Skip to main content

MEdiating between Driver and Intelligent Automated Transport systems on Our Roads

Periodic Reporting for period 1 - MEDIATOR (MEdiating between Driver and Intelligent Automated Transport systems on Our Roads)

Reporting period: 2019-05-01 to 2020-10-31

Vehicle automation has a substantial potential to improve road safety, since it reduces the influence of human fallibility. At the same time, vehicle automation is likely to introduce new risks, particularly during the transition phase to full automation when the task of the driver changes from an active to a more passive, supervisory role. This could result in reduced attention and situational awareness, and mode confusion, making the driver unfit to take over control when needed.

MEDIATOR aims to develop an intelligent ‘mediator’ support system, enabling safe, real-time switching between the human driver and automation. The Mediator system continuously and in real time monitors and weighs the information about the driving context, the driver state, as well as the automation status. By weighing these elements, the Mediator system will determine how and to what extent the human or the automation should be in control, and ensures safe, comfortable, real-time switching between the two.
During the first half of the project the MEDIATOR work concentrated on
- Elaboration of the general principles of the Mediator system and related functional requirements for three automation levels:
- Assisted driving: drivers are responsible but supported by the automation,
- Conditional automation: drivers can be out of the loop for a short time but must be standby to take back control when needed,
- High-level automation: drivers can be out of the loop for long periods of time and even fall asleep.
- Definition of the knowledge needed and available for substantiating decisions when and how to transfer control from driver to automation and vice versa.
- Exploration of the literature and dedicated experiments for defining degraded human performance and user-centred HMI.
- Development of a detailed design and work plan for building Mediator prototypes.
- First steps in building the actual system modules.

Whereas this list suggests work to take place serially, in practice much of the work is being done iteratively and in interaction. The next paragraphs highlight a few of the results of the work done so far, focusing on two of the main features of the Mediator system and on the development of a strategy for exploiting the MEDIATOR results once the project has finished.

Predicting drivers’ fitness and comfort
To intervene in time, the Mediator system must be able to predict that a driver is likely to become unfit to drive or to feel uncomfortable before it affects driving performance. It must also predict when a currently unfit or uncomfortable driver can be fit again to take over when the automation becomes unfit. Predicting the near future situation means that fitness (fatigue and distraction) and comfort cannot be detected directly, e.g. from drivers steering behaviour, as most currently available applications do. Hence, algorithms to detect early-stage driver fatigue and distraction irrespective of driver control input have been developed. This step was based on the literature, data from an on-road study on driver fatigue in manual and low-level automation vehicles and on existing datasets about distracted driving. For predicting when a driver would become uncomfortable, the work resulted in a description of typical uncomfortable driving situations, as well as initial research into possible methods for detecting upcoming discomfort in real time and personalizing comfort predictions. Future work will include the elaboration and implementation of algorithms that can estimate the time to driver (un)fitness and discomfort for each of the three automation levels. First steps to a similar approach for the estimation and real time prediction of the status of the automation, i.e. time to automation (un)fitness, were set and ways to collect required information about the driving context, e.g. weather and traffic, were defined.

Prevention and intervention
The human-machine interface (HMI) of the Mediator system will focus on both preventing unsafe and uncomfortable driving situations to arise and intervening when needed. For prevention, an analysis of the literature resulted in an overview of possible HMI designs that can prevent task-induced fatigue and distraction, the main challenges of assisted driving and conditional automation. This led to several options for implementing an engaging stimulus-response task. A separate literature study and a series of online experiments focused on preventing the main challenges of conditional and high-level automation like mode confusion and overreliance. Providing continuous and peripherally visible information on automation reliability and remaining time in current driving mode proved to be a viable strategy and will be further elaborated. Research into HMI interventions when having detected upcoming unsafe or uncomfortable driving situations focussed on takeovers and corrective actions. With user acceptability in mind, a takeover interface was tested that allows a driver to indicate his preferred automation mode without compromising safety. Other experiments focused at avoiding mode confusion and regaining situational awareness when switching from automated to manual driving and vice versa. For corrective actions, a literature overview provided insight into ways to increase driver fitness up to the required level.

Exploitation strategy
To optimise the opportunities for commercial implementation of the Mediator system, a preliminary exploitation plan was developed. Based on the definition of the main potentially exploitable results (hardware, software, knowledge) and a related SWOT analysis, each of the project partners identified its own opportunities to contribute to the exploitation of the results. As elements of the Mediator system are expected also to be of value for other transport modes, a similar preliminary exploitation plan was prepared for these other modes. Both preliminary exploitation plans will be elaborated and finalised at the end of the project.
Work so far already substantially contributed to the intended progress beyond the state of the art by extending knowledge on predicting degraded performance by driver fatigue and distraction, by explicitly defining the role of automation status in elaborating the concept of the Mediator system, and by taking user acceptance as the central element of the HMI design.

Until the end of the project, the scientific basis for the decisions of the Mediator system will be elaborated for specific use cases and applied in laboratory and in-vehicle prototypes. The prototypes will be evaluated by computer simulation, in driving simulators and on-road. Guidelines for measuring degraded human performance, protocols for low-cost laboratory system testing, and recommendations on legal and regulatory aspects will be developed to assist the automotive industry in further developing the Mediator system principles, and tailor it to their exact needs.

Progress has also been made towards the realisation of most of the expected potential impacts. The ultimate impact of a Mediator system will be on the number of road casualties. The size of this impact (and related societal impacts) will be estimated based on the effects on driving behaviour as assessed in the evaluation studies.
figure-2-visualisation-of-the-ten-use-cases.png
figure-3-schematic-overview-of-the-four-modules-of-the-mediator-system.png
figure-1-schematic-summary-of-the-functioning-of-the-mediator-system.png