Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation

• URL: http://arxiv.org/abs/2603.19418v1
• Date: Thu, 19 Mar 2026 19:24:14 GMT
• Title: Speculative Policy Orchestration: A Latency-Resilient Framework for Cloud-Robotic Manipulation
• Abstract summary: Cloud robotics enables robots to offload high-dimensional motion planning and reasoning to remote servers.<n>For continuous manipulation tasks requiring high-frequency control, network latency and jitter can severely destabilize the system.<n>We propose Speculative Policy Orchestration (SPO), a latency-resilient cloud-edge framework.
• Score: 6.709418204725671
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• DriveCache: Action-Aware Caching for Driving World Model Inference [61.07117287683939]
  Diffusion-based driving generators evaluate large backbones across denoising steps, which limits generation throughput.<n>Existing diffusion acceleration methods reduce this cost, but general-purpose designs omit driving signals available before generation, such as ego speed and planned trajectories.<n>We propose DriveCache, a training-free, action-aware controller that uses planned motion to allocate reuse across scenes and dynamic programming to place it across denoising steps under a calibrated response budget.
  arXiv  Detail & Related papers  (2026-08-17T10:04:49Z)
• Latency-Tolerant Cloud-Edge Collaborative Vision-Language-Action Models via Emergent Representational Specialization [6.831202558046453]
  We introduce CloudEdgeVLA, a cloud-edge policy that treats temporal misalignment as a representation-learning problem.<n>A lightweight edge head combines the latest available cloud feature with current local vision.<n>CloudEdgeVLA retains 63.8--78.0% success with a 40-step uniform-delay window.
  arXiv  Detail & Related papers  (2026-08-01T10:11:59Z)
• Action ControlNet: A Lightweight Delay-Aware Adapter for Smooth Asynchronous Control in Vision-Language-Action Models [2.1822977353368778]
  Action ControlNet (ACNet) is a lightweight delay-aware adapter for vision-language--action models.<n>ACNet improves robustness under inference delay and yields smoother asynchronous trajectories than direct chunk stitching.
  arXiv  Detail & Related papers  (2026-06-24T15:53:43Z)
• Edge-Based QoS-Aware Adaptive Task Placement: A Closed-Loop Control in Multi-Robot Systems [5.480084037947013]
  We present a pilot edge-centric MRS testbed using Raspberry Pi nodes to evaluate a camera-to-manipulator pipeline.<n>Results show that ATP-aware controller, by switching task placement based on measured latency and utilization thresholds, consistently lowers deadline violations and tail latency.
  arXiv  Detail & Related papers  (2026-05-30T05:54:44Z)
• AsyncShield: A Plug-and-Play Edge Adapter for Asynchronous Cloud-based VLA Navigation [21.033021862213825]
  AsyncShield is a plug-and-play control framework for asynchronous navigation.<n>System uses a constrained Markov decision process to balance intent restoration fidelity and physical safety.<n>AsyncShield operates as a lightweight, plug-and-play module.
  arXiv  Detail & Related papers  (2026-04-27T06:20:15Z)
• DexWorldModel: Causal Latent World Modeling towards Automated Learning of Embodied Tasks [54.32016216994156]
  We introduce the Causal Latent World Model (CLWM), which employs DINOv3 features as generative targets to disentangle interaction semantics from visual noise.<n>To overcome memory scaling, CLWM features a Dual-State Test-Time Training (TTT) Memory that guarantees a strict $mathcalO(1)$ footprint for long-horizon tasks.<n>We present EmbodiChain, an online framework that establishes the Efficiency Law by injecting an infinite flow of physics-grounded trajectories during training.
  arXiv  Detail & Related papers  (2026-04-13T03:19:36Z)
• Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference [3.9986079633630975]
  Deep neural networks (DNNs) in cyber-physical systems (CPS) enhance perception fidelity, but impose substantial computational demands on execution platforms.<n>Traditional distributed CPS architectures favor on-device inference to avoid network variability and contention-induced delays on remote platforms.<n>In this work, we revisit the assumption that cloud-based inference is intrinsically unsuitable for latency-sensitive control tasks.
