AI system PALCAS improves autonomous vehicle lane changes with federated reinforcement learning

Researchers have developed PALCAS, a new system for autonomous vehicles that uses federated reinforcement learning to advise on lane changes. Unlike previous systems, PALCAS prioritizes lane changes based on a vehicle's urgency to reach its destination. The system incorporates a novel reward function to ensure safe and judicious decisions in various driving scenarios, utilizing a parameterized deep Q-network for agent cooperation. Simulations show PALCAS improves traffic efficiency, safety, and arrival rates. AI

影响 Enhances AV decision-making for traffic efficiency and safety through prioritized lane changes.

排序理由 Academic paper detailing a novel system for autonomous vehicles.

在 arXiv cs.AI 阅读 →

• Federated Reinforcement Learning
• Mosaic V2X
• SUMO
• Autonomous Vehicles

• 论文
• 其他

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →