A Neuromorphic Reinforcement Learning Framework for Efficient Pathfinding in Robotic Mobile Fulfillment Systems

2026-06-18

AI Summary

This work addresses the high computational complexity of conventional path planning and the difficulty of deploying reinforcement learning policies on resource-constrained hardware with low power consumption in robotic mobile fulfillment systems. To this end, the authors propose SDQN-RMFS, an end-to-end framework that employs a collision-tolerant training strategy to generate dense trajectories for efficiently training artificial neural networks (ANNs). The approach further introduces an output distribution matching mechanism, combined with hard-label knowledge distillation, to convert the trained ANN into a spiking neural network (SNN) capable of event-driven sparse computation. Experimental results demonstrate that, compared to a high-performance GPU baseline, the proposed method achieves up to 11,281× energy savings and nearly 2× lower latency on neuromorphic hardware while maintaining comparable decision-making performance.

Abstract

Dynamic environmental changes, confined workspaces, and stringent real-time constraints make pathfinding in Robotic Mobile Fulfillment Systems (RMFS) a challenging problem for conventional search- and rule-based methods, which typically suffer from high computational complexity and long decision latency. While reinforcement learning (RL) has emerged as a powerful alternative, deploying learned policies with extreme energy efficiency on resource-constrained hardware remains an open challenge. We present SDQN-RMFS, an end-to-end framework that achieves high-fidelity deployment of an RL-trained policy from a full-precision artificial neural network (ANN) through to a neuromorphic chip. By computing only when triggered by sparse events, this framework unlocks ultra-low-power RMFS pathfinding. Our full-stack pipeline operates as follows: an ANN policy is first efficiently trained via a collision-allowing strategy to densify informative trajectories, and then converted into a spiking neural network (SNN) via a hard-label knowledge distillation approach. This effectively addresses the output distribution mismatch, preserving policy capability across the ANN-to-SNN pipeline while substantially reducing inference latency. Hardware experiments demonstrate up to 11,281$\times$ energy savings and a nearly two-fold reduction in latency compared to a high-performance GPU baseline, while maintaining decision quality on par with the original trained policy. These results establish physical neuromorphic inference as a practical and energy-sustainable pathway for large-scale RMFS operations.

Problem

• Robotic Mobile Fulfillment Systems
• pathfinding
• reinforcement learning
• energy efficiency
• real-time constraints

Innovation

• Neuromorphic Computing
• Spiking Neural Network
• Reinforcement Learning
• Energy-Efficient AI
• Robotic Mobile Fulfillment Systems