HiRAD improves large-scale warehouse AGV routing speed and efficiency
HiRAD: A Flexible Large-Scale AGV Routing System
RoboticsArtificial Intelligence
Summary
Coordinating many warehouse robots to move goods quickly is very hard for computers because the problem gets complicated as more robots are added. The authors propose HiRAD, a new system that breaks down the robot movement decisions into simpler steps and uses clever methods to make real-time routing faster and more efficient. Their approach reduces delays by up to 63% and runs much faster than existing methods while working in continuous, real-world robot movement settings. This makes managing large fleets of warehouse robots easier and quicker.
What this means in practice
- •For warehouse robotics teams: Deploy large fleets of warehouse robots with faster routing decisions that reduce delivery time and improve throughput.
- •For industrial automation engineers: Integrate real-time, continuous-control routing algorithms into AGV control software to lower computational delays and scale fleet sizes.
Authors
Yunjie Huang, Ruizhong Wu, Mengxuan Zhang, Frodo Kin Sun Chan, Yan Nei Law, Lei Li
Abstract
Automatic Guided Vehicles (AGVs) substantially boost warehouse throughput, but routing large-scale AGV fleets remains challenging. Classical Multi-Agent Pathfinding solvers suffer from exploding combinatorial complexity and super-quadratic runtime, while relying on idealized grid or piecewise-linear motion models that mismatch real-world kinematics. Recent Reinforcement Learning (RL) solutions improve flexibility via decentralized agent policies but depend on discretized spatiotemporal representations, require millions of episodes to converge, and incur full-map observation at every step, which leads to large models, slow convergence, and high inference latency that violates real-time industrial control constraints. To address these bottlenecks, we propose HiRAD, a hierarchical RL framework for continuous-space AGV routing with real-time guarantees: (1) a step-level spatiotemporal representation that translates continuous motion into a differentiable RL problem, (2) a hierarchical strategy that splits heading choice from velocity control to reduce the action space, and (3) an asynchronous event-driven decision pipeline that lowers inference complexity from O(n^2) to O(n) and cuts per-step latency by as much as 71 percent. Across random graphs and two warehouse maps, HiRAD reduces makespan by 45 percent to 63 percent and shortens end-to-end runtime.