Real-Time Lane Change Risk Estimation Using Extended Lane Change Risk Index (ELCRI) and Fault Tree Analysis

Accidents during lane changes are increasingly becoming a problem due to various human based and environment-based factors. Reckless driving, fatigue, bad weather are just some of these factors. This research introduces an innovative algorithm for estimating crash risk during lane changes, including the Extended Lane Change Risk Index (ELCRI). Unlike existing studies and algorithms that mainly address rear-end collisions, this algorithm incorporates exposure time risk and anticipated crash severity risk using fault tree analysis (FTA). The risks are merged to find the ELCRI and used in real time applications for lane change assist to predict if lane change is safe or not. The algorithm defines zones of interest within the current and target lanes, monitored by sensors attached to the vehicle. These sensors dynamically detect relevant objects based on their trajectories, continuously and dynamically calculating the ELCRI to assess collision risk during lane changes. Additionally, adherence to R79 regulations and usage of safety distances enhance the algorithms handling of uncertainties in the system and environment. Also, a separate threshold for ELCRI has been used in each zone to allow for modularity in determining if a lane change is safe or not for different zones. The inclusion of the above additions to the algorithm serves as an extension to already existing similar risk index concepts, therefore the term “Extended” LCRI has been used. The algorithm has been tested on several simulated scenarios. A comparison of the simulations has been done with real-world data to understand the strengths and limitations of the algorithm. While it was found that very high relative velocities between the object and self-vehicle might pose some difficulties for ELCRI accuracy, its performance in most day-to-day dynamic traffic situations leads to improved lane change safety.