Dynamic AGV Conflict Detection Under Speed Uncertainty Considerations

Dynamic, accurate, and predictive conflict detection is crucial for ensuring collision-free movement and efficient route planning for Automated Guided Vehicles (AGVs). Timely alarms based on detection enable AGVs to efficiently plan collision-free routes. However, existing conflict detection methods typically do not consider the above elements simultaneously, either making assumptions that reduce the accuracy of applications, such as assuming constant vehicle speed (value of velocity), or focusing on real-time physical collisions but ignoring the future vehicle moving state. In this article, we propose a dynamic AGV conflict detection scheme with time windows to detect possible AGV conflicts timely. The proposed scheme fully considers the accuracy, dynamics, and predictability requirements of detection, which encompasses the following three components: preliminary conflict detection, potential motion trajectory generation, and conflict detection and alarm. In particular, for conflict detection and alarm where potential conflicts trigger corresponding alarm reminders, we have observed that the AGV conflict occurrence conditions within a specific time window can be mathematically expressed as a binary quadratic inequality, then conflict alarms between two AGVs can be efficiently calculated. Our proposed scheme could help dynamically and accurately detect potential AGV conflicts within the planned time window, and the speed fluctuation of the AGV is also fully considered. Experiment results on several sets of simulation scenarios prove the applicability and effectiveness of our scheme.