发表机构
Stanford University; MIT; Northeastern University（斯坦福大学; 麻省理工学院; 东北大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究构建长期运行机器人智能体的闭环管道问题，提出Retriever，它涵盖异步决策模型等整个堆栈，将智能体表示为有状态因果流函数图，编译到支持多后端的运行时，可系统调试和确定性重放，通过案例研究等进行评估。
AI 中文摘要
构建长期运行的机器人智能体需要组合闭环管道，其组件运行在不同时钟且延迟可变。当前系统常采用临时并发和发布/订阅约定，导致时间和输入消费语义隐含，行为依赖调度且难重现、调试和复用。现有解决方案多只解决部分问题。本文提出Retriever，涵盖整个堆栈，包括异步决策模型、编程模型、运行时和示例闭环智能体管道。它将智能体表示为在显式运行时钟上执行的有状态因果流函数图，通过连续时间流上的异步环境-智能体循环形式化此观点，表明有限内存因果策略可由这些算子组合表示。Retriever将这些图编译到支持多个后端的运行时，实现跨运行环境的系统调试和从记录的异步数据进行确定性重放。我们通过实际机器人案例研究以及对运行时开销和确定性重放行为的控制研究对Retriever进行评估。
英文摘要
Building long-horizon robot agents requires composing closed-loop pipelines -- perception, belief update, planning, and control -- whose components run at different clocks and with variable latency. Today, these systems are often assembled with ad-hoc concurrency and pub/sub conventions that make timing and input-consumption semantics implicit, yielding schedule-dependent behavior that is hard to reproduce, debug, and reuse. Current solutions typically solve parts of this problem at either the algorithmic or the systems layer, but not both. In this work, we propose Retriever, which spans the entire stack: an asynchronous decision model, a programming model, a runtime, and an example closed-loop agent pipeline. Retriever represents an agent as a graph of stateful causal stream functions executed on explicit run clocks. We formalize this view via an asynchronous environment-agent loop over continuous-time streams and show that finite-memory causal policies can be represented by compositions of these operators. Retriever compiles these graphs into a runtime that supports multiple backends, enabling systematic debugging across running environments and deterministic replay from logged asynchronous data. We evaluate Retriever through a real-robot case study together with controlled studies of runtime overhead and deterministic replay behavior.
CommentsProject website: http://retriever.systems; Package open-source website: http://openretriever.org
