要旨で参照されている研究は明示されていないが、関連手法としてVLAモデル(Vision-Language-Action models)や、動的操作のためのベンチマーク(例えば、RoboSuiteやRLBenchなど)が考えられる。また、時間的推論や未来予測に関する研究(例えば、Video PredictionやTemporal Reasoning in RL)も関連する。具体的には、要旨に挙げられたReflexVLAの手法(latent future prediction, multi-frame temporal fusion, batched visual encoding, CUDA Graph replay)に関連する論文を読むとよい。
※ 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: Yuxuan Chen, Wanruo Zhang, Xiao Li
分類: cs.RO, cs.AI
原文アブストラクト
Vision-Language-Action (VLA) models have recently achieved promising performance in robotic manipulation. However, existing benchmarks mainly evaluate generalization on static manipulation tasks and largely overlook dynamic interaction scenarios. To address this gap, we present ReflexBench, a benchmark for reaction-critical manipulation. ReflexBench contains six dynamic tasks and introduces an evaluation framework that decouples simulator stepping from robot control while supporting configurable latency under synchronous and asynchronous inference. Building upon ReflexBench, we propose ReflexVLA, an efficient VLA model designed for reaction-critical manipulation without large-scale robot-data pretraining. ReflexVLA enhances temporal reasoning through latent future prediction and multi-frame temporal fusion within the vision backbone, while reducing deployment latency through batched visual encoding and CUDA Graph replay. Experiments show that ReflexVLA consistently improves dynamic manipulation performance while maintaining competitive accuracy on standard static manipulation benchmarks, and real-world experiments further demonstrate its effectiveness under practical deployment conditions. Project website: https://reflexvla.github.io