Dataset Information

Shared Control of Bimanual Robotic Limbs With a Brain-Machine Interface for Self-Feeding.

ABSTRACT: Advances in intelligent robotic systems and brain-machine interfaces (BMI) have helped restore functionality and independence to individuals living with sensorimotor deficits; however, tasks requiring bimanual coordination and fine manipulation continue to remain unsolved given the technical complexity of controlling multiple degrees of freedom (DOF) across multiple limbs in a coordinated way through a user input. To address this challenge, we implemented a collaborative shared control strategy to manipulate and coordinate two Modular Prosthetic Limbs (MPL) for performing a bimanual self-feeding task. A human participant with microelectrode arrays in sensorimotor brain regions provided commands to both MPLs to perform the self-feeding task, which included bimanual cutting. Motor commands were decoded from bilateral neural signals to control up to two DOFs on each MPL at a time. The shared control strategy enabled the participant to map his four-DOF control inputs, two per hand, to as many as 12 DOFs for specifying robot end effector position and orientation. Using neurally-driven shared control, the participant successfully and simultaneously controlled movements of both robotic limbs to cut and eat food in a complex bimanual self-feeding task. This demonstration of bimanual robotic system control via a BMI in collaboration with intelligent robot behavior has major implications for restoring complex movement behaviors for those living with sensorimotor deficits.

SUBMITTER: Handelman DA

PROVIDER: S-EPMC9274256 | biostudies-literature | 2022

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Shared Control of Bimanual Robotic Limbs With a Brain-Machine Interface for Self-Feeding.

Handelman David A DA Osborn Luke E LE Thomas Tessy M TM Badger Andrew R AR Thompson Margaret M Nickl Robert W RW Anaya Manuel A MA Wormley Jared M JM Cantarero Gabriela L GL McMullen David D Crone Nathan E NE Wester Brock B Celnik Pablo A PA Fifer Matthew S MS Tenore Francesco V FV

Frontiers in neurorobotics 20220628

Advances in intelligent robotic systems and brain-machine interfaces (BMI) have helped restore functionality and independence to individuals living with sensorimotor deficits; however, tasks requiring bimanual coordination and fine manipulation continue to remain unsolved given the technical complexity of controlling multiple degrees of freedom (DOF) across multiple limbs in a coordinated way through a user input. To address this challenge, we implemented a collaborative shared control strategy ...[more]

PMID: 35837250

Similar Datasets

Project description:BackgroundThis research focused on the development of a motor imagery (MI) based brain-machine interface (BMI) using deep learning algorithms to control a lower-limb robotic exoskeleton. The study aimed to overcome the limitations of traditional BMI approaches by leveraging the advantages of deep learning, such as automated feature extraction and transfer learning. The experimental protocol to evaluate the BMI was designed as asynchronous, allowing subjects to perform mental tasks at their own will.MethodsA total of five healthy able-bodied subjects were enrolled in this study to participate in a series of experimental sessions. The brain signals from two of these sessions were used to develop a generic deep learning model through transfer learning. Subsequently, this model was fine-tuned during the remaining sessions and subjected to evaluation. Three distinct deep learning approaches were compared: one that did not undergo fine-tuning, another that fine-tuned all layers of the model, and a third one that fine-tuned only the last three layers. The evaluation phase involved the exclusive closed-loop control of the exoskeleton device by the participants' neural activity using the second deep learning approach for the decoding.ResultsThe three deep learning approaches were assessed in comparison to an approach based on spatial features that was trained for each subject and experimental session, demonstrating their superior performance. Interestingly, the deep learning approach without fine-tuning achieved comparable performance to the features-based approach, indicating that a generic model trained on data from different individuals and previous sessions can yield similar efficacy. Among the three deep learning approaches compared, fine-tuning all layer weights demonstrated the highest performance.ConclusionThis research represents an initial stride toward future calibration-free methods. Despite the efforts to diminish calibration time by leveraging data from other subjects, complete elimination proved unattainable. The study's discoveries hold notable significance for advancing calibration-free approaches, offering the promise of minimizing the need for training trials. Furthermore, the experimental evaluation protocol employed in this study aimed to replicate real-life scenarios, granting participants a higher degree of autonomy in decision-making regarding actions such as walking or stopping gait.

