This work presents an extension of the statistical jump model that incorporates uncertainty estimation in cluster assignments. Leveraging the similarities between statistical jump models and the fuzzy c-means framework, our fuzzy jump model sequentially estimates time-varying state probabilities. Our approach offers high flexibility, enabling clustering of mixed-type data. We apply it to the identification of co-orbital dynamics in the three-body problem, a novel application within the machine learning framework, yet highly relevant for understanding asteroid behavior and designing trajectories for interplanetary missions.