Robotic systems lack a principled abstraction for organizing intelligence, capabilities, and execution in a unified manner. Existing approaches either couple skills within monolithic architectures or decompose functionality into loosely coordinated modules or multiple agents, often without a coherent model of identity and control authority. We argue that a robot should be modeled as a single persistent intelligent subject whose capabilities are extended through installable packages. We formalize this view as AEROS (Agent Execution Runtime Operating System), in which each robot corresponds to one persistent agent and capabilities are provided through Embodied Capability Modules (ECMs). Each ECM encapsulates executable skills, models, and tools, while execution constraints and safety guarantees are enforced by a policy-separated runtime. This separation enables modular extensibility, composable capability execution, and consistent system-level safety. We evaluate a reference implementation in PyBullet simulation with a Franka Panda 7-DOF manipulator across eight experiments covering re-planning, failure recovery, policy enforcement, baseline comparison, cross-task generality, ECM hot-swapping, ablation, and failure boundary analysis. Over 100 randomized trials per condition, AEROS achieves 100% task success across three tasks versus baselines (BehaviorTree.CPP-style and ProgPrompt-style at 92--93%, flat pipeline at 67--73%), the policy layer blocks all invalid actions with zero false acceptances, runtime benefits generalize across tasks without task-specific tuning, and ECMs load at runtime with 100% post-swap success.

翻译：机器人系统缺乏一种统一的原则性抽象来组织智能、能力和执行过程。现有方法要么将技能耦合在单体架构中，要么将功能分解为松散协调的模块或多个智能体，通常缺乏连贯的身份与控制权威模型。我们认为机器人应被建模为一个持久的单一智能主体，其能力通过可安装的包进行扩展。我们将这一观点形式化为AEROS（智能体执行运行时操作系统），其中每个机器人对应一个持久智能体，能力通过具身能力模块（ECM）提供。每个ECM封装了可执行技能、模型和工具，而执行约束和安全保障由策略分离的运行时强制执行。这种分离实现了模块化可扩展性、可组合的能力执行以及一致的系统级安全。我们在PyBullet仿真中，使用Franka Panda 7自由度机械臂对参考实现进行了八项实验评估，涵盖重规划、故障恢复、策略执行、基线对比、跨任务通用性、ECM热插拔、消融分析和故障边界分析。每个条件下超过100次随机试验表明，AEROS在三个任务中均实现100%任务成功率（对比基线：BehaviorTree.CPP风格和ProgPrompt风格为92-93%，扁平流水线为67-73%），策略层以零误接受率拦截所有无效动作，运行时优势无需任务特定调优即可泛化至各任务，ECM在运行时加载并实现100%的交换后成功率。