Drowsy driving is one of the main causes of traffic accidents. To reduce such accidents, early detection of drowsy driving is needed. In previous studies, it was shown that driver drowsiness affected driving performance, behavioral indices, and physiological indices. The purpose of this study is to investigate the feasibility of classification of the alert states of drivers, particularly the slightly drowsy state, based on hybrid sensing of vehicle-based, behavioral, and physiological indicators with consideration for the implementation of these identifications into a detection system. First, we measured the drowsiness level, driving performance, physiological signals (from electroencephalogram and electrocardiogram results), and behavioral indices of a driver using a driving simulator and driver monitoring system. Next, driver alert and drowsy states were identified by machine learning algorithms, and a dataset was constructed from the extracted indices over a period of 10 s. Finally, ensemble algorithms were used for classification. The results showed that the ensemble algorithm can obtain 82.4% classification accuracy using hybrid methods to identify the alert and slightly drowsy states, and 95.4% accuracy classifying the alert and moderately drowsy states. Additionally, the results show that the random forest algorithm can obtain 78.7% accuracy when classifying the alert vs. slightly drowsy states if physiological indicators are excluded and can obtain 89.8% accuracy when classifying the alert vs. moderately drowsy states. These results represent the feasibility of highly accurate early detection of driver drowsiness and the feasibility of implementing a driver drowsiness detection system based on hybrid sensing using non-contact sensors.

Thermal factors not only affect the thermal comfort sensation of occupants, but also affect their arousal level, productivity, and health. Therefore, it is necessary to control thermal factors appropriately. In this study, we aim to design a thermal environment that improves both the arousal level and thermal comfort of the occupants. To this end, we investigated the relationships between the physiological indices, subjective evaluation values, and task performance under several conditions of changes in the indoor ambient temperature. In particular, we asked subjects to perform a mathematical task and subjective evaluation related to their thermal comfort sensation and drowsiness levels. Simultaneously, we measured their physiological parameters, such as skin temperature, respiration rate, electroencephalography, and electrocardiography, continuously. We investigated the relationship between the comfort sensation and drowsiness level of occupants, and the physiological indices. From the results, it was confirmed that changes in the indoor ambient temperature can improve both the thermal comfort and the arousal levels of occupants. Moreover, we proposed the evaluation indices of the thermal comfort and the drowsiness level of occupants using physiological indices.

Detection of traversable areas is essential to navigation of autonomous personal mobility systems in unknown pedestrian environments. However, traffic rules may recommend or require driving in specified areas, such as sidewalks, in environments where roadways and sidewalks coexist. Therefore, it is necessary for such autonomous mobility systems to estimate the areas that are mechanically traversable and recommended by traffic rules and to navigate based on this estimation. In this paper, we propose a method for weakly-supervised recommended traversable area segmentation in environments with no edges using automatically labeled images based on paths selected by humans. This approach is based on the idea that a human-selected driving path more accurately reflects both mechanical traversability and human understanding of traffic rules and visual information. In addition, we propose a data augmentation method and a loss weighting method for detecting the appropriate recommended traversable area from a single human-selected path. Evaluation of the results showed that the proposed learning methods are effective for recommended traversable area detection and found that weakly-supervised semantic segmentation using human-selected path information is useful for recommended area detection in environments with no edges.

In Japan, the aging population is expected to increase the number of elderly people in the future. The purpose of this study was to develop a hip lift transfer assistive system to improve the QOL of elderly living and to prevent back pain for caregivers. We extracted the impediment factor and the necessary scene for the assistance, decided on the transfer process from the wheelchair in the toilet, and considered the reduction method of the burden based on the quantitative evaluation of the caregiver’s lumbar burden and developed the device. Then we proposed the algorithm of the system by grasping the behavior and lumbar burden characteristics at the time of using the hip lift transfer assistive system by the developed device in which the proposed support algorithm of standing seating assistance operation is implemented in the actual use environment. Through the assistive movement evaluation experiment and the actual operation in the toilet, we have verified that the use of this device can reduce the caregivers’ lumbar burden below the standard value (3400 N) and have proved the effectiveness of the proposed transfer assistive system.

Individuals with severe physical impairments have difficulties operating electric wheelchairs (EWs), especially in situations where fine steering abilities are required. Automatic driving partly solves the problem, although excessive reliance on automatic driving is not conducive to maintaining their residual physical functions and may cause more serious diseases in the future. The objective of this study was to develop a shared control system that can be adapted to different environments by completely utilizing the operating ability of the user while maintaining the motivation of the user to drive. The operating characteristics of individuals with severe physical impairments were first analyzed to understand their difficulties when operating EWs. Subsequently, a novel reinforcement learning-based shared control method was proposed to adjust the control weight between the user and the machine to meet the requirements of fully exploiting the operating abilities of the users while assisting them when necessary. Experimental results showed that the proposed shared control system gradually adjusted the control weights between the user and the machine, providing safe operation of the EW while ensuring full use of the control signals from the user. It was also found that the shared control results were deeply affected by the types of users.

With the aging society in Japan, the number of elderly people residing in elderly facilities is increasing. In previous study, we developed a transfer assistive device designed to aid the elderly in transferring from the bedroom to the bathroom. Additionally, the device assists the elderly with standing and sitting to facilitate independent toileting activities. We verified that, throughout the entire transfer movement, the lumbar burden on caregivers remained below 3400 N. In this study, based on quantitative evaluation indices of transfer movements, the relationship between the lumbar burden on caregivers and factors such as psychological anxiety or cognitive impairment in the elderly during the use of a transfer assistive device was elucidated through motion analysis. We developed a control algorithm for the human–machine collaborative transfer system with the aim of alleviating the strain on the caregiver’s lower back while ensuring the elderly can use the device with peace of mind. The practicality of the control algorithm was verified.