Elishai Ezra Tsur
Gianluca Di Flumeri
Hadar Cohen Duwek- 1The Neuro-Biomorphic Engineering Lab (NBEL), Department of Mathematics and Computer Science, The Open University of Israel, Ra'anana, Israel
- 2Department of Molecular Medicine, Sapienza University of Rome, Rome, Italy
Editorial on the Research Topic
Brain-inspired autonomous driving
Autonomous driving is one of the hallmarks of artificial intelligence. Neuromorphic, brain-inspired computing architectures, are revolutionizing vehicular autonomy through biomimetic approaches (Tsur, 2021). They can dramatically impact the multidimensional landscape of autonomous driving, extending across critical domains such as control (DeWolf, 2021), navigation (Novo et al., 2024), and neurophysiological assessment (Wilson and Russell, 2003). Particularly, these brain-inspired computational systems leverage spiking neural networks (SNNs) and event-driven processing to enhance real-time perception (Cohen Duwek and Tsur, 2021), decision-making (Shalumov et al., 2021), and adaptive learning capabilities (Ehrlich et al., 2022). This article collection revolves around the state of the art of neuromorphic systems, designed to support autonomous driving across those dimensions.
Neuromorphic control is posed to significantly contribute to autonomous behavior by leveraging spiking neural networks-based energy-efficient computational frameworks. In this collection, Halaly et al. explored neuromorphic implementations of four prominent controllers for autonomous driving: pure-pursuit, Stanley, PID (Proportional – Integral – Derivative), and MPC (Model Predictive Control), using CARLA (Gomez-Huelamo et al., 2021), a physics-aware simulation framework. Their results show that those neuromorphic control models converge to their optimal performances with merely 100–1,000 neurons. They also highlight the importance of hybrid conventional and neuromorphic designs, as was suggested here with the MPC controller. This MPC was later extended to support adaptive behavior and to address unforeseen situations such as malfunctioning and swift steering scenarios (Halaly and Tsur, 2024). Further in this Research Topic, Lian et al. addressed the importance of adaptive control for changing road conditions by proposing a neural model for deriving road adhesion coefficient (the maximum friction coefficient between tire and road surface) and tire cornering stiffness (affected by road friction and tire slip angle). Those parameters can be used to improve the design of the vehicle's dynamic model and enhance the controller's robustness.
Autonomous driving systems (ADSs) often comprise multimodal sensing, including cameras, LiDARs, IMUs, and GPS, for real-time object detection, semantic segmentation, planning, and control (Zhao et al., 2024). LiDAR-driven neural perception is an important stepping stone toward the design of self-navigating vehicles (Shalumov et al., 2021). In this Research Topic, Lee and Jeong propose a neural reinforcement model, they termed the “Velocity Range-based Evaluation Method” in which LiDAR data is used to provide path planning in a map-less environment.
Finally, in the evolutionary scenario of autonomous driving technologies, the transitional phase characterized by partial vehicle autonomy presents critical challenges in human-machine interaction (Xing et al., 2021). The emerging paradigm necessitates a sophisticated, bidirectional monitoring system that transcends traditional human-vehicle interfaces. In fact, the vehicle must develop robust capabilities for comprehensive driver state monitoring, including advanced sensor fusion techniques for enabling holistic driver condition evaluation, to determine whether the driver is able to intervene and take control (Ansari et al., 2022). Empirical research suggests that effective human-autonomous system collaboration requires not just technological sophistication, but a deep understanding of human cognitive and physiological variability (Unni et al., 2022). The ultimate goal is to develop a symbiotic human-machine interface where autonomous systems act as collaborative partners rather than mere technological substitutes, enhancing overall transportation safety and efficiency. In this regard, in this article collection, Giorgi et al. propose an integrated framework to assess the driver's mental fatigue in real time using electroencephalographic, electrooculographic, photoplethysmographic, and electrodermal activity. Their holistic approach showed that the most sensitive and timely parameters are those related to brain activity. To a lesser extent, those related to ocular parameters are also sensitive to the onset of mental fatigue but with a delayed effect.
In conclusion, the confluence of neuromorphic computing, advanced sensing technologies, and sophisticated human-machine interaction represents a pivotal transformation in autonomous driving. This Research Topic illuminates the multifaceted challenges and innovative solutions emerging at the intersection of artificial intelligence, neuroscience, and automotive engineering. From energy-efficient neural controllers to adaptive perception systems and comprehensive driver state monitoring, the research demonstrates that autonomous driving is far more than a technological challenge—it is a complex socio-technical ecosystem.
