Skip to content

论文arXiv 2611.191315 天前

WEALR框架:无线边缘辅助VLA自适应潜在推理提升23%任务成功率 ​

本文由 AI 根据公开内容整理,可能有误,请以原文为准:Wireless Edge-Assisted Adaptive Latent Reasoning for Vision-Language-Action Models in Physical AI(arXiv 2611.19131)

核心内容 ​

针对视觉-语言-动作(VLA)模型在物理AI应用中面临的端侧资源受限与实时控制矛盾,研究团队提出无线边缘辅助自适应潜在推理框架WEALR。该方案旨在解决测试时扩展(Test-time scaling)引入的推理延迟与能耗权衡问题,通过边缘计算增强本体算力。实验基于LIBERO操作任务、VLA推理成本画像及光线追踪无线信道模型进行验证,结果显示采用TRPO-Lag算法的策略在复杂通信条件下,取得了较基准约束马尔可夫决策过程(CMDP)方法高出23%的可行性加权任务成功率。

技术架构上,WEALR将执行位置选择与潜在推理收敛阈值的联合适配建模为CMDP,并设计拉格朗日约束深度强化学习算法TRPO-Lag进行求解。决策智能体根据动态无线信道状态与任务需求,自适应分配端云负载并调整隐式推理深度,避免了显式思维链(CoT)生成的额外开销。该方法在不增加本体硬件成本的前提下,通过算法层面的通信-计算协同,实现了VLA模型在带宽波动环境下的稳定推理与能效最优。

关键看点 ​

  • TRPO-Lag算法:采用拉格朗日约束信任域策略优化,在CMDP框架下联合决策推理位置与收敛阈值,平衡任务性能与资源消耗。
  • 性能量化指标:在LIBERO基准测试中,可行性加权任务成功率较现有CDRL方法提升23%,验证了边缘协同对VLA推理的有效性。
  • 自适应潜在推理:通过调节隐层表示收敛阈值替代显式CoT生成,在保障推理质量的同时显著降低通信带宽占用与端侧计算负载。
  • 真实通信仿真:集成光线追踪无线信道模型与VLA推理成本画像,确保算法在动态网络条件下的鲁棒性与工程落地参考价值。

工程与产业观察 ​

该研究为具身大模型端侧部署提供了通信-计算协同的新范式。通过算法自适应调节推理深度与卸载策略,解决了VLA模型在弱网或算力受限场景下的实时性难题。对于机器人系统集成商而言,这意味着可在不升级昂贵机载芯片的情况下,利用边缘基础设施保障复杂任务的执行成功率,降低了具身智能终端的硬件BOM成本门槛。

英文摘要 (Abstract) ​

Vision-language-action (VLA) models enable embodied artificial intelligence (AI) by translating visual observations and language instructions into robotic actions. Emerging use cases in physical AI are expected to drive the need for efficient inference and communication, as the computational demands of the VLA models pose challenges for real-time control with limited onboard resources. Test-time scaling through latent reasoning allows these models to refine hidden representations without generating explicit chain-of-thought (CoT) tokens, but introduces a trade-off between task success, inference latency, and energy consumption. In this paper, we address the efficient collaborative inference under a realistic communication scenario. We propose a wireless edge-assisted framework for adaptive latent reasoning (WEALR) that augments onboard computation with edge computing. A decision-making agent jointly selects the execution location and latent-reasoning convergence threshold. We formulate this joint adaptation as a constrained Markov decision process (CMDP). A Lagrangian-constrained deep reinforcement learning (CDRL) approach, namely trust region policy optimization Lagrangian (TRPO-Lag), learns to balance task performance and resource consumption under varying wireless conditions and task requirements. We evaluate the framework using LIBERO manipulation tasks, profiled VLA inference costs, and ray-traced wireless channels. Experimental results demonstrate that TRPO-Lag achieves up to 23% higher feasibility-weighted task success rate compared to benchmark CDRL methods.

作者:Fatih Temiz, Melike Erol-Kantarci

基于本页技术方向关联的整机参数、核心零部件、实测报告与同赛道选型横评。

外部来源

本页事实对应的公开页面,以原文为准。(点击将离开本站)

  1. arXiv 2611.19131:Wireless Edge-Assisted Adaptive Latent Reasoning for Vision-Language-Action Models in Physical AI ↗访问 2026-11-18