Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866908901855723520 |
|---|---|
| author | Nguyen, Chanh Jin, Shutong Pokorny, Florian T. Elmroth, Erik |
| author_facet | Nguyen, Chanh Jin, Shutong Pokorny, Florian T. Elmroth, Erik |
| contents | Cloud robotics enables robots to offload high-dimensional motion planning and reasoning to remote servers. However, for continuous manipulation tasks requiring high-frequency control, network latency and jitter can severely destabilize the system, causing command starvation and unsafe physical execution.
To address this, we propose Speculative Policy Orchestration (SPO), a latency-resilient cloud-edge framework. SPO utilizes a cloud-hosted world model to pre-compute and stream future kinematic waypoints to a local edge buffer, decoupling execution frequency from network round-trip time. To mitigate unsafe execution caused by predictive drift, the edge node employs an $ε$-tube verifier that strictly bounds kinematic execution errors. The framework is coupled with an Adaptive Horizon Scaling mechanism that dynamically expands or shrinks the speculative pre-fetch depth based on real-time tracking error.
We evaluate SPO on continuous RLBench manipulation tasks under emulated network delays. Results show that even when deployed with learned models of modest accuracy, SPO reduces network-induced idle time by over 60% compared to blocking remote inference. Furthermore, SPO discards approximately 60% fewer cloud predictions than static caching baselines. Ultimately, SPO enables fluid, real-time cloud-robotic control while maintaining bounded physical safety. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_19418 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation Nguyen, Chanh Jin, Shutong Pokorny, Florian T. Elmroth, Erik Robotics Distributed, Parallel, and Cluster Computing Cloud robotics enables robots to offload high-dimensional motion planning and reasoning to remote servers. However, for continuous manipulation tasks requiring high-frequency control, network latency and jitter can severely destabilize the system, causing command starvation and unsafe physical execution. To address this, we propose Speculative Policy Orchestration (SPO), a latency-resilient cloud-edge framework. SPO utilizes a cloud-hosted world model to pre-compute and stream future kinematic waypoints to a local edge buffer, decoupling execution frequency from network round-trip time. To mitigate unsafe execution caused by predictive drift, the edge node employs an $ε$-tube verifier that strictly bounds kinematic execution errors. The framework is coupled with an Adaptive Horizon Scaling mechanism that dynamically expands or shrinks the speculative pre-fetch depth based on real-time tracking error. We evaluate SPO on continuous RLBench manipulation tasks under emulated network delays. Results show that even when deployed with learned models of modest accuracy, SPO reduces network-induced idle time by over 60% compared to blocking remote inference. Furthermore, SPO discards approximately 60% fewer cloud predictions than static caching baselines. Ultimately, SPO enables fluid, real-time cloud-robotic control while maintaining bounded physical safety. |
| title | Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation |
| topic | Robotics Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2603.19418 |