• Journal of the Korean Society of Physical Medicine
• /
• v.19 no.2
• /
• pp.55-64
• /
• 2024

PURPOSE: This study evaluated the effects of robot-assisted gait training combined with virtual reality training on balance and gait ability in stroke patients. METHODS: Thirty-one stroke patients were allocated randomly into one of two groups: robot-assisted gait training combined virtual reality training group (RGVR group; n = 16) and control group (n = 15). The RGVR group received 30 minutes of robot-assisted gait training combined with virtual reality training. Robot-assisted gait training was conducted in parallel using a virtual reality device. In the Control group, neurodevelopmental therapy was performed according to the function of chronic stroke patients. Both groups underwent training for 30 minutes, three times per week for eight weeks. The balance assessment system (BioRescue, Marseille, France), BBS, and TUG were used to evaluate the balance ability. The OptoGait (Microgate Srl, Bolzano, Italy) and 10 mWT were measured to evaluate the gait ability. The measurements were performed before and after the eight-week intervention period. RESULTS: Both groups showed significant improvement in their balance and gait ability during the intervention. RGVR showed significant differences in balance and gait ability compared to the control group groups (p < .05). These results showed that RGVR was more effective on balance and gait ability in patients with chronic stroke. CONCLUSION: RGVR can improve balance and gait ability, highlighting the benefits of RGVR. This study provides intervention data for recovering the balance and gait ability of chronic stroke patients.

• The Journal of Korean Physical Therapy
• /
• v.28 no.2
• /
• pp.71-76
• /
• 2016

Purpose: This study was conducted to assess the effects of robot-assisted gait training with visual feedback on gait, balance, and balance confidence in patients with chronic stroke. Methods: Thirty subjects with chronic stroke were randomly assigned to two groups: the experimental group (n=15) and the control group (n=15). The experimental group performed robot-assisted gait training for 30 minutes and the control group performed gait training with assisted devices training for 30 minutes after both groups performed conventional physical therapy for 30 minutes. Both groups performed the therapeutic interventions for 5 days per week, for a period of 4 weeks. For assessment of the 10 m walking test (10 MWT), Figure of 8 on the walk test (F8WT), Timed-Up and Go test (TUG), and Berg Balance Scale (BBS) were used to test the gait and balance, and the Korean version of the Activities-specific Balance Confidence Scale was used to test the balance confidence. Results: The experimental group showed significant improvement in the 10 MWT and the K-ABC (p<0.05), and the control group showed significant improvement in the BBS and the TUG (p<0.05). In four measurements, there were significant differences between the two groups (p<0.05), and the control group showed significant improvement in the F8WT at pre and post intervention (p<0.05). Conclusion: This study demonstrated that Robot-assisted gait training with visual feedback is an effective intervention for improving straight gait abilities and balance confidence, while the control group showed some improvement in curve gait and balance. Thus, we suggest both Robot-assisted gait training with visual feedback and gait training with assisted devices training exercise as a therapeutic intervention in chronic stroke rehabilitation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.171.2-171
• /
• 2001

This paper presents a force control of a arm of walking training robot. The current gait training apparatus in hospital are ineffective for the difficulty in keeping constant unloading level and constraining patients to walk freely. The proposed walking training robot is designed to unload body weight effectively during walking. The walking training robot consists of unloading manipulator and mobile platform. The manipulator driven with a electro-mechanical linear mechanism unloads body weight in various level. The mobile platform is wheel type, which allows to patients unconstrained walking. Unloading system with electro-mechanical linear mechanism has been developed, which has advantages such as low noise level, light weight, low manufacturing cost and low power consumption. A system model for the manipulator ...

• Physical Therapy Rehabilitation Science
• /
• v.8 no.2
• /
• pp.93-98
• /
• 2019

Objective: The purpose of this study was to investigate the effect of robot arm reach training on upper extremity functional movement in chronic stroke survivors. Design: One group pretest-posttest design. Methods: Thirteen chronic stroke survivors participated in this study. Robot arm reach training was performed with a Whole Arm Manipulator (WAM) and a 120-inch projective display to provide visual and auditory feedback. During the robotic arm reach training, WAM provided gravity compensation and assist-as-needed (AAN) force according to the robot control mode. When a participant could not move the arm toward the target for more than 2 seconds, WAM provided AAN force to reach the desired targets. All patients participated in the training for 40 minutes per day, 3 times a week, for 4 weeks. Main outcome measures were the Fugl-Meyer Assessment (FMA), Action Research Arm Test (ARAT) and Box and Block Test (BBT) to assess upper extremity functional movement. Results: After 4 weeks, significant improvement was observed in upper extremity functional movement (FMA: 42.15 to 46.23, BBT: 12.23 to 14.00, p<0.05). In the subscore analysis of the FMA upper extremity motor function domains, significant improvement was observed in upper extremity and coordination/speed units (p<0.05). However, there were no significant differences in the ARAT. Conclusions: This study showed the positive effects of robot arm reach training on upper extremity functional movement in chronic stroke survivors. In particular, we confirmed that robot arm reach training could have a positive influence by leading to improvement of motor recovery of the proximal upper extremity.

