Efficient Coordination with the System-Level Shared State: An Embodied-AI Native Modular Framework
This addresses reliability and scalability issues for developers deploying closed-loop AI systems in real-world environments, though it appears incremental as it builds on existing modular and coordination concepts.
The paper tackles the problem of interface drift and brittle recovery in partially decoupled Embodied AI systems by introducing ANCHOR, a modular framework that uses explicit system-level primitives for decoupling and robustness, resulting in automatic stream resumption after crashes and controlled degradation under load.
As Embodied AI systems move from research prototypes to real world deployments, they tend to evolve rapidly while remaining reliable under workload changes and partial failures. In practice, many deployments are only partially decoupled: middleware moves messages, but shared context and feedback semantics are implicit, causing interface drift, cross-module interference, and brittle recovery at scale. We present ANCHOR, a modular framework that makes decoupling and robustness explicit system-level primitives. ANCHOR separates (i) Canonical Records, an evolvable contract for the standardized shared state, from (ii) a communication bus for many-to-many dissemination and feedback-oriented coordination, forming an inspectable end-to-end loop. We validate closed-loop feasibility on a de-identified workflow instantiation, characterize latency distributions under varying payload sizes and publish rates, and demonstrate automatic stream resumption after hard crashes and restarts even with shared-memory loss. Overall, ANCHOR turns ad-hoc integration glue into explicit contracts, enabling controlled degradation under load and self-healing recovery for scalable deployment of closed-loop AI systems.