Q-SpiRL: Quantum Spiking Reinforcement Learning for Adaptive Robot Navigation

2026-05-20

AI Summary

This work addresses the challenges of reliability, efficiency, and motion smoothness in robot navigation within dynamic environments by proposing Q-SpiRL, a novel framework that integrates spiking neural networks with variational quantum feature maps to construct a quantum-enhanced reinforcement learning agent. The approach leverages a synergistic combination of a quantum-enhanced multilayer perceptron (QMLP) and a quantum spiking neural network (QSNN) to jointly perform spatiotemporal processing and quantum feature encoding, enabling end-to-end policy learning within a unified training and evaluation pipeline deployed on real IBM quantum hardware. Experimental results demonstrate that QSNN achieves a 99% navigation success rate in complex 40×40 environments while maintaining high path efficiency and motion smoothness, thereby validating the feasibility and superiority of the quantum–spiking hybrid architecture on actual quantum devices.

Abstract

Adaptive robot navigation in dynamic environments requires policies that can reach the target reliably while producing efficient and stable trajectories. This paper presents Q-SpiRL, a quantum spiking reinforcement learning framework for obstacle-aware robot navigation. The framework develops and evaluates five agent families: tabular Q-learning, classical MLP, classical SNN, quantum-enhanced MLP (QMLP), and quantum-enhanced spiking neural network (QSNN). While all models are implemented under a unified training and evaluation pipeline, the QSNN is the central architecture of interest, as it combines spike-based temporal processing with variational quantum feature transformation. Experiments are conducted across three grid-world environments of increasing size, namely 20x20, 30x30, and 40x40, with both static and dynamic obstacles. Performance is assessed using success rate, success-weighted path length, path length, and turn rate under deterministic inference. Results show that QSNN achieves the strongest overall trade-off between task completion, trajectory efficiency, and motion smoothness, reaching up to 99% success rate while maintaining high path efficiency in the most challenging setting. Execution on IBM quantum hardware further demonstrates the feasibility of deploying the proposed hybrid policy under real-device conditions.

Problem

• adaptive robot navigation
• dynamic environments
• obstacle-aware navigation
• trajectory efficiency
• motion smoothness

Innovation

• Quantum Spiking Neural Network
• Reinforcement Learning
• Robot Navigation
• Variational Quantum Feature Mapping
• Hybrid Quantum-Classical Architecture