Innovative Interaction Approach in IMM Filtering for Vehicle Motion Models With Unequal States Dimension

Robust and adaptive vehicle state estimation tracking algorithms have become a very important part within the autonomous driving field. The family of interacting multiple model (IMM) filters has shown to provide effective accurate in systems whose behavior patterns change significantly over time. main reason for improved performance IMM compared single approaches is mode mixing, which constantly aligns different models. This paper proposes an innovative way when state-vectors models are size. proposed mixing approach consists two parts: firstly common states secondly weighting between original mixed based on probabilities. Results from artificial simulations real world measurement setups demonstrate validity approach. Compared previously suggested solutions, more general overall complexity step reduced, contribution presented paper.