拆分感知与生成模块，实现高效异步推理，提升智能体响应速度。
Boosting Embodied AI Agents through Perception-Generation Disaggregation and Asynchronous Pipeline Execution
- 将感知与生成分离，采用异步流水线并行处理
- 平均吞吐量提升2.54倍，精度保持在原模型的102.7%
- 适合对实时性要求高的机器人、虚拟代理等场景
具身智能系统需在动态环境中处理高频输入输出。传统串行计算虽保证精度，但难以满足真实应用所需的“思考”频率。本文提出Auras——一种算法与系统协同设计的推理框架，通过拆分感知与生成模块，并引入受控流水线并行，实现高且稳定的吞吐量。针对并行带来的数据过时问题，Auras构建共享公共上下文，保障智能体精度。实验表明，Auras平均吞吐量提升2.54倍，同时保持原模型102.7%的精度，有效突破串行计算瓶颈。
原文摘要 · Abstract (English)
Embodied AI systems operate in dynamic environments, requiring seamless integration of perception and generation modules to process high-frequency input and output demands. Traditional sequential computation patterns, while effective in ensuring accuracy, face significant limitations in achieving the necessary "thinking" frequency for real-world applications. In this work, we present Auras, an algorithm-system co-designed inference framework to optimize the inference frequency of embodied AI agents. Auras disaggregates the perception and generation and provides controlled pipeline parallelism for them to achieve high and stable throughput. Faced with the data staleness problem that appears when the parallelism is increased, Auras establishes a public context for perception and generation to share, thereby promising the accuracy of embodied agents. Experimental results show that Auras improves throughput by 2.54x on average while achieving 102.7% of the original accuracy, demonstrating its efficacy in overcoming the constraints of sequential computation and providing high throughput.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。