Cloud-hosted foundation models enable robots to use semantic reasoning beyond onboard computational limits. In this setting, the robot executes a currently available primitive generated by the cloud, and uninterrupted task progress requires the next cloud result before this primitive is exhausted. This execution becomes fragile under spatially heterogeneous connectivity, because the current primitive determines when the next result is needed, whereas the wireless environment determines where the next request can be submitted and where the response can be retrieved. To address this problem, we introduce the request--response window, which characterizes the time required for the next cloud cycle, including uplink transmission, cloud inference, downlink retrieval, and inference uncertainty. Building on this window and an available communication map, the proposed framework treats the next request point as a motion decision during ongoing primitive execution, selecting it to provide sufficient communication quality for cloud request submission while preserving progress within the finite support of the current primitive. The selected request point is incorporated into a local planner, which guides the robot toward it before submission and then uses communication and arrival time penalties while the response is pending. Experiments in a simulated indoor wireless scenario with a measurement-based communication map and emulated cloud inference show that the proposed method achieves the highest task success and lowest request failure rates among the compared methods. The request point ablation further supports the contribution of selecting submission locations to execution continuity under spatially varying connectivity.

翻译：暂无翻译