TU Chemnitz Forschung Projekte Hybrid Societies: Humans Interacting with Embodied Technologies

Hybrid Societies: Humans Interacting with Embodied Technologies

Hybrid Societies: Humans Interacting with Embodied Technologies

Detection of Implicit Driving Cues as the Basis for a Proactive Driving Style of Highly Automated Cars
DFG, German Research Foundation (416228727 – SFB 1410)
Research Group Cognitive & Engineering Psychology
Januar, 2020 bis Dezember, 2023

Motivation und Zielstellung

Problem definition and aim

Manually driven vehicles and both highly automated as well as self-driving cars will share the road in the near future. In the driving context, monitoring and communication of intentions is essential for a smooth, efficient, and safe interaction with other traffic participants. Besides explicit cues for intention communication such as the turn signal or the horn, implicit cues such as vehicle movements (acceleration, deceleration, swerving) or wheel positions/angles play an important role. The technical implementation and interpretation of implicit cues are challenging issues for highly automated vehicles in shared environments with humans: On the one hand, a current highly automated vehicle is unable to “see” and decipher cues that manual drivers send to other road users. On the other hand, a highly automated vehicle does not necessarily provide other road users with human-like cues and accordingly, it is more complicated for manual drivers to anticipate the future driving maneuvers of this car. For example, a highly automated car would not deviate from its straight trajectory before a lane change and only brake as soon as it encounters an obstacle. Implicit intent communication is considered essential to design a proactive driving style for highly automated cars that is perceived as safe, smooth, cooperative, and acceptable by the driver and all other traffic participants. Driving styles that are proactive (i.e., anticipating
a lane change maneuver) and cooperative (i.e., releasing the accelerator pedal to let another vehicle merge into the own lane) build on a sound understanding and anticipation of the intentions of all interaction partners. To reach this goal, it is necessary to investigate implicit driving cues in various situations with these main research questions:

  • Which cues can be detected in which driving situations to communicate intentions?
  • Which cues are relevant for a correct anticipation of driving maneuvers?
  • In which situations and how can cues be used to establish communication between highly automated vehicles and other road users?

These research questions are addressed by driving simulator studies, video-based lab experiments as well as on-road studies.



The research questions are addressed by driving simulator studies as well as on-road studies. Step 1, an analysis of existing datasets with regard to situations that require the detection of implicit driving cues from vehicles is done. Previous analyses in these projects have not focused on implicit interaction between drivers and vehicles, but the material is expected to hold information on such situations (e.g., lane change maneuvres of other drivers). Thus, the material will be reanalysed with this new focus. Step 2, a naturalistic driving study is conducted with the focus on ambiguous situations. The focus of the study is a viewing of traffic situations, in which implicit communication takes place. Step 3, to find out which implicit cues are relevant for drivers to correctly anticipate behaviour of other cars a first simulator study is conducted. Step 4, the subsequent driving simulator study focuses on how the most relevant cues for each scenario could be used to show a highly automated car’s intentions to other road users, and how the cues would be accepted by these road users. After the 4 steps, a sound understanding of implicit cues is developed.


Beiträge in Konferenzband

Felbel, K., Dettmann, A., Heinz, A. & Bullinger, A.C. (2022). Manoeuvre design in automated driving: investigation of on-ramp situations under the variation of safety distances and traffic flow. In D. de Waard, S.H. Fairclough, K.A. Brookhuis, D. Manzey, L. Onnasch, A. Naumann, R. Wiczorek, F. Di Nocera, S. Röttger & A. Toffetti (Eds.), Proceedings of the Human Factors and Ergonomics Society Europe Chapter 2022 Annual Conference: Enhancing Safety Critical Performance (pp. 39-50). Human Factors and Ergonomics Society. https://www.hfes-europe.org/largefiles/proceedingshfeseurope2022.pdf

Felbel, K., Dettmann, A. & Bullinger, A.C. (2022). Analysis of eye gaze given different automated driving styles in an urban environment. IEEE 9th International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications (CIVEMSA) (pp. 1-5). https://doi.org/10.1109/CIVEMSA53371.2022.9853647

Felbel, K., Dettmann, A., & Bullinger, A.C. (2023). The Effect of Implicit Cues in Lane Change Situations on Driving Discomfort. In Krömker, H. (Ed.), HCI in Mobility, Transport, and Automotive Systems. HCI International 2023. Lecture Notes in Computer Science (Vol. 14049, pp.32–41). Springer International Publishing. https://doi.org/10.1007/978-3-031-35908-8_3

Hensch, A.-C., Felbel, K., Beggiato, M., Dettmann, A., Krems, J. F., & Bullinger, A. C. (in press). Implicit driving cues for coordinating actions when sharing spaces. In B. Meyer, U. Thomas, & O. Kanoun (Eds.), Hybrid Societies - Humans Interacting with Embodied Technologies (Vol. 1). Springer.

Dettmann, A., Berkemeier, A., Felbel, K., & Bullinger, A. C. (2024). Investigation of Implicit and Contextual Cues for the Facilitation of Cooperative Automated Driving: A Qualitative Analysis. In M. Carfagni, R. Furferi, P. Di Stefano, L. Governi, & F. Gherardini (Eds.), Lecture Notes in Mechanical Engineering. Design Tools and Methods in Industrial Engineering III (pp. 319–326). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-58094-9_35


Dettmann, A., Hartwich, F., Roßner, P., Beggiato, M., Felbel, K., Krems, J.F., & Bullinger, A.C. (2021). Comfort or Not? Automated Driving Style and User Characteristics Causing Human Discomfort in Automated Driving. International Journal of Human–Computer Interaction, 37(4), 331-339. https://doi.org/10.1080/10447318.2020.1860518