← Back to the feed
AI & softwareResearch findings

Proposal of Core Components and Technical Directions in Knowledge-Driven Autonomous Driving

Original published 2023.12.07 23:17 KSTAdded to Blackdeck 2026.11.15 10:40 KST

What has changed?

Knowledge-driven methods with cognition, generalization, and lifelong learning can overcome data bias and long-tail scenario challenges

Key points

  1. Knowledge-driven autonomous driving addresses data bias and long-tail scenario challenges effectively
  2. Large language models and world models enhance system adaptability and intelligence
  3. Core components including dataset, environment, and driver agent are systematically analyzed

Connect it to your work

Systematically analyzes core components such as dataset and environment, driver agent in knowledge-driven autonomous driving

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.

  1. arxivTowards Knowledge-driven Autonomous Driving