Leveraging OS-Level Primitives for Robotic Action Management

2025-08-13

AI Summary

Current end-to-end vision-language-action (VLA) robotic systems suffer from scarce training data, poor task generalization, and inefficient action execution. To address these limitations, we propose AMS—the first framework to integrate operating-system-level primitives into robotic action management. AMS introduces three novel mechanisms: action anomaly interruption, context reuse, and record-and-replay—enabling robust cross-task action scheduling and efficient action reuse. Crucially, AMS enhances VLA model deployment efficacy through system-level architectural optimization, without requiring additional training data. Extensive experiments on both simulated and real-world robotic platforms demonstrate that AMS improves task success rates by 7–24×, reduces end-to-end execution time by 29%–74%, and significantly boosts generalization capability and real-time performance.

Technology Category

• Intelligent Robots: Manipulation
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Applications

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

End-to-end imitation learning frameworks (e.g., VLA) are increasingly prominent in robotics, as they enable rapid task transfer by learning directly from perception to control, eliminating the need for complex hand-crafted features. However, even when employing SOTA VLA-based models, they still exhibit limited generalization capabilities and suboptimal action efficiency, due to the constraints imposed by insufficient robotic training datasets. In addition to addressing this problem using model-based approaches, we observe that robotic action slices, which consist of contiguous action steps, exhibit strong analogies to the time slices of threads in traditional operating systems. This insight presents a novel opportunity to tackle the problem at the system level. In this paper, we propose AMS, a robot action management system enhanced with OS-level primitives like exception, context switch and record-and-replay, that improves both execution efficiency and success rates of robotic tasks. AMS first introduces action exception, which facilitates the immediate interruption of robotic actions to prevent error propagation. Secondly, AMS proposes action context, which eliminates redundant computations for VLA-based models, thereby accelerating execution efficiency in robotic actions. Finally, AMS leverages action replay to facilitate repetitive or similar robotic tasks without the need for re-training efforts. We implement AMS in both an emulated environment and on a real robot platform. The evaluation results demonstrate that AMS significantly enhances the model's generalization ability and action efficiency, achieving task success rate improvements ranging from 7x to 24x and saving end-to-end execution time ranging from 29% to 74% compared to existing robotic system without AMS support.

Problem

• Improving generalization in robotic imitation learning models
• Enhancing action efficiency in robotic task execution
• Reducing error propagation in robotic action sequences

Innovation

• Uses OS-level primitives for robotic action management
• Introduces action exception to prevent error propagation
• Leverages action replay for repetitive tasks efficiency