AIToday
Large Language ModelsAutonomous DrivingTop Companies' AI MovesTop Companies AIPublished: Aug 29, 2026, 06:30 JST2 min read

KDDI and Michinori HD to run AI-based network optimization trial for autonomous buses

KDDI and Michinori HD to run AI-based network optimization trial for autonomous buses

Key takeaway

  • KDDI and Michinori Holdings will test AI that optimizes communication for autonomous buses.

  • The trial starts September 2026 in Hitachi.

  • It aims to improve 5G reliability and reduce monitoring workload.

3 Key Points

  1. What happened

    KDDI and Michinori Holdings will run a trial using AI to autonomously optimize communication quality for autonomous buses. The trial starts September 1, 2026 in Hitachi City, Ibaraki Prefecture.

  2. Why it matters

    Stable communication is essential for remote monitoring of autonomous vehicles, but building new infrastructure is costly and time-consuming. The trial uses multiple AIs to optimize base station parameters, aiming to improve 5G connectivity and reduce operational workload.

  3. What to watch

    The trial will validate whether AI-based RAN parameter optimization (adjusting base station radio settings) improves communication quality and cuts network design and adjustment work. It is part of a government-approved project supporting Level 4 autonomous driving.

Ask the AI about this article →

Context & Analysis

This trial builds on KDDI's broader rollout of AI-based network optimization technology, which the company and its research institute began introducing to base stations nationwide in February 2026. That earlier deployment reportedly improved communication stability by 25% and cut optimization work time by over 95%. The Hitachi trial applies this same technology to a specific use case: autonomous buses operating under Level 4 automation, where remote monitoring is mandatory. The Hitachi BRT route has been running Level 4 autonomous service since February 2025 over a 6.1 km stretch, while the Omika loop route has been testing Level 2 automation since January 2025. By applying AI-driven network tuning in this setting, the companies aim to verify whether communication quality improvements can reduce the burden on remote monitoring staff. If successful, the approach could support autonomous bus operations without requiring expensive new telecom infrastructure, potentially addressing driver shortages and underserved transport areas.

FAQ

Where will the trial take place?
The trial will be held in Hitachi City, Ibaraki Prefecture, on two routes: the Hitachi BRT route and the Omika Station loop route.
What technology is being tested?
The trial tests AI-based RAN parameter optimization, where multiple AIs cooperate to adjust base station settings to improve communication quality and connectivity.
What is the expected duration of the trial?
Data collection is expected to occur on about 7 days between September 1, 2026 and the end of October 2026.
Top Companies AIRead Original Article

Get the latest Large Language Models news every morning

For example, today's edition would include:

  • AI's math proofs challenge field's core valueJapan Times Tech · 3h ago
  • AI-written citations 38.6% fabricated, study findsHacker News · 3h ago
  • Lam Research breaks ground on AI chip lab in OregonTop Companies AI · 10h ago

AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.

Free · takes 30 seconds · unsubscribe anytimeWhat is AIToday? →

Ask AI

Ask AI anything about this article. Q&As are published on this page for other readers too.

Related Articles

Next articleColt Japan CEO: AI-powered autonomous network