Space & aviationResearch findings
Development of Spiking Neural Network-Based Autonomous Driving System
Original published 2024.05.30 13:57 KSTAdded to Blackdeck 2026.11.13 18:48 KST
What has changed?
First unified spiking neural network-based autonomous driving system achieving energy efficiency and real-time processing simultaneously
Key points
- Proposes Spiking Autonomous Driving (SAD), a unified spiking neural network for autonomous driving
- Integrates perception, prediction, and planning into a single end-to-end model
- Achieves energy efficiency and real-time processing simultaneously
Connect it to your work
SAD uses multi-view camera inputs to generate spatiotemporal bird's eye view, employs a dual-pathway prediction module with spiking neurons, and generates safe,
What remains unproven
This research note is based on an abstract; check the original for test conditions and application scope.
Originals used for this note
Links open the original publisher in a new tab.