crucial step toward rehabilitation scenarios where collecting subject-specific error-related potential data is challenging. Our findings highlight the potential for integrating real-time error-detection to enhance human-robot interaction by correcting unintended robot behaviors, which could significantly improve rehabilitation outcomes where accurate and contingent feedback is essential.

Robotic manipulation in unstructured, human-centric environments poses a dual challenge: achieving the precision need for delicate free-space operation while ensuring safety during unexpected contact events. Traditional wrists struggle to balance these demands, often relying on complex control schemes or complicated mechanical designs to mitigate potential damage from force overload. In response, we present BiFlex, a flexible robotic wrist that uses a soft buckling honeycomb structure to provide a natural bimodal stiffness response. The higher stiffness mode enables precise household object manipulation, while the lower stiffness mode provides the compliance needed to adapt to external forces. We design BiFlex to maintain a fingertip deflection of less than 1 cm while supporting loads up to 500 g and create a BiFlex wrist for many grippers, including Panda, Robotiq, and BaRiFlex. We validate BiFlex under several real-world experimental evaluations, including surface wiping, precise pick-and-place, and grasping under environmental constraints. We demonstrate that BiFlex simplifies control while maintaining precise object manipulation and enhanced safety in real-world applications. More information and videos are available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://robin-lab.cs.utexas.edu/BiFlex/</uri>

Robotic devices offer assistance to individuals with upper-limb impairments. Among different control strategies, assistance should specifically account for the weight of both the device and the wearer's arm without introducing any distortion to the kinematic behaviour. This study investigates how varying weight support levels in the Harmony exoskeleton impact hand spatio-temporal features and inter-joint coordination during a pick-and-place task. Eight healthy subjects performed the selected functional movement across five distinct levels of arm support. Results indicated that movement smoothness and planning in the Cartesian space were not influenced by the Harmony exoskeleton. A decreased accuracy was noted only at high levels of weight support for movements against gravity, while movements propelled by gravity suffered an overall drop. Consistent inter-joint coordination was observed across different support levels, except for shoulder intra-extra rotation during movements against gravity. This study shed light on the effect of gravity compensation provided by the Harmony exoskeleton on kinematic performance, providing valuable insights for optimizing assistive devices for individuals with upper-limb impairments.

Robotic manipulation in unstructured, humancentric environments poses a dual challenge: achieving the precision need for delicate free-space operation while ensuring safety during unexpected contact events. Traditional wrists struggle to balance these demands, often relying on complex control schemes or complicated mechanical designs to mitigate potential damage from force overload. In response, we present BiFlex, a flexible robotic wrist that uses a soft buckling honeycomb structure to provides a natural bimodal stiffness response. The higher stiffness mode enables precise household object manipulation, while the lower stiffness mode provides the compliance needed to adapt to external forces. We design BiFlex to maintain a fingertip deflection of less than 1 cm while supporting loads up to 500g and create a BiFlex wrist for many grippers, including Panda, Robotiq, and BaRiFlex. We validate BiFlex under several real-world experimental evaluations, including surface wiping, precise pick-and-place, and grasping under environmental constraints. We demonstrate that BiFlex simplifies control while maintaining precise object manipulation and enhanced safety in real-world applications.

Abstract Robotic exoskeletons offer the potential to train novel motor skill acquisition and thus aid physical rehabilitation. Our prior work demonstrated that individuals converge to certain kinematic coordinations as they learn a novel task. An upper-limb exoskeleton controller that constrains individuals to this known coordination was also shown to significantly improve straight-line reaching task performance. This paper studies the impact of variations of this controller on novel skill acquisition. We quantify learning under three variations of the intervention (each group with N = 10 participants) against a control group ( N = 13). Our results show that introducing any constraint during learning can hinder the learning process, as this alters the task dynamics that lead to success. However, when presented with a personalized constraint, participants still learn. When presented with a task-specific constraint, rather than a personalized one, participants cannot overcome the differences in the training and target task, suggesting exoskeleton-based training interventions should be personalized. The changes in kinematic behaviors during learning further suggest that participants do not have a statistically consistent performance. While participants respond more to exoskeleton intervention, others may not respond in short training sessions, necessitating further analysis of how strong a response can be encouraged. Our findings emphasize the need for further study of the effects of exoskeleton intervention for motor training and the potential need for personalization.

