Search Results

Demand for predictive powertrain control is rapidly increasing with the recent advancement of Advanced Driving Assistance Systems (ADAS) and Autonomous Driving (AD). The full or semi-autonomous functions could be leveraged to realize better user acceptance as well as powertrain efficiency of the connected vehicle utilizing the proposed Drive Horizon. The sensors of automated driving provide perception of surrounding driving environment which is required to safely navigate the vehicle in real-world driving scenarios. The proposed Drive Horizon provides real-time forecast of driving environment that a vehicle will encounter during its entire travel. This paper summarizes the vehicle’s future speed prediction technique which is an integral part of Drive Horizon for optimized energy control of the vehicle. The prediction model has been developed that integrates information from multiple sources including vehicle GPS, traffic information and map data.

Suspension is an important chassis part which is vital to ride comfort [1]. However, it is difficult to achieve our targeted comfortability level in a short time. Therefore, improving efficiency of damper development is our primary challenge. We have launched a project which aims to reduce the workload on developing dampers by introducing analytical approaches to the improvement of ride comfort. To be more specific, we have been putting effort into developing the damping force prediction, the vehicle dynamics prediction and subjective rating prediction. This paper describes subjective rating prediction method which output a subjective rating corresponding to the physical value of the vehicle dynamics with deep learning. As a result of verification using objective data which was not used for learning process, DNN (Deep Neural Network) prediction method could fairly precisely predict subjective rating of the expert driver.

There is accumulating evidence that drowsy driving is one of the leading causes of vehicle crashes and accidents worldwide. Consequently, automotive manufacturers started to develop in-vehicle drowsiness detection devices. However, due to the limited computation resources and the complexity of the vehicular environment, the existing products' performance is limited. Moreover, the vast majority of the commercialized products focus on monitoring the subject's current drowsiness level, whereas predicting drowsiness level in advance to avoid future risks is overlooked. In this research, a multi-time-scale fusion approach is proposed where prediction results from both long-term and short-term Recurrent Neural Networks (RNN) were combined to predict a person's drowsiness level. Our results indicate that the proposed fusion strategies can successfully capture both the short-term microsleep-related features and long-term sleepiness features and improve the drowsiness prediction performance.

The flight area of drones and other unmanned aerial vehicles (UAVs) had been highly restricted but has been relaxing, including flights beyond the scope of sight. Deregulation without aircraft-reliability improvement increases the risk of accidents. However, demanding high reliability for all aircraft leads to an increase in the price of the aircraft. Therefore, if airspace restrictions are relaxed for more reliable aircraft, the cost of higher reliability and its benefits can be balanced. This will improve efficiency and optimize cost-effectiveness. The purpose of this proposal is to balance the cost of aircraft-reliability improvement (which allows flight to continue in the event of a failure) and its advantages. Specifically, the author proposes rules that apply more relaxed airspace restrictions to UAVs with higher FCLs (Flight Continuity Possibility Levels) and stricter airspace restrictions to those with lower FCLs.