The future of autonomous vehicles might lie not in complete human replacement, but in creating intelligent, responsive systems that collaborate seamlessly with human operators. By integrating biomimetic computational approaches, advanced sensor fusion, and a nuanced understanding of human cognitive variability, we move closer to a transportation paradigm that prioritizes safety, efficiency, and harmonious human-machine interaction.
Author contributions
EE: Writing – original draft, Writing – review & editing. GD: Writing – original draft, Writing – review & editing. HC: Writing – original draft, Writing – review & editing.
Conflict of interest
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Publisher's note
All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article, or claim that may be made by its manufacturer, is not guaranteed or endorsed by the publisher.
References
Ansari, S., Naghdy, F., and Du, H. (2022). Human-machine shared driving: challenges and future directions. IEEE Trans. Intell. Vehic. 7, 499–519. doi: 10.1109/TIV.2022.3154426
Cohen Duwek, H., and Tsur, E. E. (2021). “Biologically plausible spiking neural networks for perceptual filling-in,” in Proceedings of the Annual Meeting of the Cognitive Science Society.
DeWolf, T. (2021). Spiking neural networks take control. Sci. Robot. 6:eabk3268. doi: 10.1126/scirobotics.abk3268
Ehrlich, M., Zaidel, Y., Weiss, L., Melamed Yekel, A., Gefen, N., Supic, L., et al. (2022). Adaptive control of a wheelchair mounted robotic arm with neuromorphically integrated velocity readings and online-learning. Front. Neurosci. 16:1007736. doi: 10.3389/fnins.2022.1007736
Gomez-Huelamo, C., Del Egido, J., Bergasa, L. M., Barea, R., Lopez-Guillen, E., Arango, F., et al. (2021). “Train here, drive there: simulating real-world use cases with fully-autonomous driving architecture in carla simulator,” in Advances in Physical Agents II: Proceedings of the 21st International Workshop of Physical Agents (Madrid, Springer), 44–59. doi: 10.1007/978-3-030-62579-5_4
Halaly, R., and Tsur, E. E. (2024). Continuous adaptive nonlinear model predictive control using spiking neural networks and real-time learning. Neuromor. Comput. Eng. 4:024006. doi: 10.1088/2634-4386/ad4209
Novo, A., Lobon, F., Garcia de Marina, H., Romero, S., and Barranco, F. (2024). Neuromorphic perception and navigation for mobile robots: a review. ACM Comput. Surv. 56, 1–37. doi: 10.1145/3656469
Shalumov, A., Halaly, R., and Tsur, E. E. (2021). Lidar-driven spiking neural network for collision avoidance in autonomous driving. Bioinspir. Biomimet. 16:066016. doi: 10.1088/1748-3190/ac290c
Tsur, E. E. (2021). Neuromorphic Engineering: The Scientist's, Algorithms Designer's and Computer Architect's Perspectives on Brain-Inspired Computing?. Boca Raton: CRC Press. doi: 10.1201/9781003143499
Unni, A., Trende, A., Pauley, C., Weber, L., Biebl, B., Kacianka, S., et al. (2022). Investigating differences in behavior and brain in human-human and human-autonomous vehicle interactions in time-critical situations. Front. Neuroergon. 3:836518. doi: 10.3389/fnrgo.2022.836518
Wilson, G. F., and Russell, C. A. (2003). Real-time assessment of mental workload using psychophysiological measures and artificial neural networks. Hum. Factors 45, 635–644. doi: 10.1518/hfes.45.4.635.27088
Xing, Y., Lv, C., Cao, D., and Hang, P. (2021). Toward human-vehicle collaboration: review and perspectives on human-centered collaborative automated driving. Transpor. Res. C 128:103199. doi: 10.1016/j.trc.2021.103199
Keywords: navigation & control, spiking neural network (SNN), control theorem and control engineering, neurophysiologic assessment, adaptive control
Citation: Ezra Tsur E, Di Flumeri G and Cohen Duwek H (2025) Editorial: Brain-inspired autonomous driving. Front. Neurorobot. 19:1543115. doi: 10.3389/fnbot.2025.1543115
Received: 10 December 2024; Accepted: 02 January 2025;
Published: 16 January 2025.
Edited and reviewed by: Florian Ròhrbein, Chemnitz University of Technology, Germany
Copyright © 2025 Ezra Tsur, Di Flumeri and Cohen Duwek. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Elishai Ezra Tsur, ZWxpc2hhaUBuYmVsLWxhYi5jb20=