Control Strategies and Artificial Intelligence in Rehabilitation Robotics

  title={Control Strategies and Artificial Intelligence in Rehabilitation Robotics},
  author={Domen Novak and Robert Riener},
  journal={AI Mag.},
Rehabilitation robots physically support and guide a patient's limb during motor therapy, but require sophisticated control algorithms and artificial intelligence to do so. This article provides an overview of the state of the art in this area. It begins with the dominant paradigm of assistive control, from impedance-based cooperative controller through electromyography and intention estimation. It then covers challenge-based algorithms, which provide more difficult and complex tasks for the… Expand

Figures and Topics from this paper

Using a Collaborative Robot to the Upper Limb Rehabilitation
This paper addresses the use of a collaborative robot applied in the rehabilitation field to help the physiotherapy of upper limb of patients, specifically shoulder with the proposed Reinforcement Learning (RL) algorithm. Expand
The realization of robotic neurorehabilitation in clinical: use of computational intelligence and future prospects analysis
A critical review summarizes multiple computation algorithms which have been proved to be valuable for better robotic use in clinical settings and guide the possible future advances in this industry. Expand
Cable-Driven Robots in Physical Rehabilitation
This chapter deals with cable-driven robots when applied in physical rehabilitation, and suggests that these structures can be used as a complement to conventional therapies and not as a substitute. Expand
Exerciser for rehabilitation of the Arm (ERA): Development and unique features of a 3D end-effector robot
  • M. Milot, M. Hamel, +5 authors F. Michaud
  • Engineering, Medicine
  • 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)
  • 2016
The design and implementation of ERA, an upper-limb 3-DOF force-controlled exerciser robot, which presents a workspace covering the entire range of motion of the upper limb and provides 3D reaching movements in a haptic virtual environment is presented. Expand
Artificial Intelligence-Based Wearable Robotic Exoskeletons for Upper Limb Rehabilitation: A Review
The main trend in the research is the development of wearable robotic exoskeletons and the fusion of data collected from multiple sensors that enrich the training of intelligent algorithms. Expand
Advances in Automation Technologies for Lower Extremity Neurorehabilitation: A Review and Future Challenges
A comprehensive review on recent technological advances in wearable sensors, biofeedback devices, and assistive robots is provided to improve the safety, efficiency, and usability of the technologies. Expand
Automatic Exercise Assistance for the Elderly Using Real-Time Adaptation to Performance and Affect
This work presents the design of a system and methodology for reducing risk of locomotive syndrome among the elderly through the delivery of real-time at-home exercise assistance via intensityExpand
Adaptation, Artificial Intelligence, and Physical Medicine and Rehabilitation
  • D. Barry
  • Medicine
  • PM & R : the journal of injury, function, and rehabilitation
  • 2018
Adaptation, cooperation, and trust are at the center of rehabilitation. Artificial intelligence and robots enhance adaptation with guidance for movement, cues for sensation, control of environment,Expand
Clustering of Directions Improves Goodness of Fit in Kinematic Data Collected in the Transverse Plane During Robot-Assisted Rehabilitation of Stroke Patients
There is overwhelming evidence that it is necessary to adjust for direction in the models of multi-directional movements, and that clustering kinematic data by feature similarly may yield the optimal configuration for this co-variate. Expand
Feature Selection and Validation of a Machine Learning-Based Lower Limb Risk Assessment Tool: A Feasibility Study
The usage of nine squat and four one-leg standing exercise features as input parameters to Machine Learning (ML) classifiers in order to perform lower limb skill assessment does not demand manpower and infrastructure, unlike traditional methods. Expand


Rehabilitation Robotics: Performance-Based Progressive Robot-Assisted Therapy
A proposed method to achieve this goal is a novel performance-based impedance control algorithm, which is triggered via speed, time, or EMG, which has already noted one very strong benefit, a significant reduction in arm tone. Expand
Patient-cooperative strategies for robot-aided treadmill training: first experimental results
This paper deals with the application of "patient-cooperative" techniques to robot-aided gait rehabilitation of neurological disorders by hypothesized that such cooperative robotic approaches can improve the therapeutic outcome compared to classical rehabilitation strategies. Expand
Optimizing Compliant, Model-Based Robotic Assistance to Promote Neurorehabilitation
A novel controller using a standard model-based, adaptive control approach in order to learn the patient's abilities and assist in completing movements while remaining compliant and including the ldquoslackingrdquo modification in the controller increases participation from the motor system. Expand
Adaptive training algorithm for robot-assisted upper-arm rehabilitation, applicable to individualised and therapeutic human-robot interaction
The GENTLE/A system was able to adapt so that the duration required to execute point-to-point movement was according to the leading or lagging performance of the user with respect to the robot. Expand
Assistive Control System Using Continuous Myoelectric Signal in Robot-Aided Arm Training for Patients After Stroke
The results showed that the twenty-session training program improved upper limb functions, with statistically significant improvements in the modified Ashworth scale, Fugl-Meyer scale for shoulder and elbow, motor status scale, elbow extension range, muscle strength, and root mean square error between actual elbow angle and target angle. Expand
Review of control strategies for robotic movement training after neurologic injury
There is increasing interest in using robotic devices to assist in movement training following neurologic injuries such as stroke and spinal cord injury, and this review summarizes techniques for implementing assistive strategies, including impedance-, counterbalance-, and EMG- based controllers, as well as adaptive controllers that modify control parameters based on ongoing participant performance. Expand
Controlling patient participation during robot-assisted gait training
A metric is proposed which enables clinicians to select the best strategy for each patient, according to the patient's physical and cognitive capabilities, and will enable therapists to challenge the patient to more activity by automatically controlling the patient effort to a desired level. Expand
Evaluation of upper extremity robot-assistances in subacute and chronic stroke subjects
The robot-assistances used in the study were found to be a possible way to raise the catching efficiency and efficiency of the pick-and-place movements in subacute and chronic subjects and the observed movement parameters showed that robot- ASSISTances used for the virtual task should be improved to maximize physical activity. Expand
Myoelectrically controlled wrist robot for stroke rehabilitation
Results indicate that robot-aided therapy with voluntary participation of patient’s paretic motor system using myoelectric control might have positive effect on upper limb motor recovery. Expand
Reference Trajectory Generation for Rehabilitation Robots: Complementary Limb Motion Estimation
This study showed that Complementary Limb Motion Estimation ensures stable gait, and indicates that subjects can walk more naturally with CLME, and they are assisted less by the robot when it is not needed. Expand