LLMサービングを超えて：身体性AIシステム設計のための視覚-言語-行動ワークロードの特性評価
Beyond LLM Serving: Characterizing Vision-Language-Action Workloads for Embodied AI System Design
VLAモデルのバッチ1制御推論をエッジGPUとオンボードSoCで計測し、メモリ/計算律速や精度-速度-エネルギーのトレードオフを明らかにした。
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: Seonghun Jung, Sieun Moon, Jiyoung Jeong, Jimin Lee, Jaehyuk Huh
分類: cs.AR, cs.RO
原文アブストラクト
Vision-language-action (VLA) models translate multimodal observations into low-level robot actions. During robot operation, each control period sets an inference deadline, and overruns leave the robot acting on stale observations, reducing task success. Meeting this deadline motivates on-device or nearby edge execution, where a single robot requires batch-1 inference outside the design point of LLM serving systems. Although VLA architectures combine familiar vision-language, autoregressive, and diffusion-style components, their runtime behavior in this batch-1 control setting remains uncharacterized. We characterize four representative VLA models on an edge GPU server and two onboard SoCs, using single-inference profiling and 43,200 closed-loop episodes. Action tensor dimensionality determines whether a stage is memory- or compute-bound, platform balance can shift that bottleneck, and GPU frequency scaling yields a platform-dependent energy-latency sweet spot. In closed-loop operation, overlapping inference with action execution creates an accuracy-speed-energy tradeoff, and no configuration is Pareto-dominant across deployment SLOs. These results guide joint design of VLA model architectures, hardware, and runtime policies.