Search

Introduction/Background For stroke patients with hemiplegia, walking exercise are conventionally practiced using orthoses. For severe hemiplegic patients, knee-ankle-foot orthoses (KAFO) are frequently used to prevent giving way in the stance phase. However, it is very difficult to swing paralytic leg with KAFO. As a result, walking exercise with KAFO requires a high level of assistance and raise low exercise intensity. To solve these problems, we developed Welwalk, which has a motor on the knee joint with KAFO-like framework. Welwalk can extend and flex the knee in appropriate timing. This time, we examined whether subacute stroke patients with hemiplegia using Welwalk show early improvement in walking independence compared to patients using KAFO. Material and method Fourteen patients who satisfied the following criteria were included: patients with hemiplegia caused by primary supratentorial intracerebral hemorrhage or cerebral infarction, within 60 days after onset, aged 20 to 75 years, Functional Independence Measure (FIM) walking score ≤ 3, Stroke Impairment Assessment Set (SIAS) lower extremity total score ≤ 6, and use of KAFO. Rehabilitation was conducted for a maximum of 3 hours a day, including 40 minutes of walking exercise using Welwalk. A historical control group was selected from among patients admitted to the ward for intensive inpatient rehabilitation at Nanakuri Memorial Hospital. One control patient matching the criteria of each subject was selected, with a total of fourteen in the control group. The primary outcome measure was the improvement in efficiency of FIM-walk, defined as the gain in FIM walking score from the baseline to supervised walking divided by the number of weeks required. Results The mean improvement in efficiency of FIM- walk was 0.9 in the Welwalk group and 0.5 in the control group, and was significantly higher in the GEAR group (P Conclusion Walking exercise using Welwalk may facilitate early improvement in walking independence.

Traditionally, robots and humans work independently, isolated from each other for safety reasons. We developed a robot for use on the assembly line which works together with a human operator, assisting and augmenting the operator's skills. Because of its function, this robot is known as the “Car Window Installation Assist Robot” and is currently in use on the plant of Toyota Motor Corporation. In this paper, we propose a method to estimate human intent as well as a skill assist control method. Moreover, we present technology that enables safe human-robot cooperation, high product quality, and the cycle time of only 48 seconds.

Industrial robots have been widely used in factory automation. On the other hand, in the final assembly in automobile factories, many tasks are still completed by humans due to the difficulties and costs associated with automation. One example still requiring skilled human operators is the installation of the automobile window. The window installation assist robot we developed enables a single operator to install a window easily. The present study focuses on kinesthetic assistance including preliminary experiments and application to automobile window installation during car assembly demonstrating the effectiveness of our proposal.

Automatic detection of the level of human interest is of high relevance for many technical applications, such as automatic customer care or tutoring systems. However, the recognition of spontaneous interest in natural conversations independently of the subject remains a challenge. Identification of human affective states relying on single modalities only is often impossible, even for humans, since different modalities contain partially disjunctive cues. Multimodal approaches to human affect recognition generally are shown to boost recognition performance, yet are evaluated in restrictive laboratory settings only. Herein we introduce a fully automatic processing combination of Active-Appearance-Model-based facial expression, vision-based eye-activity estimation, acoustic features, linguistic analysis, non-linguistic vocalisations, and temporal context information in an early feature fusion process. We provide detailed subject-independent results for classification and regression of the Level of Interest using Support-Vector Machines on an audiovisual interest corpus ( AVIC ) consisting of spontaneous, conversational speech demonstrating "theoretical" effectiveness of the approach. Further, to evaluate the approach with regards to real-life usability a user-study is conducted for proof of "practical" effectiveness.