Stereo Vision-Based Road Debris Detection System for Advanced Driver Assistance Systems

Reliable detection of obstacles around an autonomous vehicle is essential to avoid potential collision and ensure safe driving. However, a vast majority of existing systems are mainly focused on detecting large obstacles such as vehicles, pedestrians, and so on. Detection of small obstacles such as road debris, which pose a serious potential threat are often overlooked. In this article, a novel stereo vision-based road debris detection algorithm is proposed that detects debris on the road surfaces and estimates their height accurately. Moreover, a collision warning system that could warn the driver of an imminent crash by using 3D information of detected debris has been studied. A novel feature-based classifier that uses a combination of strong and weak features has been developed for the proposed algorithm, which identifies debris from selected candidates and calculates its height. 3D information of detected debris and vehicle’s speed are used in the collision warning system to warn the driver to safely maneuver the vehicle. The performance of the proposed algorithm has been evaluated by implementing it on a passenger vehicle. Experimental results confirm that the proposed algorithm can successfully detect debris of ≥5 cm height for up to a 22 m distance with an accuracy of 90%. Moreover, the debris detection algorithm runs at 20 Hz in a commercially available stereo camera making it suitable for real-time applications in commercial vehicles.

Expert’s Heuristic Biases in Airport Predictive Risk Assessments

Expert perceptions have been increasingly used to perform risk assessments in airport predictive risk assessments in recent years. Although it is known that biases are less influential in groups of experts when compared to laypeople, they still can be residually present in such tasks with this specific group. Therefore, this article aims to propose (1) the pragmatic organization of knowledge about the biases that may affect airport risk assessments by groups of experts and (2) which of them most often arise in this type of analysis and at what intensity. For the development of the work, we carried out a dense bibliographic review of the theme. Later, we performed a predictive risk assessment and a survey, with the support of an experienced group of 30 experts from Brazilian regulatory agency and airport operators. After 1224 risk judgments, experts were able to clearly indicate regulations and their sections that are disproportionately more and less important in terms of risk, leading States to a better regulatory quality only by changing their logic of actions to a risk-based approach. Later the group answered a survey on a list of 12 heuristic biases created from the bibliographic review. Results showed that, in fact experts have a resistance to biases influence, mainly based in their academic and professional background, but also showed this influence is not exactly negligible. It was also possible to rank the heuristic biases in terms of importance and indicate that experts tend to concern with three hierarchical information characteristics when judging risk: at first, would be the form in which risk problems are presented; second, how they interpret information presented; and third, the amount of information presented.

A Nonlinear Model Predictive Control Design for Autonomous Multivehicle Merging into Platoons

Integrated control for automated vehicles in platoons with nonlinear coupled dynamics is developed in this article. A nonlinear MPC approach is used to address the multi-input multi-output (MIMO) nature of the problem, the nonlinear vehicle dynamics, and the platoon constraints. The control actions are determined by using model-based prediction in conjunction with constrained optimization. Two distinct scenarios are then simulated. The first scenario consists of the multivehicle merging into an existing platoon in a controlled environment in the absence of noise, whereas the effects of external disturbances, modeling errors, and measurement noise are simulated in the second scenario. An extended Kalman filter (EKF) is utilized to estimate the system states under the sensor and process noise effectively. The simulation results show that the proposed approach is a suitable tool to handle the nonlinearities in the vehicle dynamics, the complication of the multivehicle merging scenario, and the presence of modeling uncertainties and measurement noise.

Survey-Based Accident Analysis for Human-Powered Three-Wheeled Vehicles

The causes of accidents involving nonconventional bicycle types have hardly been investigated in the literature to date. However, these vehicles could play an important role in reducing the CO2 emissions generated by traffic. As a basis for improving the driving safety of these environmentally friendly vehicles, this article presents the results of a survey on accidents and near-accidents of multitrack bicycle vehicles. More than 120 critical or accident situations of 86 drivers were analyzed. The situations are investigated with respect to the circumstances, the causes, and the consequences of the accidents using manual analysis and multiple correspondence analysis. A distinction is made between single accidents and accidents with another party. The aim of the survey is not to make statistically accurate statements on the frequency and probability of accidents, but rather to analyze the accident or near-accident circumstances. It is shown that the causes of single accidents are usually too high cornering velocities in combination with other factors such as road conditions. In the case of accidents with external involvement, the person who caused the accident is usually the other party involved. The accident opponent is in most cases a passenger car. Here the overlooking of the vehicles is the most frequent cause of accidents. Finally, possibilities to reduce the probability of accidents are briefly discussed for the different situations. As the research shows, most of the situations described occur on the road. This indicates that there are deficits in the bicycle infrastructure for the vehicles considered here. The results also indicate that there are deficits with regard to the perceptibility of the vehicles by other road users.

