Driver Assistance Systems – ADAS
The design of user interfaces and usage concepts for the vehicle differs considerably from the design for stationary or handheld devices in other contexts. In the automotive field, it is critical to define clear interfaces that are easy to understand and operate, in order to keep distraction of the driver at a minimum. Here, the usability, i.e. the actual degree to which a human-machine interface (HMI) works for a given task considering all relevant user-centric aspects, is of a prime importance.
The Automotive IUI group has long-standing experience in the design of such “usable” interfaces. In projects such as SIM-TD, in which comprehensive HMIs need to be designed, we apply standards such as the ADAS Code of Practice whenever possible to define the ideal values for elements such as icons, font sizes, colors etc. By conducting HMI user studies, developers and psychologists work together to test not only driving distraction, but also aspects such as efficiency and error-proneness of the UIs. They also evaluate the subjective usability / user satisfaction concerning the interface. Special experiments, e.g. icon tests, are performed to evaluate some concepts already during the design phase.
One of the most important metrics with respect to safety while driving are the mental or cognitive resources available to the driver. If these resources are depleted, reaction times increase, dangers are overlooked, and warnings are missed, even though the brain still applies a specific order. A high cognitive load also leads to stress and other physical reactions, and can even decrease steering performance. Contrary, a low resource load over a longer period of time can lead to loss of attention too.
Considering cognitive resources matters to us as researchers for two reasons:
- Each new assistance system (ADAS), apart from the expected driver support other improvements, also means an added cognitive load (depending on type and degree of interaction with the driver). Keeping an eye on these effects and quantifying them is an important task.
- Knowledge about the current cognitive load of the driver can be utilized to actively counteract an over- or under-load. This can be achieved by dynamically adjusting the behavior of all ADAS, in particular those with HMI.
Cognitive load cannot be measured directly. However, there are the following basic approaches to estimating it:
- Effects of high cognitive load can be measured. Indications of stress can be measured e.g. via biosensors (increased heart rate, skin conductance) or deterioration of driving performance (deviation from an ideal line as integrated in the driving simulator OpenDS)
- Predicting effects of interactions and stimuli on the cognitive load. Given the knowledge about the user’s behavior and the influences of the environment, based on statistical methods, the relative implications can be estimated. This assumes that the corresponding models are available.
The latter method is currently one of our main research topics, since it is much more suitable for realization within the driving car. A cognitive model of the driver, as well as a reference catalog of interaction costs, are to be integrated into our dialogue platform SiAM-dp in order to adjust the dialog flow to the user state as described above on the one hand, and on the other hand provide a function for automatic offline evaluation of dialog models.
Personalized driver assistence
Today, we are used to portable computers and mobile phones knowing and respecting our preferences, and behave appropriately and intelligently in each situation. In the vehicle, the possibilities for personalization are still only utilized to a small extent, even though they offer improved efficiency, increased comfort, support for older or impaired users, and even contribute to driving safety. Moreover, a car is often shared by multiple people (in particular in case of car rental or car sharing facilities), including passengers.
Some application scenarios related to personalization that the Automotive IUI group is currently working on or has been working on are:
- An obstacle warning ADAS that displays warnings depending on the cognitive load
- A user-adaptive parking assistant, which suggest different parking options based on certain user characteristics
- A version of the SIM-td system for color-blind and vision-impaired users
To implement personalization using adaptive systems, we offer two key components:
- a situation-adaptive dialog platform (see multimodal interaction) that can model user and context adaptive features
- the knowledge component KAPcom (Knowledge Management, Adaptation and Personalization Component), which can aggregate and maintain structured knowledge and sensors data, and share it between applications – similar to a middleware, but also across vehicle boundaries. It employs a reference ontology (Automotive Ontology) that has been steadily improved and extended in various projects.
Drivers are constantly making choices and decisions, concerning not only the driving itself but also the use of the growing number of devices available inside the car. At the same time, cars are becoming more “intelligent” and capable of performing relatively complex maneuvers in a semiautonomous manner. Examples of relatively simple maneuvers that many current cars can execute are adaptive cruise control (i.e., automatically adjusting the car’s speed to maintain a safe distance from the car in front), parallel parking and backing out of a parking space. More complex maneuvers that can be expected in the next few years include entering and leaving a highway, changing lanes, overtaking one or more cars and even navigating construction sites.
Complex maneuvers require drivers to make various choices, like deciding whether to tell the car to execute a specific maneuver (as opposed to doing it manually or omitting it entirely); deciding among two or more available variants of the same maneuver; deciding whether to intervene and assume control of the vehicle if something unexpected occurs during the execution of a maneuver by the car; or deciding which additional activities can be attempted during the execution of a maneuver, without compromising driving safety. Enabling drivers to make better decisions during driving is an important goal in the design of automotive interfaces. Much relevant research has been done in the past, but many types of driver decision remain highly problematic.