SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HDMap Construction
–Neural Information Processing Systems
Autonomous vehicles rely on detailed and accurate environmental information to operate safely. High definition (HD) maps offer a promising solution, but their high maintenance cost poses a significant barrier to scalable deployment. This challenge is addressed by online HD map construction methods, which generate local HD maps from live sensor data. However, these methods are inherently limited by the short perception range of onboard sensors. To overcome this limitation and improve general performance, recent approaches have explored the use of standard definition (SD) maps as prior, which are significantly easier to maintain.
Neural Information Processing Systems
Jun-15-2026, 21:42:09 GMT
- Country:
- North America > United States > Minnesota (0.28)
- Genre:
- Research Report > Experimental Study (1.00)
- Industry:
- Government (0.67)
- Transportation
- Ground > Road (0.93)
- Infrastructure & Services (0.93)
- Technology:
- Information Technology > Artificial Intelligence
- Natural Language (1.00)
- Machine Learning (1.00)
- Representation & Reasoning (0.67)
- Robots > Autonomous Vehicles (0.48)
- Information Technology > Artificial Intelligence