Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving

Aref Ghoreishee; Abhishek Mishra; Lifeng Zhou; John Walsh; Anup Das; Nagarajan Kandasamy

cs.NEApr 6, 2026

Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving

Authors: Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou, John Walsh, Anup Das, Nagarajan Kandasamy

Organizations: Electrical and Computer Engineering Department, Drexel University, Philadelphia, USA

Abstract

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.

Figures & tables

Fig. 1 : The MM-DSQN architecture that uses a spiking cross-attention module to fuse BEV images and LiDAR representations for RL-based decision making (adapted from Ghoreishee et al. [ 4 ] ).

Panel of Figure 2 — Fig. 2 : Population-based encoder using $N$ triangular fuzzy membership functions and lightweight neural decoder that uses $|\mathcal{A}|$ populations of $M$ neurons.

Panel of Figure 3 — Fig. 3 : Comparison of non-spiking MM-DQN, rate-based encoding MM-DSQN, and the encoding–decoding MM-DSQN models in terms of average reward, speed, and crash frequency.

Fig. 4 : Learned fuzzy triangular membership functions showing how each pixel is mapped into three intensity-dependent membership channels.

Panel of Figure 5 — Fig. 5 : Effects of removing the decoder, removing both encoder and decoder, and replacing triangular membership functions with Gaussian ones. The triangular encoder with decoder achieves highest reward.

Reinforcement Learning

Reinforcement learning studies how agents learn sequential decisions from rewards and interaction, balancing exploration, performance, safety, and adaptation.

See all 1,717 papers

SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts
Oct 11, 2026Yiding Sun, Zijie Xu, Hongqiang Lin +73D Occupancy Prediction Multimodal Robustness
Peking University · Xi’an Jiaotong University · Zhejiang University +1
Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks
May 24, 2026Sambit Mohapatra, Senthil Yogamani, Heinrich Gotzig +1Lidar-Based 3D Object Detection Autonomous Driving Perception
Valeo, Germany · TU Ilmenau, Germany · Valeo, Ireland
Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks
Oct 6, 2026Zijie Xu, Bingrui Guo, Yiding Sun +3Deep Q-Learning Temporal-Difference Learning
Peking University Beijing, 100871, China

Oct 11, 2026J/K move · Enter open · S save

SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts

Yiding Sun, Zijie Xu, Hongqiang Lin, Jiajun Cao+6

Peking University · Xi’an Jiaotong University · Zhejiang University+1

3D Occupancy Prediction Multimodal Robustness Missing-Modality Learning Multimodal Sensor Fusion Spiking Neural Networks Mixture of Experts

Open paper AskPDF arXiv

Multimodal 3D occupancy prediction underpins safe autonomous driving through comprehensive scene understanding. However, existing methods have largely pursued higher accuracy through sophisticated fusion, leaving resilience to missing sensors underexplored. In this paper, we investigate spiking neural networks (SNNs) as a means of building more resilient multimodal perception. Still, the discrete nature of spiking neurons makes optimization challenging. To overcome this difficulty, SpikeOcc is introduced with two complementary components, a Spiking Mixture-of-Experts (SMoE) and Sensor Availability Learning (SAL). Specifically, SMoE organizes RGB, LiDAR, and joint fusion into specialized pathways, enabling full-width unimodal representations while retaining the original multimodal features via a bounded residual. Beyond sensor dropout, SAL employs a staged curriculum with explicit routing supervision, progressively improving robustness under severe sensing conditions. Remarkably, SAL also yields notable gains for conventional models, highlighting its broader potential for resilient multimodal learning. Extensive experiments demonstrate that SpikeOcc maintains competitive full-sensor accuracy while markedly raising the performance floor under sensor outages. SpikeOcc illustrates the promise of neuromorphic computing, pointing toward more reliable and energy-efficient autonomous driving.

Abstract

Reinforcement Learning

Explore similar work

SpikeOcc: Towards Resilient Multimodal 3D Occupancy Perception via Spiking Experts

Neuromorphic LiDAR-based Bird's Eye View Object Detection using Energy-efficient Spiking Neural Networks

Common-Mode Errors Limit Low-Timestep Deep Spiking Q-Networks