Human reliability analysis in situated driving context considering human experience using a fuzzy-based clustering approach

Although more higher level advanced driver assistance systems (ADAS) are applied to driving, human driver reliability remains crucial for driving safety. Existing reliability approaches qualify human behaviors in a static manner. In this contribution dynamically changing situations are considered: as example dynamic and situated driving context is used for human reliability evaluation. The dynamic and situated driving context requires dynamic solutions for human reliability evaluation. Cognitive reliability and error analysis method (CREAM) provides the evaluation method for human reliability in industrial fields, when it is applied to situated context, adaption is required. Human-related accidents account for the highest proportion of total accidents. Human experience as an important factor for driving safety so should be considered when human driver reliability is evaluated. In this contribution, human driver experience (HDE) is quantitatively characterized for the first time. Three variables are selected to evaluate HDE in situated driving context. A new list of common performance conditions (CPCs) in CREAM to characterize the situated driving context is generated due to the application limits of CPCs in original CREAM. To determine the levels in HDE variables and new generated CPCs, fuzzy neighborhood density-based spatial clustering of application with noise (FN-DBSCAN) is applied to driving data defining the membership function parameters. Therefore, HDE and human driver reliability score (HDRS) in situated driving context are calculated quantitatively. In this contribution evaluation of HDE and HDRS is data-driven and the reliance on expert knowledge is reduced. Next, a new evaluation index, human performance reliability score (HPRS) is defined. The results show that the method could quantity and evaluate human driver reliability in real time.

I. Introduction

With the development of technology, automation has been applied in a wide variety of fields. In most safety-critical systems, such as power plants [1], aviation [2], and transportation [3], automation is applied. Automation has profoundly influenced human behaviors in human-machine systems. Following the application of automation in human-machine systems, the importance of humans is increasing as more and more accidents are related to human errors [4]. In several automated system transitions between human guidance and automated processes are possible, so takeover processes may occur. A reliable transition should be guaranteed to realize continuous and safe operation. For example, when driver assistance systems of a highly automated vehicle fail, the driver must take control to avoid an accident. A suitable level of human driver reliability is required in exactly that moment to handle a specific take-over situation. Human driver reliability may be affected by different take-over scenarios. It should be noted that continuous human operation could be also considered using similar approaches. From [5], it can be concluded that employing one common take-over request (TOR) time for all drivers and critical takeover situations is inappropriate.