Towards A Human-centric Design Solution for Automated Systems to Enhance Driver's Comfort and Acceptance
Authors:
- 7 October 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
Vehicle automation (even SAE level 1 automated systems) can substantially increase traffic safety, reduce road fatalities/injuries, and improve traffic flow and efficiency. Despite these benefits of automated systems, their acceptance and usage are low among drivers. The current state-of-the-art automated systems such as Adaptive Cruise Control and Lane Keeping Assist follow pre-defined comfort and safety margins for controlling the longitudinal and lateral motion of the vehicle, which are not adequate to distinguish between similar-looking events. In contrast, the driver can recognize and anticipate such upcoming situations and accordingly adapts his behavior. The foremost requirement for enhancing drivers' comfort, trust, and acceptance is to understand situations where automated systems behave differently from human drivers and, subsequently, determine how such behavioral differences can be resolved safely and comfortably. This paper addresses this gap by studying the behavior of Adaptive Cruise Control and Lane Keeping Assist in contrast with the human driver in a real-life highway environment. A four-step design approach is presented for Adaptive Cruise Control and Lane Keeping Assist based on the identified events of interest, facilitating anticipative behavior for them similar to human drivers. The applicability of the design approach is demonstrated using a virtual scenario created using Simcenter Prescan and Matlab Simulink. The scenario showcases the dynamic lane positioning behavior of modified Lane Keeping Assist that can adapt the vehicle lane position within a 1.2% of the human driver in the presence of vehicles in the adjacent lanes.Keywords
This publication has 15 references indexed in Scilit:
- Adaptive driver modelling in ADAS to improve user acceptance: A study using naturalistic dataSafety Science, 2019
- Driver profiling – Data-based identification of driver behavior dimensions and affecting driver characteristics for multi-agent traffic simulationTransportation Research Part F: Traffic Psychology and Behaviour, 2019
- Typical-driving-style-oriented Personalized Adaptive Cruise Control design based on human driving dataTransportation Research Part C: Emerging Technologies, 2019
- Human–machine shared control for vehicle lane keeping systems: a Lyapunov‐based approachIET Intelligent Transport Systems, 2018
- Enhancing Trust in Autonomous Vehicles through Intelligent User Interfaces That Mimic Human BehaviorMultimodal Technologies and Interaction, 2018
- Cognitive Driver Behavior Modeling: Influence of Personality and Driver Characteristics on Driver Behavior2018
- Driving comfort, enjoyment and acceptance of automated driving – effects of drivers’ age and driving style familiarityErgonomics, 2018
- Do You Want Your Autonomous Car To Drive Like You?2017
- Investigation of Driver Lane Keeping Behavior in Normal Driving based on Naturalistic Driving Study DataSAE International Journal of Transportation Safety, 2016
- Empirical Longitudinal Driving Behavior in Authority Transitions between Adaptive Cruise Control and Manual DrivingTransportation Research Record: Journal of the Transportation Research Board, 2015