Project description:OBJECTIVE:Intracortical brain-machine interfaces (BMIs) are a promising source of prosthesis control signals for individuals with severe motor disabilities. Previous BMI studies have primarily focused on predicting and controlling whole-arm movements; precise control of hand kinematics, however, has not been fully demonstrated. Here, we investigate the continuous decoding of precise finger movements in rhesus macaques. APPROACH:In order to elicit precise and repeatable finger movements, we have developed a novel behavioral task paradigm which requires the subject to acquire virtual fingertip position targets. In the physical control condition, four rhesus macaques performed this task by moving all four fingers together in order to acquire a single target. This movement was equivalent to controlling the aperture of a power grasp. During this task performance, we recorded neural spikes from intracortical electrode arrays in primary motor cortex. MAIN RESULTS:Using a standard Kalman filter, we could reconstruct continuous finger movement offline with an average correlation of ???=??0.78 between actual and predicted position across four rhesus macaques. For two of the monkeys, this movement prediction was performed in real-time to enable direct brain control of the virtual hand. Compared to physical control, neural control performance was slightly degraded; however, the monkeys were still able to successfully perform the task with an average target acquisition rate of 83.1%. The monkeys' ability to arbitrarily specify fingertip position was also quantified using an information throughput metric. During brain control task performance, the monkeys achieved an average 1.01 bits s-1 throughput, similar to that achieved in previous studies which decoded upper-arm movements to control computer cursors using a standard Kalman filter. SIGNIFICANCE:This is, to our knowledge, the first demonstration of brain control of finger-level fine motor skills. We believe that these results represent an important step towards full and dexterous control of neural prosthetic devices.

Project description:Medically-induced coma is a drug-induced state of profound brain inactivation and unconsciousness used to treat refractory intracranial hypertension and to manage treatment-resistant epilepsy. The state of coma is achieved by continually monitoring the patient's brain activity with an electroencephalogram (EEG) and manually titrating the anesthetic infusion rate to maintain a specified level of burst suppression, an EEG marker of profound brain inactivation in which bursts of electrical activity alternate with periods of quiescence or suppression. The medical coma is often required for several days. A more rational approach would be to implement a brain-machine interface (BMI) that monitors the EEG and adjusts the anesthetic infusion rate in real time to maintain the specified target level of burst suppression. We used a stochastic control framework to develop a BMI to control medically-induced coma in a rodent model. The BMI controlled an EEG-guided closed-loop infusion of the anesthetic propofol to maintain precisely specified dynamic target levels of burst suppression. We used as the control signal the burst suppression probability (BSP), the brain's instantaneous probability of being in the suppressed state. We characterized the EEG response to propofol using a two-dimensional linear compartment model and estimated the model parameters specific to each animal prior to initiating control. We derived a recursive Bayesian binary filter algorithm to compute the BSP from the EEG and controllers using a linear-quadratic-regulator and a model-predictive control strategy. Both controllers used the estimated BSP as feedback. The BMI accurately controlled burst suppression in individual rodents across dynamic target trajectories, and enabled prompt transitions between target levels while avoiding both undershoot and overshoot. The median performance error for the BMI was 3.6%, the median bias was -1.4% and the overall posterior probability of reliable control was 1 (95% Bayesian credibility interval of [0.87, 1.0]). A BMI can maintain reliable and accurate real-time control of medically-induced coma in a rodent model suggesting this strategy could be applied in patient care.

Project description:BackgroundExcessive reliance on wheelchairs in individuals with tetraplegia or paraplegia due to spinal cord injury (SCI) leads to many medical co-morbidities, such as cardiovascular disease, metabolic derangements, osteoporosis, and pressure ulcers. Treatment of these conditions contributes to the majority of SCI health care costs. Restoring able-body-like ambulation in this patient population can potentially reduce the incidence of these medical co-morbidities, in addition to increasing independence and quality of life. However, no biomedical solution exists that can reverse this loss of neurological function, and hence novel methods are needed. Brain-computer interface (BCI) controlled lower extremity prostheses may constitute one such novel approach.MethodsOne able-bodied subject and one subject with paraplegia due to SCI underwent electroencephalogram (EEG) recordings while engaged in alternating epochs of idling and walking kinesthetic motor imagery (KMI). These data were analyzed to generate an EEG prediction model for online BCI operation. A commercial robotic gait orthosis (RoGO) system (suspended over a treadmill) was interfaced with the BCI computer to allow for computerized control. The subjects were then tasked to perform five, 5-min-long online sessions where they ambulated using the BCI-RoGO system as prompted by computerized cues. The performance of this system was assessed with cross-correlation analysis, and omission and false alarm rates.ResultsThe offline accuracy of the EEG prediction model averaged 86.30% across both subjects (chance: 50%). The cross-correlation between instructional cues and the BCI-RoGO walking epochs averaged across all subjects and all sessions was 0.812 ± 0.048 (p-value <10(-4)). Also, there were on average 0.8 false alarms per session and no omissions.ConclusionThese results provide preliminary evidence that restoring brain-controlled ambulation after SCI is feasible. Future work will test the function of this system in a population of subjects with SCI. If successful, this may justify the future development of BCI-controlled lower extremity prostheses for free overground walking for those with complete motor SCI. Finally, this system can also be applied to incomplete motor SCI, where it could lead to improved neurological outcomes beyond those of standard physiotherapy.

Dataset Information

Shared Control of Bimanual Robotic Limbs With a Brain-Machine Interface for Self-Feeding.

Publications

Shared Control of Bimanual Robotic Limbs With a Brain-Machine Interface for Self-Feeding.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets