CLACD: A complete LAne-Changing decision modeling framework for the connected and traditional environments

This study develops a Complete LAne-Changing Decision (CLACD) modeling framework that explains both the mandatory and discretionary lane-changing behaviors, incorporates successful failed attempts, describes behaviors in traditional connected environments. The environment provides real-time valuable information about surrounding vehicles downstream situations (e.g., congestion ahead) drivers cannot foresee. Such can be particularly useful for complex driving maneuvers like (DLC), which requires traffic speeds subsequent gaps available on adjacent lanes. DLC efforts appear to nascent, primarily because of: (a) novelty of (and consequent scarcity relevant data), (b) lack behaviorally sound model even (that is, without driver-aid messages). Moreover, existing models omit attempts by motorists are likely create disruptions have significant impact safety. To overcome these challenges, this (i.e., CLACD model) environment, is extended environment. An integrated approach employed behavior combining target lane selection using utility theory gap acceptance game approach. collect high-quality vehicle trajectory data CARRS-Q advanced simulator was used. (for environments) calibrated NGSIM data, models’ performances were rigorously assessed various performance indicators. Results reveal effectively capture observed decisions with high accuracy. compared two alternative described literature, revealing outperform alternatives. A sensitivity analysis suggests consistent trend models, agrees past research. Furthermore, shows realistic prediction flow patterns model. By incorporating into realism been significantly improved.