The main function of the plug-in developed by us is to detect drivers' emotions and abnormal behaviors in real time, and feedback the results to the mobile web terminal and UC-Win /Road in real time. When the driver is detected to be angry, sad and other extreme emotions, the system will display a warning message to remind the driver to keep a good mood and play soothing music on the mobile web to ease the driver's mood. When it detects unusual behavior such as yawning, drowsiness, eating or smoking, the system will send out red warnings and voice alerts on the phone. So that drivers can maintain good driving habits, reduce the incidence of traffic accidents.

We developed a pedestrian simulator, an intelligent bracelet, and an eHMI early warning system based on UC/winRoad 15.0. The pedestrian simulator consists of three parts: pedestrian motion capture, information transmission, and information feedback. Pedestrian motion capture module uses keli to write MCU program and installs MCU module into a 3D printed shell. The information transmission module is realized by a UDP transmission tool and a python script. The feedback module is implemented based on the VR plugin of UC/winRoad, and feeds back the information in the scene to pedestrians through VR glasses of Oculus. The data of intelligent bracelet comes from UC/winRoad, and Arduino programs the specific functions. The eHMI early warning system is modeled by 3ds Max, and its specific functions are realized based on plug-ins written by UC/winRoad 15.0 SDK.

As a typical type of adverse weather, heavy rainfall can result in congestion and productivity loss in urban transportation system, which has been a severe problem for cities. Nowadays, little attention has been paid to the effects of the combination of rainfall and rain-induced waterlogging on urban road traffic. This study aims at thoroughly and quantitatively studying the effect of rainfall and waterlogging on traffic flow on urban road sections, based on a combination of methods including driving experiment and simulation. The results from this study can facilitate a deeper understanding of the rainfall and waterlogging on traffic flow.

The project proposes a system that uses UC-win/Road to obtain individual driving data and learn it in a deep learning model to create a personalized autonomous driving model and drive autonomously through it. Through this, it helps reduce the frustration or anxiety of drivers that can come from mechanical autonomous driving and drive more comfortably.And unlike existing UC-win/Road traffic vehicles, it creates traffic vehicles capable of human-like driving through our system.

Fatigue driving refers to the phenomenon that the driver's physiological and psychological functions become dysfunctional after a long period of continuous driving, and the driving skills objectively decline. To counter the possible dangerous effects of fatigue driving, we use UC-WinRoad software to simulate various fatigue driving scenarios and transmit vehicle data such as speed and driving time to the client in real time to remind drivers to take proper rest when there is a risk of fatigue driving,thus reducing traffic accidents caused by fatigue driving.

Currently, autonomous driving technology is advancing, and as a result, it is predicted that different type of accidents from the conventional manual driving will occur. Therefore, we are developing a database that can be used to create scenarios efficiently using the scenario function of UC-win Road, assuming traffic accidents during autonomous driving based on accident types and SIP1). With this database, we will be able to examine the accident risks of autonomous driving using a driving simulator, and contribute to the prevention of accidents during autonomous driving that are expected to occur from the viewpoint of "people, roads, and vehicles”.

Based on the need to fight ongoing global pandemic of coronavirus disease 2019 (COVID-19) and the fact that there’s no existing application to predict the infection risk of people’s travel in a city, we propose to develop an algorithm for travel path finding to minimize infection risk. Our work is 2 parts: simulation of the traffic and path finding algorithm to minimize infection risk value of each travel, calculated by aggregating (summing up) the value for risk of each transfer along that path. After carrying out simulation and path finding algorithm, we did visualization for verification.

With the trends of the Fourth Industrial Revolution, we can't deny the role of big data in different fields and not except for the travel industry. However, a challenge to all 4.0 tour operators/ travel agencies nowadays is increasingly complex data collection processes.
Firstly, data comes in all types of formats that can be difficult to harness. Secondly, the unreliable or incomplete nature of some data sets is significant obstacles to progress for the travel industry.
Therefore, we are creating TeleTrip - a mobile application to help businesses to collect visitor insights about their attractions and improve the services. Moreover, TeleTrip also gives people assistance to visit many famous landscapes all around the world.