John Walsh

Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou et al.

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.

Aref Ghoreishee, Abhishek Mishra, Lifeng Zhou et al.

This work proposes an end-to-end multi-modal reinforcement learning framework for high-level decision-making in autonomous vehicles. The framework integrates heterogeneous sensory input, including camera images, LiDAR point clouds, and vehicle heading information, through a cross-attention transformer-based perception module. Although transformers have become the backbone of modern multi-modal architectures, their high computational cost limits their deployment in resource-constrained edge environments. To overcome this challenge, we propose a spiking temporal-aware transformer-like architecture that uses ternary spiking neurons for computationally efficient multi-modal fusion. Comprehensive evaluations across multiple tasks in the Highway Environment demonstrate the effectiveness and efficiency of the proposed approach for real-time autonomous decision-making.

Aref Ghoreishee, Abhishek Mishra, John Walsh et al.

We propose a new ternary spiking neuron model to improve the representation capacity of binary spiking neurons in deep Q-learning. Although a ternary neuron model has recently been introduced to overcome the limited representation capacity offered by the binary spiking neurons, we show that its performance is worse than that of binary models in deep Q-learning tasks. We hypothesize gradient estimation bias during the training process as the underlying potential cause through mathematical and empirical analysis. We propose a novel ternary spiking neuron model to mitigate this issue by reducing the estimation bias. We use the proposed ternary spiking neuron as the fundamental computing unit in a deep spiking Q-learning network (DSQN) and evaluate the network's performance in seven Atari games from the Gym environment. Results show that the proposed ternary spiking neuron mitigates the drastic performance degradation of ternary neurons in Q-learning tasks and improves the network performance compared to the existing binary neurons, making DSQN a more practical solution for on-board autonomous decision-making tasks.

Akshay Bhardwaj, Daniel Slavin, John Walsh et al.

The force transmitted from the front tires to the steering rack of a vehicle, called the rack force, plays an important role in the function of electric power steering (EPS) systems. Estimates of rack force can be used by EPS to attenuate road feedback and reduce driver effort. Further, estimates of the components of rack force (arising, for example, due to steering angle and road profile) can be used to separately compensate for each component and thereby enhance steering feel. In this paper, we present three vehicle and tire model-based rack force estimators that utilize sensed steering angle and road profile to estimate total rack force and individual components of rack force. We test and compare the real-time performance of the estimators by performing driving experiments with non-aggressive and aggressive steering maneuvers on roads with low and high frequency profile variations. The results indicate that for aggressive maneuvers the estimators using non-linear tire models produce more accurate rack force estimates. Moreover, only the estimator that incorporates a semi-empirical Rigid Ring tire model is able to capture rack force variation for driving on a road with high frequency profile variation. Finally, we present results from a simulation study to validate the component-wise estimates of rack force.