Robotic devices offer assistance to individuals with upper-limb impairments. Among different control strategies, assistance should specifically account for the weight of both the device and the wearer's arm without introducing any distortion to the kinematic behaviour. This study investigates how varying weight support levels in the Harmony exoskeleton impact hand spatio-temporal features and inter-joint coordination during a pick-and-place task. Eight healthy subjects performed the selected functional movement across five distinct levels of arm support. Results indicated that movement smoothness and planning in the Cartesian space were not influenced by the Harmony exoskeleton. A decreased accuracy was noted only at high levels of weight support for movements against gravity, while movements propelled by gravity suffered an overall drop. Consistent inter-joint coordination was observed across different support levels, except for shoulder intra-extra rotation during movements against gravity. This study shed light on the effect of gravity compensation provided by the Harmony exoskeleton on kinematic performance, providing valuable insights for optimizing assistive devices for individuals with upper-limb impairments.

Soft robots have been increasingly utilized as sophisticated tools in physical rehabilitation, particularly for assisting patients with neuromotor impairments. However, many soft robotics for rehabilitation applications are characterized by limitations such as slow response times, restricted range of motion, and low output force. There are also limited studies on the precise position and force control of wearable soft actuators. Furthermore, not many studies articulate how bellow-structured actuator designs quantitatively contribute to the robots' capability. This study introduces a paradigm of upper limb soft actuator design. This paradigm comprises two actuators: the Lobster-Inspired Silicone Pneumatic Robot (LISPER) for the elbow and the Scallop-Shaped Pneumatic Robot (SCASPER) for the shoulder. LISPER is characterized by higher bandwidth, increased output force/torque, and high linearity. SCASPER is characterized by high output force/torque and simplified fabrication processes. Comprehensive analytical models that describe the relationship between pressure, bending angles, and output force for both actuators were presented so the geometric configuration of the actuators can be set to modify the range of motion and output forces. The preliminary test on a dummy arm is conducted to test the capability of the actuators.

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

Neurological conditions like stroke severely impact many individuals, requiring effective rehabilitation. Although new technologies such as robotics and virtual reality have been introduced to neurorehabilitation, they have yet to surpass conventional therapy. This is due in part to current assistive controllers that enforce predefined trajectories, which allows slacking. Our approach to maximize the efficacy of these devices is to target impairments specific to the injury, in this case maladaptive movement patterns that arise after stroke. In this paper, we present the Synergy Avoidance with Reward (SAR) robotic exoskeleton controller. It is intended to target abnormal synergies that occur after stroke by penalizing maladaptive synergies and rewarding normative kinematics. The controller defines an unwanted coordination in the joint velocity space and applies resistive or assistive torques based on the user's joint velocity coordination. Experiments with healthy participants examined the effects of the synergy avoidance and reward control actions on synergistic arm movements. Muscular effort was evaluated using sEMG data. Primary Component Analysis (PCA) was conducted on joint velocity data to evaluate kine-matic similarity and movement quality. Results demonstrated that this controller effectively influenced muscular effort and joint kinematics without enforcing a predefined trajectory. This could lead to interventions that reduce compensatory strategies and increase functional ability after stroke.

Abstract A majority of robotic gait trainers to facilitate physical therapy for gait rehabilitation in humans are based on multidegree-of-freedom exoskeleton-based systems with sophisticated electro-mechanical hardware and software, and consequently remain inaccessible to vast sections of the populations around the world. This study seeks to advance the development of a single degree-of-freedom (DOF) gait trainer for gait therapy for individuals with neuromuscular impairments. The goal is to offer a cost-effective, accessible solution to cater to the global need for gait rehabilitation. We build upon the previous gait trainer design based on Jansen mechanism and provide an in-depth analysis and experimental validation of its kinematic performance. The device's performance is also tested and successfully demonstrated through trials involving two healthy individuals to examine its kinematic behavior under human-induced load conditions. The gait trainer demonstrates satisfactory performance under both no load conditions and a 2 kg load, exhibiting an area difference of 1% and 7%, respectively. However, when subjected to a 5 kg loading condition, a significant area difference of 27% is observed, primarily attributed to the cantilever loading at the driving shaft. A method to adjust link lengths based on specific human gait trajectories is proposed and validated. Additionally, a cost-effective tool for ankle trajectory measurement is introduced to establish a ground truth. The study demonstrates the potential of an affordable, single DOF gait trainer in facilitating high-volume therapy for those with walking disorders. This research represents a step toward making gait therapy more accessible worldwide.

