This Automated driving is an emerging technology in which a car performs recognition, decision making, and control. Recognizing surrounding vehicles is a key technology in order to generate a trajectory of ego vehicle. This paper is focused on detecting a turn signal information as one of the driver's intention for surrounding vehicles. Such information helps to predict their behavior in advance especially about lane change and turn left-or-right on intersection. Using their intension, the automated vehicle is able to generate the safety trajectory before they begin to change their behavior. The proposed method recognizes the turn signal for target vehicle based on mono-camera. It detects lighting state using Convolutional Neural Network, and then calculates a flashing frequency using Fast Fourier Transform.
The magnitude of impulse and work at pen tip, which are related to the fingertip force, may be indicators of fatigue and pain during writing. Previous methods used specially prepared pens for testing which have different sizes and weights from those commercially available; however, they are not suitable for evaluating the operation and workload of ordinary handwriting tasks. This paper proposes a data processing method of a six-axis force-torque sensor for determining the contact state of the pen tip and calculating the position and work of the pen tip without adding anything to a commercially available pen. The proposed method consists of kinematic calculation of the pen tip position as the observation and probabilistic determination of the contact state of the pen tip. The performance of the proposed method is presented by applying to the time-series data of force vector and moment vector during handwriting tasks of symbols. The data was measured by a low-resolution high-frequency 6-DoF force-torque sensor. Multiple handwriting tasks with the same or different load at one time were set. It was confirmed statistically whether the work amount with one pen tip can be evaluated appropriately if the work amount is the same or different. The experimental results demonstrate that the proposed method can compare the movement distance and work of the pen tip, depending on the severity of the writing task.
2 December 2024 in International Journal of Occupational Safety and Ergonomics
Heavy lifting tasks at work sites can cause musculoskeletal disorders. One strategy to avoid such disorders is to choose a work motion with low cumulative physical workload during the work. This study investigated whether the cumulative workload between different work motions can be compared from a biomechanical perspective. The work motions were analyzed biomechanically by a digital human model. The cumulative workload was calculated using the time integrated value of the product of the torque and the amount of motion at each joint, i.e., an index proposed by a previous study. The results showed that the lifting operation with the shortest route is not always optimal in terms of cumulative workload on the whole body. This indicates the importance of selecting work motions based on a cumulative workload index obtained by mechanical analysis.