The field of autonomous systems is witnessing significant advancements in navigation and decision-making capabilities. Researchers are focusing on developing innovative methods to improve the efficiency, safety, and adaptability of autonomous vehicles and robots in complex and dynamic environments. One of the key directions is the integration of probabilistic approaches, such as Bayesian networks and probabilistic roadmaps, to enhance motion planning and uncertainty quantification. Another important area of research is the development of frameworks that combine machine learning and classical planning techniques to leverage the benefits of both learning-based adaptability and deterministic reliability. Noteworthy papers in this regard include the proposal of DeMo++, a framework that decouples motion estimation into holistic motion intentions and fine spatiotemporal states, and the introduction of ProbHMI, which utilizes invertible networks to parameterize poses in a disentangled latent space for probabilistic dynamics modeling. Additionally, the development ofGoal-based Trajectory Prediction and Delving into Mapping Uncertainty for Mapless Trajectory Prediction demonstrate the importance of considering goal selection and mapping uncertainty in trajectory prediction tasks.