Assessment of Acclimation of 5th Percentile Female and 50th Percentile Male Volunteer Kinematics in Low-Speed Frontal and Frontal-Oblique Sled Tests

In order to accurately represent the response of live occupants during pre-crash events and frontal crashes, computational human body models (HBMs) that incorporate active musculature must be validated with appropriate volunteer data that represents a wide range of demographic groups and potential crash conditions. The purpose of this study was to quantify and compare occupant kinematic responses for unaware (relaxed) small female and midsize male volunteers during low-speed frontal and frontal-oblique sled tests across multiple test conditions, while recognizing, assessing, and accounting for potential acclimation effects due to multiple exposures. Six 5th percentile female and six 50th percentile male volunteers were exposed to multiple low-speed frontal and frontal-oblique sled tests on two separate test days. Volunteers experienced one test orientation and two pulse severities (1 g and 2.5 g) on each test day. A Vicon motion capture system was used to quantify the three-dimensional (3D) kinematics of the volunteers. Peak forward excursions of select body locations were compared within a test day and between test days for the same test condition to determine if and how acclimation occurred. Differences between demographic groups were also compared after accounting for any observed acclimation. Acclimation was not observed within a test day but was observed between test days for some demographic groups and some test conditions. In general, head, neck, and shoulder responses were affected, but the elbow, hip, and knee responses were not. Males generally moved farther forward compared to females during the frontal tests, but both groups moved forward similarly during the frontal-oblique tests. Overall, this study provides new female and male biomechanical data that can be used to further develop and validate HBMs that incorporate active musculature in order to better understand and assess occupant response and injury risk in pre-crash events and frontal crashes.

A Brain Wave-Verified Driver Alert System for Vehicle Collision Avoidance

Collision alert and avoidance systems (CAS) could help to minimize driver errors. They are instrumental as an advanced driver-assistance system (ADAS) when the vehicle is facing potential hazards. Developing effective ADAS/CAS, which provides alerts to the driver, requires a fundamental understanding of human sensory perception and response capabilities. This research explores the premise that external stimulation can effectively improve drivers’ reaction and response capabilities. Therefore this article proposes a light-emitting diode (LED)-based driver warning system to prevent potential collisions while evaluating novel signal processing algorithms to explore the correlation between driver brain signals and external visual stimulation. When the vehicle approaches emerging obstacles or potential hazards, an LED light box flashes to warn the driver through visual stimulation to avoid the collision through braking. Thirty (30) subjects completed a driving simulator experiment under different near-collision scenarios. The Steady-State Visually Evoked Potentials (SSVEP) of the drivers’ brain signals and their collision mitigation (control performance) data were analyzed to evaluate the LED warning system’s effectiveness. The results show that (1) The proposed modified canonical correlation analysis evaluation (CCA-EVA) algorithm can detect SSVEP responses with 4.68% higher accuracy than the Adaptive Kalman filter; (2) The proposed driver monitoring and alert system produce on average a 52% improvement in time to collision (TTC), 54% improvement in reaction distance (RD), and an overall 26% reduction in collision rate as compared to similar tests without the LED warning.

Response Corridors for Blunt Impacts to the Back

Corridors for the biofidelity of blunt impact to the back are important for sled and crash testing with Anthropomorphic Test Devices (ATDs). The Hybrid III is used in rear sled tests as part of Federal Motor Vehicle Safety Standards (FMVSS) 202a. The only corridor for biofidelity is the neck extension. Eight Post Mortem Human Subjects (PMHS) were subjected to 20 blunt impacts with a 15.2 cm (6 in.) diameter pendulum weighing 23.4 kg. The impact was below T1 at 4.5 m/s and 6.7 m/s and below T6 at 4.5 m/s centered on the back. Head, neck, and chest responses were reported in 2001 [8]. In this study, the responses were scaled to the 50th male Hybrid III, and corridors were determined defining biofidelity for blunt impacts to the back. The scaled data gives an average peak force of 3.44 kN ± 0.74 kN at T1 and 4.5 m/s, 5.08 kN ± 1.35 kN at T1 and 6.7 ms, and 3.4 kN ± 1.2 kN at T6 and 4.5 m/s. The corresponding scaled deflection was 44.0 ± 19.7 mm, 60.2 ± 21.2 mm, and 53.1 ± 16.5 mm. The average stiffness of the back was 1.21 kN/cm at T1 and 4.5 m/s, 1.17 kN/cm at T1 and 6.7 m/s, and 1.14 kN/cm at T6 and 4.5 m/s. The corridors help to define biofidelity and can be used to assess the performance of the Hybrid III, Biofidelic Rear Impact Dummy (BioRID) II, and other ATDs.