Interaction-Aware Motion Prediction for Autonomous Driving: A Multiple Model Kalman Filtering Scheme

We consider the problem of predicting motion vehicles in surrounding an autonomous car, for improved planning lane-based driving scenarios without inter-vehicle communication. First, we address single-vehicle estimation by designing a filtering scheme based on Interacting Multiple Model Kalman Filter equipped with novel intention-based models. Second, augment proposed optimization-based projection that enables generation non-colliding predictions. then extend approach to simultaneously estimating multiple using hierarchical priority list. The list is dynamically adapted real-time according sorting algorithm. Finally, evaluate simulations real-life vehicle data from Next Generation Simulation (NGSIM) dataset.