Forces That Supplement Visuomotor Learning: A "Sensory Crossover" Experiment

Automated Patient-Robot Task Assignment in a Simulated Stochastic Rehabilitation Gym

Rehabilitation after neurological injury can be provided by robots that help patients perform different exercises. Multiple such robots can be combined in a rehabilitation robot gym to allow multiple patients to perform a diverse range of exercises simultaneously. In pursuit of better multipatient supervision, we aim to develop an automated assignment system that assigns patients to different robots during a training session to maximize their skill development. Our previous work was designed for simplified simulated environments where each patient's skill development is known beforehand. The current work improves upon that work by changing the deterministic environment into a stochastic environment where part of the skill development is random and the assignment system must estimate each patient's predicted skill development using a neural network based on the patient's previous training success rate with that robot. These skill development estimates are used to create patient-robot assignments on a timestep-by-timestep basis to maximize the skill development of the patient group. Results from simplified simulation trials show that the schedules produced by our assignment system outperform multiple baseline schedules (e.g., schedules where patients never switch robots and schedules where patients only switch robots once halfway through the session). Additionally, we discuss how some of our simplifications could be addressed in the future.

Error Fields: Personalized robotic movement training that augments one's more likely mistakes

Control of movement is learned and uses error feedback during practice to predict actions for the next movement. We have shown that augmenting error can enhance learning, but while such findings are encouraging the methods need to be refined to accommodate a person's individual reactions to error. The current study evaluates error fields (EF) method, where the interactive robot tempers its augmentation when the error is less likely. 22 healthy participants were asked to learn moving with a visual transformation, and we enhanced the training with error fields. We found that training with error fields led to greatest reduction in error. EF training reduced error 264% more than controls who practiced without error fields, but subjects learned more slowly than our previous error magnification technique. We also found a relationship between the amount of learning and how much variability was induced by the error augmentation treatments, most likely leading to better exploration and discovery of the causes of error. These robotic training enhancements should be further explored in combination to optimally leverage error statistics to teach people how to move better.

Automated patient-robot assignment for a robotic rehabilitation gym: a simplified simulation model

Background

A robotic rehabilitation gym can be defined as multiple patients training with multiple robots or passive sensorized devices in a group setting. Recent work with such gyms has shown positive rehabilitation outcomes; furthermore, such gyms allow a single therapist to supervise more than one patient, increasing cost-effectiveness. To allow more effective multipatient supervision in future robotic rehabilitation gyms, we propose an automated system that could dynamically assign patients to different robots within a session in order to optimize rehabilitation outcome.

Methods

As a first step toward implementing a practical patient-robot assignment system, we present a simplified mathematical model of a robotic rehabilitation gym. Mixed-integer nonlinear programming algorithms are used to find effective assignment and training solutions for multiple evaluation scenarios involving different numbers of patients and robots (5 patients and 5 robots, 6 patients and 5 robots, 5 patients and 7 robots), different training durations (7 or 12 time steps) and different complexity levels (whether different patients have different skill acquisition curves, whether robots have exit times associated with them). In all cases, the goal is to maximize total skill gain across all patients and skills within a session.

Results

Analyses of variance across different scenarios show that disjunctive and time-indexed optimization models significantly outperform two baseline schedules: staying on one robot throughout a session and switching robots halfway through a session. The disjunctive model results in higher skill gain than the time-indexed model in the given scenarios, and the optimization duration increases as the number of patients, robots and time steps increases. Additionally, we discuss how different model simplifications (e.g., perfectly known and predictable patient skill level) could be addressed in the future and how such software may eventually be used in practice.

Conclusions

Though it involves unrealistically simple scenarios, our study shows that intelligently moving patients between different rehabilitation robots can improve overall skill acquisition in a multi-patient multi-robot environment. While robotic rehabilitation gyms are not yet commonplace in clinical practice, prototypes of them already exist, and our study presents a way to use intelligent decision support to potentially enable more efficient delivery of technologically aided rehabilitation.

Direction-Specific Iterative Tuning of Motor Commands With Local Generalization During Randomized Reaching Practice Across Movement Directions

During motor learning, people often practice reaching in variety of movement directions in a randomized sequence. Such training has been shown to enhance retention and transfer capability of the acquired skill compared to the blocked repetition of the same movement direction. The learning system must accommodate such randomized order either by having a memory for each movement direction, or by being able to generalize what was learned in one movement direction to the controls of nearby directions. While our preliminary study used a comprehensive dataset from visuomotor learning experiments and evaluated the first-order model candidates that considered the memory of error and generalization across movement directions, here we expanded our list of candidate models that considered the higher-order effects and error-dependent learning rates. We also employed cross-validation to select the leading models. We found that the first-order model with a constant learning rate was the best at predicting learning curves. This model revealed an interaction between the learning and forgetting processes using the direction-specific memory of error. As expected, learning effects were observed at the practiced movement direction on a given trial. Forgetting effects (error increasing) were observed at the unpracticed movement directions with learning effects from generalization from the practiced movement direction. Our study provides insights that guide optimal training using the machine-learning algorithms in areas such as sports coaching, neurorehabilitation, and human-machine interactions.

Error Augmentation in Immersive Virtual Reality for Bimanual Upper-Limb Rehabilitation in Individuals With and Without Hemiplegic Cerebral Palsy

With more readily available commercial immersive virtual reality (VR) technologies, the potential of new feedback strategies as tools to facilitate motor rehabilitation should be investigated. Augmented feedback or error augmentation (EA) can easily be shown in a virtual environment. Here, visual EA provided via immersive VR was tested for its effectiveness to improve bimanual symmetry in a reaching task. A single-session crossover design was used to test two training cases, with or without EA. With EA, the distance between hands in the forward direction was augmented. Participants were recruited from typically developing (TD) populations (n = 12, ages 13-21) and performed in an adapted environment with an initial asymmetry between limbs. Also, five participants with hemiplegic cerebral palsy (CP) (ages 14-21, MACS I-III) completed the study. Among TD participants, a significantly larger change in symmetry in the adapted environment was shown after EA than training without EA (F (1, 10) = 9.64, p = 0.01). Each participant in the CP group also improved more after EA training (8.8-103.7)%, such that they achieved lower symmetry error after training with EA. As participants in both groups adapted more symmetrically with EA, beneficial changes from this training method could be evaluated in future studies for longer-term functional changes.