New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehicles
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915647216156672 |
|---|---|
| author | Ghoreishee, Aref Mishra, Abhishek Zhou, Lifeng Walsh, John Kandasamy, Nagarajan |
| author_facet | Ghoreishee, Aref Mishra, Abhishek Zhou, Lifeng Walsh, John Kandasamy, Nagarajan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_01882 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehicles Ghoreishee, Aref Mishra, Abhishek Zhou, Lifeng Walsh, John Kandasamy, Nagarajan Machine Learning 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. |
| title | New Spiking Architecture for Multi-Modal Decision-Making in Autonomous Vehicles |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2512.01882 |