Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Adaptive Learning based Upper-Limb Rehabilitation Training System with Collaborative Robot

Jun Hong Lim, Kaibo He, Zeji Yi, Chen Hou, Chen Zhang, Yanan Sui, Luming Li

TL;DR

This work developed a new system for multi-purpose upper-limb rehabilitation training using a generic robot arm with human motor feedback and preference and demonstrates the potential of utilizing collaborative robots for in-home motor rehabilitation training.

Abstract

Rehabilitation training for patients with motor disabilities usually requires specialized devices in rehabilitation centers. Home-based multi-purpose training would significantly increase treatment accessibility and reduce medical costs. While it is unlikely to equip a set of rehabilitation robots at home, we investigate the feasibility to use the general-purpose collaborative robot for rehabilitation therapies. In this work, we developed a new system for multi-purpose upper-limb rehabilitation training using a generic robot arm with human motor feedback and preference. We integrated surface electromyography, force/torque sensors, RGB-D cameras, and robot controllers with the Robot Operating System to enable sensing, communication, and control of the system. Imitation learning methods were adopted to imitate expert-provided training trajectories which could adapt to subject capabilities to facilitate in-home training. Our rehabilitation system is able to perform gross motor function and fine motor skill training with a gripper-based end-effector. We simulated system control in Gazebo and training effects (muscle activation level) in OpenSim and evaluated its real performance with human subjects. For all the subjects enrolled, our system achieved better training outcomes compared to specialist-assisted rehabilitation under the same conditions. Our work demonstrates the potential of utilizing collaborative robots for in-home motor rehabilitation training.

Adaptive Learning based Upper-Limb Rehabilitation Training System with Collaborative Robot

TL;DR

This work developed a new system for multi-purpose upper-limb rehabilitation training using a generic robot arm with human motor feedback and preference and demonstrates the potential of utilizing collaborative robots for in-home motor rehabilitation training.

Abstract

Rehabilitation training for patients with motor disabilities usually requires specialized devices in rehabilitation centers. Home-based multi-purpose training would significantly increase treatment accessibility and reduce medical costs. While it is unlikely to equip a set of rehabilitation robots at home, we investigate the feasibility to use the general-purpose collaborative robot for rehabilitation therapies. In this work, we developed a new system for multi-purpose upper-limb rehabilitation training using a generic robot arm with human motor feedback and preference. We integrated surface electromyography, force/torque sensors, RGB-D cameras, and robot controllers with the Robot Operating System to enable sensing, communication, and control of the system. Imitation learning methods were adopted to imitate expert-provided training trajectories which could adapt to subject capabilities to facilitate in-home training. Our rehabilitation system is able to perform gross motor function and fine motor skill training with a gripper-based end-effector. We simulated system control in Gazebo and training effects (muscle activation level) in OpenSim and evaluated its real performance with human subjects. For all the subjects enrolled, our system achieved better training outcomes compared to specialist-assisted rehabilitation under the same conditions. Our work demonstrates the potential of utilizing collaborative robots for in-home motor rehabilitation training.
Paper Structure (4 sections, 8 figures)

This paper contains 4 sections, 8 figures.

Table of Contents

  1. INTRODUCTION
  2. Methods
  3. Experiment and Results
  4. Conclusion

Figures (8)

  • Figure 1: Training adapted to subject capabilities
  • Figure 2: Overview of the proposed remote system
  • Figure 3: (a) Simulation of the training system with visual and motor feedback in Gazebo. (b) Simulation of gross level motor training with OpenSim. (c) Simulation of fine-level motor training with OpenSim.
  • Figure 4: Real Trajectory(BLUE) executed for another new Expert Trajectory(RED LINE) from the trained model. The red area is the acceptable area by experts. RMSE is around $1e-2$m.
  • Figure 5: Target muscles chosen to evaluate the training effects (Adopted from muscles illustrated in Noraxon MR3 program)
  • ...and 3 more figures