Matthias Beggiato

A mathematical model for predicting lane changes using the steering wheel angle

INTRODUCTION Positive safety effects of advanced driver assistance systems can only become effective if drivers accept and use these systems. Early detection of drivers intention would allow for selective system activation and therefore reduce false alarms. METHOD This driving simulator study aims at exploring early predictors of lane changes. In total, 3111 lane changes of 51 participants on a simulated highway track were analyzed. RESULTS Results show that drivers stopped their engagement in a secondary task about 7s before crossing the lane, which indicates a first planning phase of the maneuver. Subsequently, drivers start moving toward the lane, marking a mean steering wheel angle of 2.5°. Steering wheel angle as a directly measurable vehicle parameter appears as a promising early predictor of a lane change. A mathematical model of the steering wheel angle is presented, which is supposed to contribute for predicting lane change maneuvers. PRACTICAL APPLICATIONS The mathematical model will be part of a further predictor of lane changes. This predictor can be a new advanced driver assistance system able to recognize a drivers intention. With this knowledge, other systems can be activated or deactivated so drivers get no annoying and exhausting alarm signals. This is one way how we can increase the acceptance of assistance systems.

Adaptive Fuzzy Pattern Classification for the Online Detection of Driver Lane Change Intention

Abstract In this paper we introduce a new fuzzy system using adaptive fuzzy pattern classification (AFPC) for data-based online evolvement. The fuzzy pattern concept represents an efficient tool for handling uncertainty in multi-dimensional data streams and combines powerful performance, flexibility and meaningful interpretability within one consistent framework. We outline AFPC for non-linear, multi-dimensional transition processes, namely, for the identification of lane change intention in car driving. While lane changes are rare, they are highly safety-relevant transition processes, showing high fuzziness and large individual and inter-individual variations (e.g., in lane change duration). The method employs a combined knowledge- and data-based approach, and the underlying fuzzy potential membership function concept models expert knowledge, closely mirroring human cognition. The design of AFPC comprises (I) an initial training phase (off-line and supervised), which generates a meaningful start-classifier, (II) an online application phase, and finally (III) an evolvement phase (online and unsupervised). Here we consider parametric and structural adaptations and discuss prospects and future challenges. Furthermore, we present specific modeling results for such online data from a real driving study. Next-generation advanced driver assistance systems, as well as autonomously driven vehicles need to evolve, in terms of parameters and structure, based on online real-time data. AFPC presents an efficient tool for application in this area and others (e.g., medicine).

Use of adaptive cruise control functions on motorways and urban roads: Changes over time in an on-road study

The study aimed at investigating how drivers use Adaptive Cruise Control and its functions in distinct road environments and to verify if changes occur over time. Fifteen participants were invited to drive a vehicle equipped with a Stop & Go Adaptive Cruise Control system on nine occasions. The course remained the same for each test run and included roads on urban and motorway environments. Results showed significant effect of experience for ACC usage percentage, and selection of the shortest time headway value in the urban road environment. This indicates that getting to know a system is not a homogenous process, as mastering the use of all the systems functions can take differing lengths of time in distinct road environments. Results can be used not only for the development of the new generation of systems that integrate ACC functionalities but also for determining the length of training required to operate an ACC system.

Gap Acceptance and Time-To-Arrival Estimates as Basis for Informal Communication between Pedestrians and Vehicles

Informal communication plays a crucial role for negotiation processes in transport and thus, needs to be implemented in automated vehicles. Slowing down to encourage pedestrians to cross is one example of informal communication. To implement naturally-looking automated slowdown, a first step is to examine expected moments of braking from a pedestrians perspective. Gap Acceptance and Time-To-Arrival (TTA) estimates can provide these timings. The present experimental study assessed the effects of vehicle size, speed and participants age on expected braking initiation. Pre-recorded real-world videos of approaching cars (truck/smart) with various speed (10 to 40 km/h) on a parking area were presented to 42 participants from 18 to 75 years. Results showed more risky estimations/decisions with increasing speed. Older participants showed more conservative gap acceptance. Vehicle size only influenced TTA estimations (size-arrival-effect) but not gap acceptance. Thus, applying one simple time gap value does not fit human/pedestrians perception and expectations.

Lane Change Prediction: From Driver Characteristics, Manoeuvre Types and Glance Behaviour to a Real-Time Prediction Algorithm

Lane change manoeuvres pose high demands on the driver. Driver intent information is supposed to provide lane change assistance specifically when required, thus increasing acceptance and traffic safety. Based on an on-road study including 60 participants, the I-FAS investigated lane change behaviour at different levels of analysis. The present chapter shows the analysis of lane change predictors on the behavioural, strategic, manoeuvring and control level. Considering driver characteristics on the strategic/behaviour level, familiarity with the route resulted as the most important predictor for the number of lane changes performed per trip. Analyses at the manoeuvring level showed that lane change manoeuvres need to be further subdivided into subtypes with different requirements for prediction. Driver behaviour – especially automated glance behaviour at the control level – differed considerably between e.g. lane changes due to a slower vehicle ahead and lane changes on an added lane. Mirror glance patterns for specific lane change types resulted as promising and quite stable intention predictors, even before the activation of the turn signal. However, the interpretation of glances as indicator for lane change intention is vague without the integration of information about the driving situation. Therefore, a realtime lane change prediction algorithm was developed integrating driver behaviour, vehicle parameters as well as data from the vehicles’ surroundings in a Bayesian Network.