  arXiv  Detail & Related papers  (2026-02-17T20:44:13Z)
• AsyncVLA: An Asynchronous VLA for Fast and Robust Navigation on the Edge [49.66156306240961]
  High latency breaks the control loop, rendering powerful models unsafe for real-time deployment.<n>We propose AsyncVLA, an asynchronous control framework that decouples semantic reasoning from reactive execution.<n>AsyncVLA achieves a 40% higher success rate than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-02-13T21:31:19Z)
• Time Is All It Takes: Spike-Retiming Attacks on Event-Driven Spiking Neural Networks [87.16809558673403]
  Spiking neural networks (SNNs) compute with discrete spikes and exploit temporal structure.<n>We study a timing-only adversary that retimes existing spikes while preserving spike counts and amplitudes in event-driven SNNs.
  arXiv  Detail & Related papers  (2026-02-03T09:06:53Z)
• Vision-Language Models on the Edge for Real-Time Robotic Perception [0.22940141855172028]
  Edge intelligence within 6G, particularly Open RAN and Multi-access Edge Computing, offers a pathway to address these challenges.<n>This work investigates the deployment of Vision-Language Models on ORAN/MEC infrastructure using the Unitree G1 humanoid robot as an embodied testbed.<n>Our results show that edge deployment preserves near-cloud accuracy while reducing end-to-end latency by 5%.
  arXiv  Detail & Related papers  (2026-01-21T12:09:48Z)
• A Practical Honeypot-Based Threat Intelligence Framework for Cyber Defence in the Cloud [0.3714118205123091]
  We introduce an automated defense framework that dynamically update firewall rules in real time.<n>The framework integrates deception sensors (Cowrie), Azure-native automation tools (Monitor, Sentinel, Logic Apps), and MITRE ATT&CK-aligned detection.
  arXiv  Detail & Related papers  (2025-12-04T23:39:25Z)
• CSGO: Generalized Optimization for Cold Start in Wireless Collaborative Edge LLM Systems [62.24576366776727]
  We propose a latency-aware scheduling framework to minimize total inference latency.<n>We show that the proposed method significantly reduces cold-start latency compared to baseline strategies.
  arXiv  Detail & Related papers  (2025-08-15T07:49:22Z)
• Real-Time Execution of Action Chunking Flow Policies [49.1574468325115]
  This paper presents a novel inference-time algorithm that enables asynchronous execution of action interacting systems.<n>It is applicable to any diffusion- or VLA-based systems executing out of the box with no re-training.<n>Results show that RTC is fast, performant, and uniquely robust to inference manipulation.
  arXiv  Detail & Related papers  (2025-06-09T01:01:59Z)
• Can't Slow me Down: Learning Robust and Hardware-Adaptive Object Detectors against Latency Attacks for Edge Devices [21.359326502877487]
  A new class of latency attacks are reported recently targeting the real-time processing capability of object detectors.<n>We take an initial attempt to defend against this attack via background-attentive adversarial training.<n>Experiments demonstrate the defense effectiveness of restoring real-time processing capability from $13$ FPS to $43$ FPS.
  arXiv  Detail & Related papers  (2024-12-03T05:00:26Z)
• Overload: Latency Attacks on Object Detection for Edge Devices [47.9744734181236]
  This paper investigates latency attacks on deep learning applications. Unlike common adversarial attacks for misclassification, the goal of latency attacks is to increase the inference time. We use object detection to demonstrate how such kind of attacks work.
  arXiv  Detail & Related papers  (2023-04-11T17:24:31Z)
• Delay-Tolerant Constrained OCO with Application to Network Resource Allocation [44.67787270821051]
  We consider online convex optimization (OCO) with multi-slot feedback delay. An agent makes a sequence of online decisions to minimize the accumulation of time-varying convex loss functions. We propose Delay-Tolerant Constrained-OCO, which uses a novel constraint penalty with double regularization to tackle the asynchrony between information feedback and decision updates.
  arXiv  Detail & Related papers  (2021-05-09T19:32:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.