|
Abstract
|
27th International Technical Conference on the Enhanced Safety of Vehicles (ESV): Enhanced and Equitable Vehicle Safety for All: Toward the Next 50 Years
https://www-esv.nhtsa.dot.gov/Proceedings/27/27ESV-000263.pdf
Driver monitoring systems (DMS) can enhance Collision Avoidance Systems (CAS) in numerous ways, for instance by adjusting warnings or interventions when drivers are inattentive or in other ways disengaged or impaired. However, the driver interaction principles applied when using DMS to enhance CAS must be based on State-of-the-Art Human Factors research and have a clear focus on understanding driver needs and in what way assistance should be provided to be appreciated by the driver. Otherwise, one risks implementing interactions that either do not make sense or are perceived as disturbing, both of which degrade the CAS's safety potential.
Some of these interaction principles may not be fully intuitive unless your background is in behavioral psychology. For example, it may be surprising that DMS is best used to delay certain collision avoidance warnings rather than supply them earlier. It may also not be fully intuitive that DMS is best used for detection of generic degradations in the behavioral patterns that define normal driving rather than for diagnosis of specific impaired states.
To use a CAS properly, you need to interact with it regularly to learn what its outputs mean. However, current accident and mileage statistics suggest that driving conflicts where a CAS could save you from an unrecoverable error that otherwise would have resulted in a high severity crash are rare; maybe as infrequent as once in a decade or lifetime depending on how one does the calculation.
From a design perspective, CAS are therefore best approached as lifetime driving companions. You may only need them once, but they still need to be interacted with regularly to work as intended. Hence, the conversation between driver and CAS should adhere to the same principles as applied between humans. For example, if your colleague is busy, you only interrupt for good reason, and if you interrupt regularly, both of you must agree its relevant and the message must be clear (though not necessarily loud) so the other person quickly can decide whether to interrupt the current task.
In this paper, first a general framework and corresponding design approach for CAS is formulated based on accident statistics, driving mileage and CAS interaction frequency analysis. Next, three specific development principles for DMS enhanced CAS are described to illustrate what the outcome is when the framework and design approach are applied in practice. These include how DMS enhancement can be used to avoid "cry wolf" effects in CAS interactions, how DMS enhancement can be used to get CAS timing right for both distracted and aware drivers and finally, how DMS offers a more efficient way than specific state diagnosis when tackling driver impairment.
By explicitly describing these fundamental Human Factors development principles for DMS enhanced CAS to the traffic safety engineering community, one may avoid unnecessary development pitfalls that could counteract DMS enhanced CAS deployment.
DEFINING A GENERAL FRAMEWORK
To define a general framework for the interaction principles for CAS, one has to consider three key facts. The first is that even though CAS come in many forms, they all have one thing in common which is that to use them properly, the driver has to know how they work. So, as long as a driver uses the same car, s/he needs to interact with the CAS regularly to first learn what the systems do, and then remember what their outputs mean.
Second, for the CAS to achieve its intended safety benefit, drivers need to trust their inputs and actions (i.e., the warnings and interventions provided). If driver trust in, and understanding of, the CAS can be established in a good way, chances are good that drivers will cooperate with the CAS in the intended way and perceive the CAS actions as beneficial. However, if what the CAS does is perceived as unintelligible, pointless or perhaps even scary, it follows that drivers will neither use the CAS as intended by the designer, nor spend money on CAS features in their next car purchase.
Third, when one studies how often people end up in traffic accidents and compare that to the distances travelled or hours driven without crashing, one can conclude that driving conflicts where an CAS would save you from unrecoverable error are rare. For example, in 2020 the US average was 1,33 deaths in 100 million vehicle miles travelled [1]. At the same time, the average mileage per car was about 13 500 miles per year [2]. This means that there are about 5500 years of successful driving per fatal crash.
Of course, non-fatal crashes are far more common, but the key point here is that crashes, and particularly severe crashes, are very infrequent compared to all the driving we do; maybe as infrequent as once in a decade or lifetime depending on which crash type and outcome one is looking at. This means that the average driver exposure to critical situations where the safety margins are so small that severe injury or death is imminent if not handled correctly is very low.
Putting these three key facts together, it becomes clear that we cannot rely on exposure to a particular set of truly critical situations with potential high crash severity for drivers to understand and learn how a particular CAS works. This insight provides the foundation for the general framework proposed in this paper. This framework states that each CAS must be capable of providing a frequent enough driver interaction also outside of truly critical situations to provide a sustained, acceptable and trustworthy learning experience. The reason for this is that it's that experience which in turn secures an adequate driver response on those rare occasions when a truly critical situation occurs, and the CAS can provide a real safety benefit. This general framework forms the basis for the rest of the paper. |