Jingjiao Zhao, Jing Dong, Mingyu Cao, Ruochuan Shi, Xiansheng Chen, Pengwei Wang, Zhiwu Lu · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27917 · cited by 0 works (OpenAlex) · open-access PDF
Die historisch vertrauenswürdige Robotermanipulation erfordert den Aufgabenkontext und die Interaktionsgeschichte, da die aktuelle Beobachtung allein nicht ausreicht, um die nächste Aktion zu bestimmen. Hierarchische Frameworks verwenden Task-Memory für die High-Level-Sub-Ziel-Rezension und die Low-Level-Rezension für die Ausführung. Jedoch erfordern Speicheraktualisierungen eine genaue Abschlussbewertung: Ähnliche Beobachtungen können unterschiedlichen Ausführungsphasen entsprechen, und eine vorzeitige Aufzeichnung kann die nachfolgende Sub-Ziel-Rezension irreführen. Wir präsentieren EventSync, einen hierarchischen Rahmen, der die Aufgabe-Rezension und die Aktionsausführung durch Ereignis-gesteuerte Speicher
Machine translation (Meta M2M100); the English original follows.
History-dependent robotic manipulation requires task context and interaction history, as the current observation alone is insufficient to determine the next action. Hierarchical frameworks use task memory for high-level subgoal reasoning and low-level policies for execution. However, memory updates require accurate completion assessment: similar observations may correspond to different execution phases, and prematurely recording completion can mislead subsequent subgoal reasoning. We present EventSync, a hierarchical framework that coordinates task reasoning and action execution through event-driven memory updates. A vision-language model generates subgoals from task plans and interaction history, while a vision-language-action model executes them. A lightweight Event Monitor combines visual observations with end-effector trajectories to determine whether the current subgoal is complete. The framework records the current subgoal in its completed-subgoal history and triggers subsequent reasoning only after obtaining completion evidence. With visual history in the executor, EventSync achieves 64.5% overall success on RoboMME, exceeding the best baseline reported in the benchmark by 20.0 percentage points. Further analysis shows that this update mechanism helps build a reliable completed-subgoal history. Experiments on four real-robot tasks with different memory requirements validate the framework's effectiveness in real-world robotic manipulation.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Task (project management), Context (archaeology), Artificial intelligence, Benchmark (surveying), Action (physics)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27917, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange