Toward Measurement of Situation Awareness in Autonomous Vehicles

With the development of level 3 AVs, drivers can now disengage from the driving task for extended periods of time. However, drivers are still responsible for the overall safety of their drive. Moreover, when drivers are not engaged in their monitoring task, they lose situational awareness. This leaves drivers vulnerable when they have to retake control from the AV. This research looks to advance the development of camera-based driver monitoring systems that measure situational awareness. In addition, this research examines the effect of adaptable warning systems on driver situational awareness and takeover performance. In this study, we use situational awareness as ground truth to compare adaptable warning systems that reengage drivers in the monitoring task. Camera-based driver monitoring systems that measure gaze behavior can be used to adapt warning systems. Twenty-four participants split into three groups were asked to drive for approximately 40 miles in a level 3 AV simulator while completing a visual-manual secondary task. During the drive, participants experienced four events in which they had to disengage from the secondary task and take back control from the AV. Two interface designs based on gaze behavior were compared to a baseline warning system. The Attentional Maintenance group was given an alert throughout the drive after a fixed amount of time in which their gaze was directed away from the road. The State-Contingent Takeover group was given an alert only before takeover events after a fixed amount of time in which their gaze was directed away from the road. Results show that attentional maintenance alerts can increase situational awareness and takeover response time during automation failure. Future research to increase situational awareness is discussed in terms of advancements in cognitive control and bilateral communication between the driver and the AV.

Proceedings of the 50th Hawaii International Conference on System Sciences (2017)

Low level of driver's situation awareness (SA) and high level of cognitive load are considered as reasons of vehicle accidents. Cognitive load is higher when driving abroad because of unfamiliarity with differences in international traffic rules or vehicle configurations. This paper aims to objectively assess the driver's SA when performing lane changing tasks under unfamiliar driving conditions. We conducted an experiment using a right-hand driving simulator and a left-hand simulated traffic scenario to collect the temporal information about SA such as time, location, and speed as well as lane changing errors. Overall, the participants show low SA in curved roads and road networks, but high SA in straight roads. The results state that speed does not affect the lane changing performance on straight roads and road networks but significantly affects the lane changing performance on curved roads. These findings can be used to design a SA system for driver-assistance in unfamiliar driving conditions considering drivers' cognitive load.

Human Factors and Ergonomics in Manufacturing & Service Industries, 2010

The rapid development of sensor and tracking technology enables deployment of new advanced driver assistance systems (ADAS) that support the driver not just on highways but in urban areas as well. Intersections particularly present very critical traffic scenarios where almost 35% of accidents occur, partially due to the present lack of in-depth research about human errors and their determinants. The first step in ergonomic design of ADAS is to identify the specific situations in which drivers require support.

This workshop will focus on the problem of occupant and vehicle situational awareness with respect to automated vehicles when the driver must take over control. It will explore the future of fully automated and mixed traffic situations where vehicles are assumed to be operating at level 3 or above. In this case, all critical driving functions will be handled by the vehicle with the possibility of transitions between manual and automated driving modes at any time. This creates a driver environment where, unlike manual driving, there is no direct intrinsic motivation for the driver to be aware of the traffic situation at all times. Therefore, it is highly likely that when such a transition occurs, the driver will not be able to transition either safely or within an appropriate period of time. This workshop will address this challenge by inviting experts and practitioners from the automotive and related domains to explore concepts and solutions to increase, maintain and transfer situational awareness in semi-automated vehicles.

2020

This workshop will focus on the problem of occupant and vehicle situational awareness with respect to automated vehicles when the driver must take over control. It will explore the future of fully automated and mixed traffic situations where vehicles are assumed to be operating at level 3 or above. In this case, all critical driving functions will be handled by the vehicle with the possibility of transitions between manual and automated driving modes at any time. This creates a driver environment where, unlike manual driving, there is no direct intrinsic motivation for the driver to be aware of the traffic situation at all times. Therefore, it is highly likely that when such a transition occurs, the driver will not be able to transition either safely or within an appropriate period of time. This workshop will address this challenge by inviting experts and practitioners from the automotive and related domains to explore concepts and solutions to increase, maintain and transfer situat...

International Journal of Advanced Computer Science and Applications, 2021

Driving in an unfamiliar traffic regulation using an unfamiliar vehicle configuration contributes to increase number of traffic accidents. In these circumstances, a driver needs to have what is referred to as ‘situation awareness’ (SA). SA is divided into (level 1) perception of environmental cues, (level 2) comprehension of the perceived cues in relation to the current situation and (level 3) projection of the status of the situation in the near future. On the other hand, augmented feedback (AF) is used to enhance the performance of a certain task. In Driving, AF can be provided to drivers via in-vehicle information systems. In this paper, we hypothesize that considering the SA levels when designing AF can reduce the driving errors and thus enhance road safety. To evaluate this hypothesis, we conducted a quantitative study to test the usability of a certain set of feedback and an empirical study using a driving simulator to test the effectiveness of that feedback in terms of improv...

Electronic Proceedings in Theoretical Computer Science

Semi-autonomous driving, as it is already available today and will eventually become even more accessible, implies the need for driver and automation system to reliably work together in order to ensure safe driving. A particular challenge in this endeavour are situations in which the vehicle's automation is no longer able to drive and is thus requesting the human to take over. In these situations the driver has to quickly build awareness for the traffic situation to be able to take over control and safely drive the car. Within this context we present a software and hardware framework to asses how aware the driver is about the situation and to provide human-centred assistance to help in building situation awareness. The framework is developed as a modular system within the Robot Operating System (ROS) with modules for sensing the environment and the driver state, modelling the driver's situation awareness, and for guiding the driver's attention using specialized Human Machine Interfaces (HMIs). A particular focus of this paper is on an Answer Set Programming (ASP) based approach for modelling and reasoning about the driver's interpretation and projection of the scene. This is based on scene data, as well as eye-tracking data reflecting the scene elements observed by the driver. We present the overall application and discuss the role of semantic reasoning and modelling cognitive functions based on logic programming in such applications. Furthermore we present the ASP approach for interpretation and projection of the driver's situation awareness and its integration within the overall system in the context of a real-world use-case in simulated as well as in real driving.

Sensors

Situation awareness (SA) is crucial for safe driving. It is all about perception, comprehension of current situations and projection of the future status. It is demanding for drivers to constantly maintain SA by checking for potential hazards while performing the primary driving tasks. As vehicles in the future will be equipped with more sensors, it is likely that an SA aiding system will present complex situational information to drivers. Although drivers have difficulty to process a variety of complex situational information due to limited cognitive capabilities and perceive the information differently depending upon their cognitive states, the well-known SA design principles by Endsley only provide general guidelines. The principles lack detailed guidelines for dealing with limited human cognitive capabilities. Cognitive capability is a mental capability including planning, complex idea comprehension, and learning from experience. A cognitive state can be regarded as a condition ...

Cars have had various forms of Driver Support Systems (DSS) for considerably longer than they have taken to have an overt driver interface or to otherwise assume the outward appearance of a 'computer'. Existing forms of DSS, such as power steering, engine management and anti-lock brakes, combined with a more general trend in ubiquitous computing and increased refinement, are isomorphic with future trends that seek to increase the amenity and comfort of driving. These shared objectives, it is argued, bring with them shared driver performance implications in regard to vehicle feedback and driver Situation Awareness (SA). Three experiments are reported in this paper that describe not only the effects on driver SA of manipulations of DSS (and vehicle feedback) but also illuminate issues concerned with SA measurement methods and contexts. The findings suggest that current instantiations of DSS contribute little towards a driver's SA and, in fact, show a generalized trend towards decreasing it. The efficacy of verbal protocol and probe recall SA measurement techniques is noted in terms of observing this effect.

Ergonomics, 2007

The objective of this study was to identify task and vehicle factors that may affect driver situation awareness (SA) and its relationship to performance, particularly in strategic (navigation) tasks. An experiment was conducted to assess the effects of in-vehicle navigation aids and reliability on driver SA and performance in a simulated navigation task. A total of 20 participants drove a virtual car and navigated a large virtual suburb. They were required to follow traffic signs and navigation directions from either a human aid via a mobile phone or an automated aid presented on a laptop. The navigation aids operated under three different levels of information reliability (100%, 80% and 60%). A control condition was used in which each aid presented a telemarketing survey and participants navigated using a map. Results revealed perfect navigation information generally improved driver SA and performance compared to unreliable navigation information and the control condition (task-irrelevant information). In-vehicle automation appears to mediate the relationship of driver SA to performance in terms of operational and strategic (navigation) behaviours. The findings of this work support consideration of driver SA in the design of future vehicle automation for navigation tasks.