Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving
On the map: End-to-end autonomous driving → End-to-end system architecture
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in End-to-end system architecture, one of 9 directions in End-to-end autonomous driving. Builds on 18 of its 28 references that are in the map. First posted on arXiv 6 Apr 2026.
Builds on
18 of 28 references.
Closest ancestors · 1
Same direction, newest first
Other references · 17
- 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
- 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
- 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
- 2020Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3Dcited by 1,040
- 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 769
- 2016Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learningcited by 351
- 2022Spikformer: When Spiking Neural Network Meets Transformercited by 263
- 2022Look Closer: Bridging Egocentric and Third-Person Views with Transformers for Robotic Manipulationcited by 49
- 2020Deep Reinforcement Learning with Population-Coded Spiking Neural Network for Continuous Controlcited by 44
- 2021Human-Level Control through Directly-Trained Deep Spiking Q-Networkscited by 23
- 2020Strategy and Benchmark for Converting Deep Q-Networks to Event-Driven Spiking Neural Networkscited by 20
- 2024High-Performance Temporal Reversible Spiking Neural Networks with O(L) Training Memory and O(1) Inference Costcited by 14
5 more
- 2021Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learningcited by 13
- 2022Solving the Spike Feature Information Vanishing Problem in Spiking Deep Q Network with Potential Based Normalizationcited by 9
- 2023Combining Reconstruction and Contrastive Methods for Multimodal Representations in RLcited by 9
- 2025Improving Performance of Spike-based Deep Q-Learning using Ternary Neuronscited by 3
- 2025Population-Coded Spiking Neural Networks for High-Dimensional Robotic Controlcited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2024Autonomous Driving with Spiking Neural Networks
- 2024An Examination of Offline-Trained Encoders in Vision-Based Deep Reinforcement Learning for Autonomous Driving
- 2025Spiking Decision Transformers: Local Plasticity, Phase-Coding, and Dendritic Routing for Low-Power Sequence Control
- 2026SpikeVLA: Vision-Language-Action Models with Spiking Neural Networks
- 2023Think Twice before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving
- 2024Self-Driving Car Racing: Application of Deep Reinforcement Learning
- 2022A Low Latency Adaptive Coding Spiking Framework for Deep Reinforcement Learning
- 2024Compressing Deep Reinforcement Learning Networks with a Dynamic Structured Pruning Method for Autonomous Driving