LiteVLA-Edge: 組み込みロボティクス向け量子化オンデバイスマルチモーダル制御
LiteVLA-Edge: Quantized On-Device Multimodal Control for Embedded Robotics
Jetson Orin級の組み込みハードウェア上でVLAモデルを完全オンデバイス動作させるための実用的なパイプラインを提案し、量子化とGPU推論により約6.6Hzのリアルタイム制御を実現した。
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: Justin Williams, Kishor Datta Gupta, Roy George, Mrinmoy Sarkar
分類: cs.RO, cs.AI
原文アブストラクト
Vision-Language-Action (VLA) models provide a unified framework for perception, language conditioning, and action generation, but many existing systems remain difficult to deploy in embedded robotic settings because of their computational requirements and inference latency. In this paper, we present LiteVLA-Edge, a deployment-oriented VLA pipeline for fully on-device inference on Jetson Orin-class hardware. Our approach combines supervised image-to-action fine-tuning in FP32 with post-training 4-bit GGUF quantization and GPU-accelerated inference through the \texttt{llama.cpp} runtime. Under our deployment configuration, LiteVLA-Edge achieves a mean end-to-end latency of 150.5\,ms (approximately 6.6\,Hz) while operating entirely offline within a ROS~2-integrated perception--reasoning--action pipeline. Rather than introducing a new policy objective, our contribution is a practical systems path for executing compact multimodal control models locally on embedded hardware while preserving modular interfaces between perception, reasoning, and actuation. These results establish timing feasibility for reactive language-conditioned control and provide a reproducible baseline for future task-level evaluation of on-device VLAs in robotics.
