Zobrazit v EDS

Bio-Inspired Embedded Control Systems for Autonomous Emergency Maneuvering in AI-Driven Vehicles.

Uloženo v:
Podrobná bibliografie
Název: Bio-Inspired Embedded Control Systems for Autonomous Emergency Maneuvering in AI-Driven Vehicles.
Autoři: Govindasamy, Alagar Raja
Zdroj: International Journal of Computational & Experimental Science & Engineering Experimental Science & Engineering (IJCESEN); 2025, Vol. 11 Issue 4, p9697-9707, 11p
Témata: EMBEDDED computer systems, BIOLOGICALLY inspired computing, EMERGENCY maneuvers (Aeronautics), AUTONOMOUS vehicles, ARTIFICIAL intelligence, ARTIFICIAL neural networks
Abstrakt: Modern self-driving vehicles face significant challenges in achieving fast enough response times for emergency collision avoidance while operating within the limited power and heat budgets of automotive computer systems. Bio-inspired control systems based on brain-like computing offer promising alternatives to traditional deep learning approaches by providing reflex-like decision-making that mimics the fast reaction pathways found in biological nervous systems. Using spiking neural networks on automotive-grade microcontrollers enables event-driven computing where processing resources activate only when important environmental changes occur, as detected by specialized sensors. This approach achieves reaction times in single-digit milliseconds with power consumption orders of magnitude lower than equivalent conventional systems. The combination of event-based vision sensors and neuromorphic processors creates complete processing pipelines that eliminate motion blur, handle extreme lighting changes, and maintain functionality during partial sensor failure or harsh environmental conditions. Integration with real-time operating systems allows deployment alongside traditional perception and planning systems, adding architectural diversity that improves overall system reliability through complementary processing methods based on fundamentally different computational principles. Testing through simulated emergencies demonstrates the feasibility of bio-inspired reflex control for next-generation vehicle safety systems with ultra-low latency response capabilities that traditional AI architectures cannot provide within embedded platform constraints. [ABSTRACT FROM AUTHOR]
Copyright of International Journal of Computational & Experimental Science & Engineering Experimental Science & Engineering (IJCESEN) is the property of Journal of Computational Experimental Science, Engineering Experimental Science & Engineering and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Databáze: Complementary Index
Popis
Abstrakt:Modern self-driving vehicles face significant challenges in achieving fast enough response times for emergency collision avoidance while operating within the limited power and heat budgets of automotive computer systems. Bio-inspired control systems based on brain-like computing offer promising alternatives to traditional deep learning approaches by providing reflex-like decision-making that mimics the fast reaction pathways found in biological nervous systems. Using spiking neural networks on automotive-grade microcontrollers enables event-driven computing where processing resources activate only when important environmental changes occur, as detected by specialized sensors. This approach achieves reaction times in single-digit milliseconds with power consumption orders of magnitude lower than equivalent conventional systems. The combination of event-based vision sensors and neuromorphic processors creates complete processing pipelines that eliminate motion blur, handle extreme lighting changes, and maintain functionality during partial sensor failure or harsh environmental conditions. Integration with real-time operating systems allows deployment alongside traditional perception and planning systems, adding architectural diversity that improves overall system reliability through complementary processing methods based on fundamentally different computational principles. Testing through simulated emergencies demonstrates the feasibility of bio-inspired reflex control for next-generation vehicle safety systems with ultra-low latency response capabilities that traditional AI architectures cannot provide within embedded platform constraints. [ABSTRACT FROM AUTHOR]
ISSN:21499144
DOI:10.22399/ijcesen.4518