用模糊编码解码提升脉冲强化学习的自动驾驶决策能力
Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving
- 引入可训练模糊隶属函数生成丰富脉冲表示
- 在HighwayEnv上显著提升决策准确率，缩小脉冲与传统网络差距
- 适合追求高效实时推理的脉冲神经网络应用
本文提出一种端到端的模糊编码-解码架构，用于增强自动驾驶中基于视觉的多模态深度脉冲Q网络性能。该方法解决脉冲强化学习的两大核心问题：密集视觉输入转为稀疏脉冲信号导致的信息损失，以及脉冲值函数表达能力有限带来的弱判别性Q值估计。编码器通过可训练的模糊隶属函数生成具有表现力的群体脉冲表示，解码器则采用轻量级神经网络从脉冲输出重建连续Q值。在HighwayEnv基准测试中，所提架构显著提升决策准确性，有效缩小了脉冲网络与非脉冲网络之间的性能差距。结果表明该框架在高效、实时自动驾驶中具有巨大潜力。
原文摘要 · Abstract (English)
This paper develops an end-to-end fuzzy encoder-decoder architecture for enhancing vision-based multi-modal deep spiking Q-networks in autonomous driving. The method addresses two core limitations of spiking reinforcement learning: information loss stemming from the conversion of dense visual inputs into sparse spike trains, and the limited representational capacity of spike-based value functions, which often yields weakly discriminative Q-value estimates. The encoder introduces trainable fuzzy membership functions to generate expressive, population-based spike representations, and the decoder uses a lightweight neural decoder to reconstruct continuous Q-values from spiking outputs. Experiments on the HighwayEnv benchmark show that the proposed architecture substantially improves decision-making accuracy and closes the performance gap between spiking and non-spiking multi-modal Q-networks. The results highlight the potential of this framework for efficient and real-time autonomous driving with spiking neural networks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。