• Physical Therapy Rehabilitation Science
• /
• v.11 no.2
• /
• pp.235-244
• /
• 2022

Objective: The aim of this study was to investigate of the foot plantar pressure and usability after gait training using the ExoAtlet wearable exoskeleton robot in an incomplete spinal cord injury (SCI) patient. Design: A case study Methods: Six participants with an asymmetry in motor and sensory function completed the gait training using ExoAtlet wearable exoskeleton robot for 15 sessions, five per weeks, 3weeks. They were divided into two groups (low and high strength group) and group differences were evaluated about session at stating of gait, gait distance at final session and foot plantar pressures and useability after training. Results: Low strength group was faster than high strength group on adaptation of robot gait. And high strength group increased faster than low strength group on the gait distance during training. In standing and gait, weaker leg was higher than stronger leg on mean foot plantar pressure in low strength group. And stronger leg was higher than weaker leg on foot plantar pressure in high strength group. The length of the anterior-posterior trajectory of the center of pressure during gait was similar in low strength group, but different in high strength group. useability was positive about ExoAtlet wearable exoskeleton gait after training. Conclusions: ExoAtlet wearable exoskeleton robot gait training was positive about improving gait in all participants regardless of differences in severity of symptoms and gait abnormalities.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.40-49
• /
• 2019

Reinforcement learning has been applied to various problems in robotics. However, it was still hard to train complex robotic manipulation tasks since there is a few models which can be applicable to general tasks. Such general models require a lot of training episodes. In these reasons, deep neural networks which have shown to be good function approximators have not been actively used for robot manipulation task. Recently, some of these challenges are solved by a set of methods, such as Guided Policy Search, which guide or limit search directions while training of a deep neural network based policy model. These frameworks are already applied to a humanoid robot, PR2. However, in robotics, it is not trivial to adjust existing algorithms designed for one robot to another robot. In this paper, we present our implementation of Guided Policy Search to the robotic arms of the Baxter Research Robot. To meet the goals and needs of the project, we build on an existing implementation of Baxter Agent class for the Guided Policy Search algorithm code using the built-in Python interface. This work is expected to play an important role in popularizing robot manipulation reinforcement learning methods on cost-effective robot platforms.

• The Journal of Korea Robotics Society
• /
• v.17 no.3
• /
• pp.264-272
• /
• 2022

Human-robot cooperative tasks are increasingly required in our daily life with the development of robotics and artificial intelligence technology. Interactive reinforcement learning strategies suggest that robots learn task by receiving feedback from an experienced human trainer during a training process. However, most of the previous studies on Interactive reinforcement learning have required an extra feedback input device such as a mouse or keyboard in addition to robot itself, and the scenario where a robot can interactively learn a task with human have been also limited to virtual environment. To solve these limitations, this paper studies training strategies of robot that learn table balancing tasks interactively using deep reinforcement learning with human's facial expression feedback. In the proposed system, the robot learns a cooperative table balancing task using Deep Q-Network (DQN), which is a deep reinforcement learning technique, with human facial emotion expression feedback. As a result of the experiment, the proposed system achieved a high optimal policy convergence rate of up to 83.3% in training and successful assumption rate of up to 91.6% in testing, showing improved performance compared to the model without human facial expression feedback.

• The Journal of Korean Physical Therapy
• /
• v.31 no.2
• /
• pp.94-102
• /
• 2019

Purpose: This study examined the effects of trunk control rehabilitation robot training (TCRRT) on the dynamic balance, lower extremity strength, gait ability and pain for bipolar hemiarthroplasty. Methods: Hemiarthroplasty (n=28) patients participated in this study. The subjects were randomized into two groups: trunk control rehabilitation robot training group and control group. Results: The TCRRT group showed significantly more improvement in the MFRT, MMT, 10MWT, TUG, and VAS compared to that before intervention (p<0.05). In addition, all tests were significantly greater in the experimental group than in the control group. Conclusion: These results suggest that TCRRT is feasible and effective for improving the dynamic balance, lower extremity strength, gait ability, and pain efficacy after bipolar hemiarthroplasty.

• The Journal of Korean Physical Therapy
• /
• v.25 no.4
• /
• pp.195-203
• /
• 2013

Purpose: The purpose of this study was to determine the effect of early Robot-assisted training on gait ability, function and ADL in patients with stroke. Methods: 26 patients with stroke were recruited for this study. The subjects were randomly assigned to either the experimental group (EG) or the control group (CG), with 13 patients in each group. All subjects received a routine physical therapy. The robot-assisted training was for 30 min in the case of the EG subjects. The assessment tools of this study involved the gait ability, balance ability, function and ADL. The measurements were recorded before the intervention and after the intervention. Results: EG subjects and CG subjects, the variables measured after the intervention significantly differed from gait ability, balance ability, function and ADL without the FMA (p<0.05). The FMA was only effective experimental group after intervention. Also, there were significant differences in gait ability, balance ability, function and ADL without the FMA at post-test between the 2 groups (p<0.05). Conclusion: The findings indicate that early robot-assisted training exerts a positive effect on gait ability, balance ability, function and ADL in patients with stroke. This result indicates the possibility of application of the early Robot-assisted training to the management for stroke patients. Further studies are required to generalize the result for this study.

• Journal of Korea Multimedia Society
• /
• v.17 no.4
• /
• pp.514-525
• /
• 2014

We have performed a short-term computer information and communication technology education using Arduino. The purpose of this education was to progress basic training interestingly and discover excellent students. Training was about practicing basic examples about H/W, S/W, communication, and solving creative tasks. We divided training participants into a team composed of each 3 members and educated them for 10 hours. Instructors were consists of 1 main teacher and 3 teacher assistants. Training was about assembling Arduino based robot, blinking LED, operating speaker, serial communication, producing software for wireless communications and autonomous of robot, and control hardware of robot. Through this study, we developed a meaningful ICT integrated curriculum which has high usefulness in a short period. Students participated in this education completed 96% out of 10 creative tasks, and this study analyzes the result of curriculum and suggests further research directions.