Collision avoidance system

About: Collision avoidance system is a research topic. Over the lifetime, 1788 publications have been published within this topic receiving 23667 citations.

Characterization of Expert Drivers' Last-Second Braking and Its Application to a Collision Avoidance System

Abstract: Expert drivers' deceleration patterns in last-second braking will be formulated using a perceptual risk index for the approach and the proximity of a preceding vehicle as examples of comfortable braking patterns. It will be shown that the formulated braking pattern can uniformly generate a smooth deceleration profile for many approach conditions. In addition, the brake initiation timing of expert drivers will be successfully formulated using a modified index. Finally, an automatic braking system for collision avoidance will be proposed based on a formulated brake-initiation model and a deceleration pattern. Twenty five expert drivers will experience the automatic braking that is installed in an experimental car. It will be shown that the proposed system can generate a smooth profile and realize secure brake patterns based on the drivers' subjective evaluation.

Crash prediction with behavioral and physiological features for advanced vehicle collision avoidance system

Abstract: Real-time crash prediction is the key component of the Vehicle Collision Avoidance System (VCAS) and other driver assistance systems. The further improvements of predictability requires the systemic estimation of crash risks in the driver-vehicle-environment loop. Therefore, this study designed and validated a prediction method based on the supervised learning model with added behavioral and physiological features. The data samples were extracted from 130 drivers’ simulator driving, and included various features generated from synchronized recording of vehicle dynamics, distance metrics, driving behaviors, fixations and physiological measures. In order to identify the optimal configuration of proposed method, the Discriminant Analysis (DA) with different features and models (i.e. linear or quadratic) was tested to classify the crash samples and non-crash samples. The results demonstrated the significant improvements of accuracy and specificity with added visual and physiological features. The different models also showed significant effects on the characteristics of sensitivity and specificity. These results supported the effectiveness of crash prediction by quantifying drivers’ risky states as inputs. More importantly, such an approach also provides opportunities to integrate the driver state monitoring into other vehicle-mounted systems at the software level.

Preliminary studies in haptic displays for rear-end collision avoidance system and adaptive cruise control system applications

Abstract: In this report, the authors examine the applicability of haptic displays for rear-end collision avoidance warnings. Concepts and published research studies are reviewed in the report. This is followed by three small-scale studies of mono-pulse braking and active steering displays. Two parameter setting studies are first discussed. The first examined the display parameter settings of a mono-pulse braking display, while the second examined the effects of active steering vibration amplitude frequency, and duration on display detectability and appropriateness ratings. Based on the results obtained, the authors suggest that active steering displays be reserved for future collision avoidance system integration. In the third study, the authors examined the response of drivers in a car following situation to a mono-pulse braking display under two different simulated rear-end collision avoidance warning scenarios. Results suggest that mono-pulse braking displays might be of use in rear-end collision avoidance applications.

Synthesis report: examination of target vehicular crashes and potential its countermeasures. final report

Abstract: This report synthesizes the results of a preliminary analysis of nine major target crashes: (1) rear-end, (2) backing, (3) lane change and merge, (4) single vehicle roadway departure, (5) opposite direction, (6) signalized intersection, straight crossing path, (7) unsignalized intersection, straight crossing path, (8) left turn across path, and (9) reduced visibility. This report provides statistical descriptions of target crash sizes and characteristics, identifies crash subtypes and causal factors, defines Intelligent Transportation System (ITS) Collision Avoidance System (CAS) concepts, and includes a sample of kinematic models representing crash avoidance actions. A case-by-case examination of a sample of 1,183 crashes identified 18 crash subtypes and showed that driver recognition and driver decision errors were the primary causes of 44% and 23% of target crashes, respectively. The CAS concepts discussed in this report provide mechanisms of intervention in three basic categories: advisory, warning, and automatic control intervention. Crash avoidance actions are kinematically modeled as applied to target crash subtypes in terms of braking, steering, and holding course actions. This report concludes by highlighting key results of the analysis.