Multi-Agent Path Finding (MAPF), which focuses on finding collision-free paths for multiple robots, is crucial for applications ranging from aerial swarms to warehouse automation. Solving MAPF is NP-hard so learning-based approaches for MAPF have gained attention, particularly those leveraging deep neural networks. Nonetheless, despite the community's continued efforts, all learning-based MAPF planners still rely on decentralized planning due to variability in the number of agents and map sizes. We have developed the first centralized learning-based policy for MAPF problem called RAILGUN. RAILGUN is not an agent-based policy but a map-based policy. By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents. We collect trajectories from rule-based methods to train our model in a supervised way. In experiments, RAILGUN outperforms most baseline methods and demonstrates great zero-shot generalization capabilities on various tasks, maps and agent numbers that were not seen in the training dataset.

The military has for the first time fired a high-powered electromagnetic projectile from a ground artillery piece, raising Pentagon hopes for arming both the U.S. Army and Navy with advanced technological weaponry, Popular Mechanics reported Tuesday. The tungsten projectile, known as the Hypervelocity Projectile, can reach Mach 3 or over 2,300 miles per hour when fired, faster than any round in service. It potentially could even reach supersonic speeds. Already a historic piece of firepower when fired from an Army howitzer, the projectile was developed for an even more powerful, high-tech piece of Navy weaponry that previously existed only in science-fiction - the railgun. The railgun abandons traditional gunpowder-based firearms for what's essentially a large, overpowered electrical circuit.