We present a new approach to robot hand design specifically suited for successfully implementing robot learning methods to accomplish tasks in daily human environments. We introduce BaRiFlex, an innovative gripper design that alleviates the issues caused by unexpected contact and collisions during robot learning, offering robustness, 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 linkages 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.

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.

Even the best wearable robots face challenges with power losses in the system, especially at the physical attachment interface. While some sources for power loss are inherent to the system, such as human soft tissue or musculoskeletal joint damping, other sources such as soft padding materials and bias strap forces can be modulated to optimize interface power transmission. Few methods currently exist for estimating power loss at physical human-robot interfaces, especially for upper-body exoskeletons. This letter presents a novel method to estimate interface power from experimental data in a wearable hand device, along with a simulation model for predicting interaction behavior by incorporating viscoelastic properties at the attachment interface. The experimental method is implemented with the Maestro hand exoskeleton, and repeatability of the interface power estimation is confirmed with pilot human testing. Simulation results are compared with experimental estimation of interface power, showing agreement of trends and validating the use of a simulation model to predict physical human-robot interaction behavior. These findings highlight the advantages of multi-body simulations as a tool to perform modular, inexpensive, and predictive investigations in physical human-robot interaction, without affecting the real-world mechatronic system or hindering the subject's safety. The proposed tools for experimental estimation of interface power and simulation modeling can optimize the design and control of robots for seamless integration with the human body.

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.

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.

With the evolution of hand-based haptic interfaces, novel forms of controlled force feedback arise allowing multipoint interaction between virtual objects and the hand’s digits. With these advances, there must be an effective force display coupled with an intuitive visualization of the hand at its points of high manipulability. This is the basis for dexterous manipulation immersion in virtual environments. Still, there are challenges due to the complexity of force interaction, bandwidth limitations, and redundant visual configurations. In this paper, we present an extended proxy algorithm for digit-based interactions, which through configuration-based optimization, provides an efficient, robust, and visually plausible way to interact with virtual objects with a virtual hand. Additionally, we revisit a seldom-seen modality of haptic rendering, whole-hand kinesthetic feedback, with the Maestro exoskeleton in the implementation of our algorithm. We unify these methods and develop a CHAI3D module in a comprehensive visuo-haptic framework that was evaluated through demonstrations of joint-level haptic force data during interaction with static and dynamic objects alike. Our computationally-efficient approach sets the foundation for the visual display of in-hand virtual object manipulation with the effective rendering of stable haptic interactions under complex tasks.

Human-exoskeleton interactions have the potential to bring about changes in human behavior for physical rehabilitation or skill augmentation. Despite significant advances in the design and control of these robots, their application to human training remains limited. The key obstacles to the design of such training paradigms are the prediction of human-exoskeleton interaction effects and the selection of interaction control to affect human behavior. In this article, we present a method to elucidate behavioral changes in the human-exoskeleton system and identify expert behaviors correlated with a task goal. Specifically, we observe the joint coordinations of the robot, also referred to as kinematic coordination behaviors, that emerge from human-exoskeleton interaction during learning. We demonstrate the use of kinematic coordination behaviors with two task domains through a set of three human-subject studies. We find that participants (1) learn novel tasks within the exoskeleton environment, (2) demonstrate similarity of coordination during successful movements within participants, (3) learn to leverage these coordination behaviors to maximize success within participants, and (4) tend to converge to similar coordinations for a given task strategy across participants. At a high level, we identify task-specific joint coordinations that are used by different experts for a given task goal. These coordinations can be quantified by observing experts and the similarity to these coordinations can act as a measure of learning over the course of training for novices. The observed expert coordinations may further be used in the design of adaptive robot interactions aimed at teaching a participant the expert behaviors.

In this study, we present the Differential Spiral Joint (DSJ) mechanism for variable stiffness actuation in tendon-driven robots. The DSJ mechanism semi-decouples the modulation of position and mechanical stiffness, allowing independent trajectory tracking in different parameter space. Past studies show that increasing the mechanical stiffness achieves the wider range of renderable stiffness, whereas decreasing the mechanical stiffness improves the quality of actuator decoupling and shock absorbance. Therefore, it is often useful to modulate the mechanical stiffness to balance the required level of stiffness and safety. In addition, the DSJ mechanism offers a compact form factor, which is suitable for applications where the size and weight are important. The performance of the DSJ mechanism in various areas is validated through a set of experiments.