Driving comfort, enjoyment and acceptance of automated driving – effects of drivers’ age and driving style familiarity

Abstract Automated driving has the potential to improve the safety and efficiency of future traffic and to extend elderly peoples’ driving life, provided it is perceived as comfortable and joyful and is accepted by drivers. Driving comfort could be enhanced by familiar automated driving styles based on drivers’ manual driving styles. In a two-stage driving simulator study, effects of driving automation and driving style familiarity on driving comfort, enjoyment and system acceptance were examined. Twenty younger and 20 older drivers performed a manual and four automated drives of different driving style familiarity. Acceptance, comfort and enjoyment were assessed after driving with standardised questionnaires, discomfort during driving via handset control. Automation increased both age groups’ comfort, but decreased younger drivers’ enjoyment. Younger drivers showed higher comfort, enjoyment and acceptance with familiar automated driving styles, whereas older drivers preferred unfamiliar, automated driving styles tending to be faster than their age-affected manual driving styles. Practitioner Summary: Automated driving needs to be comfortable and enjoyable to be accepted by drivers, which could be enhanced by driving style individualisation. This approach was evaluated in a two-stage driving simulator study for different age groups. Younger drivers preferred familiar driving styles, whereas older drivers preferred driving styles unaffected by age.

The Right Moment for Braking as Informal Communication Signal Between Automated Vehicles and Pedestrians in Crossing Situations

Automated vehicles must be able to handle situations requiring cooperation with other road users in mixed traffic scenarios. Braking is an important informal vehicle signal for cooperation, indicating e.g. the intention to let a pedestrian cross. The present experimental study assessed the effects of daytime, approaching vehicle speed and participant’s age on the last moment of “gentle” braking initiation from a pedestrian’s perspective. Using a Labview-based simulation environment, pre-recorded real videos of approaching cars on a parking area were presented to 42 participants. Independent within-subject-variables were daytime (midday/dusk) and approaching vehicle speed ranging from 10 to 40 km/h in steps of 5 km/h. The between-subjects-factor consisted of two age groups ranging from 20 to 30 years and 50+ years. Results of the mixed ANOVA showed a main effect of daytime, vehicle speed and age as well as an interaction between age and vehicle speed. More conservative time gaps were chosen in the dusk condition. In line with previous studies, accepted time gaps decreased with increasing vehicle speed, indicating more risky crossing decisions. Older participants took more conservative decisions, especially on lower speed levels. Results show that applying one simple time gap for automated cooperative braking does not fit human/pedestrians perception and expectations. A function considering vehicle speed and daylight condition is recommended instead.

Der Einfluss von Fahrermerkmalen auf den erlebten Fahrkomfort im hochautomatisierten Fahren

Zusammenfassung Die Veränderung der Fahrerrolle im hochautomatisierten Fahren vom Akteur zum „Passagier am Fahrersitz“ wirft neue Fragen auf nach dem erlebten Fahrkomfort in dieser veränderten Situation. In einer kombinierten Fahrsimulator- und Realfahrstudie wurde der Einfluss von Fahrermerkmalen auf den wahrgenommenen Fahrkomfort, die Akzeptanz und den Fahrspaß im hochautomatisierten Fahren untersucht.

Using Smartbands, Pupillometry and Body Motion to Detect Discomfort in Automated Driving

As technological advances lead to rapid progress in driving automation, human-machine interaction (HMI) issues such as comfort in automated driving gain increasing attention. The research project KomfoPilot at Chemnitz University of Technology aims to assess discomfort in automated driving using physiological parameters from commercially available smartbands, pupillometry and body motion. Detected discomfort should subsequently be used to adapt driving parameters as well as information presentation and prevent potentially safety-critical take-over situations. In an empirical driving simulator study, 40 participants from 25 years to 84 years old experienced two highly automated drives with three potentially critical and discomfort-inducing approaching situations in each trip. The ego car drove in a highly automated mode at 100 km/h and approached a truck driving ahead with a constant speed of 80 km/h. Automated braking started very late at a distance of 9 m, reaching a minimum of 4.2 m. Perceived discomfort was assessed continuously using a handset control. Physiological parameters were measured by the smartband Microsoft Band 2 and included heart rate (HR), heart rate variability (HRV) and skin conductance level (SCL). Eye tracking glasses recorded pupil diameter and eye blink frequency; body motion was captured by a motion tracking system and a seat pressure mat. Trends of all parameters were analyzed 10 s before, during and 10 s after reported discomfort to check for overall parameter relevance, direction and strength of effects; timings of increase/decrease; variability as well as filtering, standardization and artifact removal strategies to increase the signal-to-noise ratio. Results showed a reduced eye blink rate during discomfort as well as pupil dilation, also after correcting for ambient light influence. Contrary to expectations, HR decreased significantly during discomfort periods, whereas HRV diminished as expected. No effects could be observed for SCL. Body motion showed the expected pushback movement during the close approach situation. Overall, besides SCL, all other parameters showed changes associated with discomfort indicated by the handset control. The results serve as a basis for designing and configuring a real-time discomfort detection algorithm that will be implemented in the driving simulator and validated in subsequent studies.