The field of autonomous systems and knowledge graphs is rapidly evolving, with a focus on improving the accuracy and reliability of predictive models and mapping technologies. Researchers are exploring innovative methods for testing and validating multimodal human trajectory prediction systems, which is crucial for the safety and reliability of autonomous vehicles and mobile robots. Additionally, there is a growing interest in developing knowledge graph-based frameworks for automated map conflation, educational knowledge graph construction, and prerequisite knowledge concept inference. These advancements have the potential to significantly impact various applications, including navigation, fleet management, and adaptive learning. Noteworthy papers in this area include:

• A study on metamorphic testing of multimodal human trajectory prediction systems, which introduces a systematic methodology for testing these systems without relying on ground-truth trajectories.
• The KRAFT framework, which provides a learning-based approach for automated map conflation, outperforming traditional methods in terms of accuracy and scalability.
• The ArgoTweak dataset, which enables self-updating HD maps through structured priors, reducing the sim2real gap and advancing scalable, self-improving mapping solutions.