Kairos: 物理AI向けのスケーラブルな推論サービスシステム
Kairos: A Scalable Serving System for Physical AI
物理AIの推論と行動実行を非同期に連携させる「生成-実行ループ」を最適化した、複数ロボット向けの初のサービスシステムを設計し、エンドツーエンドのタスク遅延を大幅に削減した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yinwei Dai, Ganesh Ananthanarayanan, Landon Cox, Xenofon Foukas, Bozidar Radunovic, Ravi Netravali
分類: cs.RO, cs.DC
原文アブストラクト
Physical AI is experiencing rapid growth with frontier foundation models increasing its capabilities across general environments. Physical AI tasks are characterized by inference properties that are markedly different from digital AI. They consist of multiple rounds of inference and action execution, generating a chunk of actions in each inference round, and asynchronously interleaving inference and execution. This makes existing digital AI serving systems unsuited for physical AI; a shortcoming that is critical for enabling their wide adoption, considering their size and the scale of the robot fleets they have to serve. To fill this gap, we design Kairos, the first multi-robot serving system that makes the generate-execute loop a first-class citizen, with active involvement in the execution phase. Across a wide range of physical AI models and robots, Kairos reduces the average end-to-end task latency by 31.8--66.5% over state-of-the-art digital AI serving practices, with gains scaling with the robot fleet size.
