Lane change for automated vehicles (AVs) is an important but challenging task in complex dynamic traffic environments. Due to difficulties guaranteeing safety as well a high efficiency, AVs are inclined choose relatively conservative strategies lane change. To avoid the conservatism, this paper presents cooperation-aware method utilizing interactions between vehicles. We first propose interacti...

Autonomous vehicles must be comprehensively evaluated before deployed in cities and highways. However, most existing evaluation approaches for autonomous are static lack adaptability, so they usually inefficient generating challenging scenarios tested vehicles. In this paper, we propose an adaptive framework to efficiently evaluate adversarial environments generated by deep reinforcement learni...

We address a multi-vehicle automated driving scenario, where vehicle has to change lane and merge in platoon one-way roadway with two lanes. focus on the coordination phase of change, vehicles need create gap for merging enter safely following pre-computed optimal trajectory. The goal is pre-computing also strategy, so as limit computational communication effort involved its online implementati...

In this study, we present an innovative approach to risk assessment for rear-end collision avoidance using a cooperation concept autonomous lane change system. A Kalman filter is designed estimate the longitudinal acceleration and predict relative position, velocity, acceleration. Risk performed predicted motion of object vehicle in target lane. The proposed improve flexibility change. If indic...

The Lane Change Task was developed to provide an objective safety criterion for the assessmentof driver distraction by in-vehicle information systems (IVIS). It consists of two basic driving tasks,namely lane keeping and lane changes. The LCT has been shown to reliably detect distractionfrom driving. As this test becomes increasingly important for the assessment of safety the validi...

In this paper, we propose initial steps towards multi-modal driver stress (distraction) detection in urban driving scenarios involving multi-tasking, dialog system conversation, and medium-level cognitive tasks. The goal is to obtain a continuous operation-mode detection employing driver’s speech and CAN-Bus signals, with a direct application for an intelligent human-vehicle interface which wil...

Drivers' behavior is one of the most important factors in traffic safety. Understanding of this issue and its effective factors can be helpful to reduce the influences of human factors on traffic accidents. The objective of this study is to apply Manchester driver behavior questionnaire (DBQ) to a group of drivers who have overtaken on two-lane rural roads and to analyze their behavior. Also, t...

In this paper, we propose a torque vectoring controller for an electric vehicle with two electric machines which drive the front wheels independently. The torque vectoring system includes a vehicle dynamics controller and a motor torque and wheel slip limiter. The vehicle dynamics controller is designed as a polytopic, linear parameter-varying (LPV) gain-scheduled controller. The LPV controller...