PURPOSES : This study is to develop an comprehensive validation methodology for autonomous mobility-on-demand system with level 4 automated driving system. METHODS : The proposed method includes the quantitative techniques for validating both automated driving system and center system using each optimal indicators. In addition, a novel method for validating the whole system applying multi-criteria decision methodology is suggested. RESULTS : The relative weights for the vehicle system was higher than the center systems. Moreover, the relative weights of failure rate for validating the vehicle system was the highest, in addition to, a relative weight for accuracy of dynamic routing algorithm within center system was the highest. CONCLUSIONS : The proposed methodology will be applicable to validate the autonomous mobility on demand system quantitatively considering the relative weights for each systems.

In general, electric powered wheelchair is used for handicapped persons as a means of movement. Electric powered wheelchair is controlled via joystick, which means that seriously handicapped person as vertebra damaged person can not use the general electric powered wheelchair. In this paper, a new navigation method for an intelligent electric powered wheelchair is proposed, which is very simple to implement by using the robotic technology. Two cameras are used in the system. The one is used for detecting obstacles in front of the wheelchair, and the other is used for detecting the intention of the user by measuring the movement of the head. A series of experiments are performed to evaluate the proposed method and the experimental results show that the proposed method can be applicable to the navigation of an intelligent electric powered wheelchair for seriously handicapped person of vertebra damage.

This paper presents a new benchmark system for visual odometry (VO) and monocular depth estimation (MDE). As deep learning has become a key technology in computer vision, many researchers are trying to apply deep learning to VO and MDE. Just a couple of years ago, they were independently studied in a supervised way, but now they are coupled and trained together in an unsupervised way. However, before designing fancy models and losses, we have to customize datasets to use them for training and testing. After training, the model has to be compared with the existing models, which is also a huge burden. The benchmark provides input dataset ready-to-use for VO and MDE research in ‘tfrecords’ format and output dataset that includes model checkpoints and inference results of the existing models. It also provides various tools for data formatting, training, and evaluation. In the experiments, the exsiting models were evaluated to verify their performances presented in the corresponding papers and we found that the evaluation result is inferior to the presented performances.

In this study an algorithm estimating total load and axial load was conducted using BWIM(Bridge Weigh-in-Motion) system with precision analysis model. Driving test for running vehicle is necessary but it needs much cost, time, and especially hard to applicate to various driving condition. Thus we need a numerical-simulation method for resolving the cost and time problems of driving test for vehicle, and a way to measure bridge responses reflecting many unpredictable situations. Using a precision analysis model reflecting the dynamic characteristic contributes to increase the accuracy in numerical simulation. In this paper, we conduct a numerical simulation to apply a precision analysis model, which reflects the dynamic characteristic of a bridge using the Bridge Weigh-in-Motion system, and suggested a method of overloaded vehicle enforcement technology using the precision analysis model.

This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.