Future Self-driving Vehicles Research Articles

Vehicular Bidirectional Internal Antenna with Asymmetric Gain Characteristics to Compensate for Backward Link Path Loss due to Interior Obstacles

Wireless communication technologies are expected to become essential in future self-driving vehicles. This study presents an antenna for vehicle wireless communication with a bandwidth of 75 MHz at a Wireless Access in Vehicular Environment frequency of 5.885 GHz. To compensate for the backward link path loss from the vehicle interior and passengers, the antenna is designed to have asymmetric gains of 0 and 6 dBi at 0° and 180°, respectively. The antenna is validated through an outdoor road test. We measured the received continuous-wave (CW) power, received signal strength indicator, and packet-delivered ratio (PDR) of the digital signal under vehicle-to-vehicle communication mode. Similar power is received in both the backward and forward scenarios. The forward and backward PDR are also similar.

Exploring the utility of EDA and skin temperature as individual physiological correlates of motion sickness

Motion sickness (MS) is known to be a potentially limiting factor for future self-driving vehicles – specifically in regards to occupant comfort and well-being. With this as a consideration comes the desire to accurately measure, track and even predict MS state in real-time. Previous research has considered physiological measurements to measure MS state, although, this is mainly measured after an MS exposure and not throughout exposure(s) to a MS task. A unique contribution of this paper is in the real-time tracking of subjective MS alongside real-time physiological measurements of Electrodermal Activity (EDA) and skin temperature. Data was collected in both simulator-based (controlled) and on-road (naturalistic) studies. 40 participants provided at total of 61 data sets, providing 1603 min of motion sickness data for analysis. This study is in agreement that these measures are related to MS but evidenced a total lack of reliability for these measures at an individual level for both simulator and on-road experimentation. It is likely that other factors, such as environment and emotional state are more impactful on these physiological measures than MS itself. At a cohort level, the applicability of physiological measures is not considered useful for measuring MS accurately or reliably in real-time. Recommendations for further research include a mixed-measures approach to capture other data types (such as subject activity) and to remove contamination of physiological measures from environmental changes.

Rapid-Response Framework for Defensive Driving Based on Internet of Vehicles Using Message-Oriented Middleware

With the rapid development of automatic driving and advanced driver assistance systems, vehicle safety has improved greatly. These systems mainly use sensors installed on the vehicle and help drivers deal with human operation errors. Traffic accidents are inherently unpredictable, and it is difficult to prevent mistakes made by others. Therefore, the concept of defensive driving has attracted much interest. Defensive driving aims to increase drivers’ self-awareness to prevent accidents. Future self-driving vehicles should integrate defensive driving to improve driver safety. This paper proposes a framework based on the risk evaluation value of defensive driving that rapidly transmits information about high-accident-likelihood zones to drivers or vehicles by using Internet of Vehicles technology. This should enable drivers or self-driving vehicles to predict risks and operate vehicles safely. To send alert messages in a timely manner, it is essential to overcome the challenge of processing real-time data during driving. We design five kinds of services in this rapid response framework, including raw data receiver, warning area decision, accident pattern recognition, message generator, and user profile to analyze driver information using distributed system architecture. Message-oriented middleware is used for communication between services. This framework identifies high-accident-likelihood zones by using density-based spatial clustering of applications with noise, simplifying the process of association calculation. After the calculation, this framework uses the weighted severity index to weight and compare risk severities. According to our experimental results, the service-oriented middleware design increases the speed and stability of information transmission.

On-Board Detection of Pedestrian Intentions

Avoiding vehicle-to-pedestrian crashes is a critical requirement for nowadays advanced driver assistant systems (ADAS) and future self-driving vehicles. Accordingly, detecting pedestrians from raw sensor data has a history of more than 15 years of research, with vision playing a central role. During the last years, deep learning has boosted the accuracy of image-based pedestrian detectors. However, detection is just the first step towards answering the core question, namely is the vehicle going to crash with a pedestrian provided preventive actions are not taken? Therefore, knowing as soon as possible if a detected pedestrian has the intention of crossing the road ahead of the vehicle is essential for performing safe and comfortable maneuvers that prevent a crash. However, compared to pedestrian detection, there is relatively little literature on detecting pedestrian intentions. This paper aims to contribute along this line by presenting a new vision-based approach which analyzes the pose of a pedestrian along several frames to determine if he or she is going to enter the road or not. We present experiments showing 750 ms of anticipation for pedestrians crossing the road, which at a typical urban driving speed of 50 km/h can provide 15 additional meters (compared to a pure pedestrian detector) for vehicle automatic reactions or to warn the driver. Moreover, in contrast with state-of-the-art methods, our approach is monocular, neither requiring stereo nor optical flow information.