バッチ型ロボットポリシー配信のためのアクションチャンクスケジューリング
Action Chunk Scheduling for Batched Robot Policy Serving
複数のロボットにリモートGPUからポリシーを配信する際のスケジューリング問題を定式化し、ロボットごとのアクションチャンク消費速度の違いを考慮したスケジューリングアルゴリズムを提案。実機実験で最大18%のスループット向上を確認した。
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: Rohan Bansal, David He, Nadun Ranawaka Arachchige, Zhenyang Chen, Soobum Kim, Kexin Rong, Danfei Xu
分類: cs.RO
原文アブストラクト
Deploying robot foundation models at scale is the next step towards realizing the potential of general-purpose robots. However, Vision-Language-Action (VLA) and other foundation models are computationally demanding, and on-device compute is constrained by power and space. In this paper, we introduce the problem of serving a robot policy to multiple robots from a remote GPU and formulate it as a scheduling problem. We build Armory, a serving system validated on fleets of both simulated and real robots. Our experiments show that naive scheduling heuristics perform well when all robots are the same, but fall short when robots consume action chunks at different rates, uncovering a mismatch between conventional batching methods and the closed-loop requirements of robot policy execution. To address this, we propose a scheduling algorithm that accounts for this heterogeneity and improves overall system throughput by up to $18\%$ in real-world experiments. Additional details are available at https://gatech-rl2.github.io/actionchunkscheduling.
