Concept of an enhanced V2X pedestrian collision avoidance system with a cost function–based pedestrian model

Abstract

Objective: State-of-the-art collision avoidance and collision mitigation systems predict the behavior of pedestrians based on trivial models that assume a constant acceleration or velocity. New sources of sensor information-for example, smart devices such as smartphones, tablets, smartwatches, etc.-can support enhanced pedestrian behavior models. The objective of this article is the development and implementation of a V2Xpedestrian collision avoidance system that uses new information sources. Methods: A literature review of existing state-of-the-art pedestrian collision avoidance systems, pedestrian behavior models in advanced driver assistance systems (ADAS), and traffic simulations is conducted together with an analysis of existing studies on typical pedestrian patterns in traffic. Based on this analysis, possible parameters for predicting pedestrian behavior were investigated. The results led to new requirements from which a concept was developed and implemented.Results: The analysis of typical pedestrian behavior patterns in traffic situations showed the complexity of predicting pedestrian behavior. Requirements for an improved behavior prediction were derived. A concept for a V2X collision avoidance system, based on a cost function that predicts pedestrian near future presence, and its implementation is presented. The concept presented considers several challenges such as information privacy, inaccuracies of the localization, and inaccuracies of the prediction. Conclusion:A concept for an enhanced V2X pedestrian collision avoidance system was developed and introduced. The concept uses new information sources such as smart devices to improve the prediction of the pedestrian's presence in the near future and considers challenges that come along with the usage of these information sources.

Prediction of Pedestrian Crossing Intentions at Intersections Based on Long Short-Term Memory Recurrent Neural Network

“…It could be too late for drivers to take evasive actions when the pedestrian was already in the FOV. Thus, more work should be done to capture and predict pedestrians’ jaywalking intentions ( 14 , 15 ).…”

Use Of Smartphones for Ensuring Vulnerable Road User Safety through Path Prediction and Early Warning: An In-Depth Review of Capabilities, Limitations and Their Applications in Cooperative Intelligent Transport Systems

“…It has to be mentioned that the majority of the authors tried to tackle non-line-of-sight and blind spots, where the driver's view is limited due to buildings, vehicles and other obstacles. The majority of research was carried out in 2014 [14,[19][20][21], in 2016 [1,[22][23][24][25][26] and in 2017 [27][28][29]. Moreover, most of the V2P developments used several sensors data fusion techniques [1,19,21,22,24,26,27,30], while some of them [20,31] discussed methods to predict VRU next move/short path and some others presented collision avoidance systems [23,26,32].…”

Study on the Framework of Intersection Pedestrian Collision Warning System Considering Pedestrian Characteristics

“…However, the previously proposed systems still have some limitations in identifying pedestrians' intended crossing behaviors, because it is difficult for the distance sensors to capture characteristics of pedestrians such as age and gender. These contributing factors are deeply correlated with the speed and acceleration of the pedestrian who is crossing (9,10). Several previous studies also revealed that information on the pedestrian's head orientation has a high potential for being useful for recognizing the pedestrian's decision to cross the road or not (10)(11)(12).…”

“…These contributing factors are deeply correlated with the speed and acceleration of the pedestrian who is crossing (9,10). Several previous studies also revealed that information on the pedestrian's head orientation has a high potential for being useful for recognizing the pedestrian's decision to cross the road or not (10)(11)(12). Consequently, such characteristics of pedestrians highly affect the performance of ICWS in preventing pedestrian-vehicle collisions caused by the unexpected hazardous behaviors of pedestrians crossing (13)(14)(15).…”

“…However, most of the existing ICWSs have been developed based on parametric approaches, which have some limitations in capturing the characteristics of the pedestrian’s crossing intention. Because pedestrian behaviors at the crosswalk are affected by different unobservable factors ( 10 ), non-parametric approaches such as machine learning techniques can be effective for describing an outcome from the characteristics of the pedestrian’s crossing intention. The machine learning technique is a method to find the relationship between data and the actual phenomenon corresponding to a large amount of data.…”