面向边缘设备上主动感知的智能自适应智能体研究
Towards smart and adaptive agents for active sensing on edge devices
AI总结：
针对边缘设备上深度学习模型适应性不足、缩放定律无法适用的问题，本文提出融入主动推理的智能体系统，可在低内存占用下实现边缘主动感知，并通过NVIDIA Jetson设备上的扫视智能体重现类人扫视运动验证了有效性。
摘要：
TinyML（微型机器学习）已让深度学习模型在低功耗边缘设备上的部署成为可能，为受限环境下的实时感知创造了新机遇。然而，这类深度学习方法的适应性仍局限于数据漂移适配，缺乏考量环境底层动态特性与固有不确定性的更广泛能力。深度学习的缩放定律通过大幅提升数据与模型规模来弥补这一局限，但该定律无法应用于边缘部署场景——在边缘端，为适配资源受限设备而缩小模型规模时，深度学习的局限性会被进一步放大。\n本文提出了一种创新的智能体系统，能够执行设备端感知与规划，实现边缘侧的主动感知。通过将主动推理（active inference）融入解决方案，我们的方法突破了深度学习的能力边界，使系统能在动态环境中规划，同时实时运行，内存占用仅低至300 MB。我们通过在NVIDIA Jetson嵌入式设备上构建并部署一个连接带云台功能的IoT摄像头的扫视智能体（saccade agent），对所提系统进行了验证。该扫视智能体遵循由主动推理原理推导的最优策略控制摄像头的视场，模拟类人扫视运动，可应用于监控和机器人领域。
英文摘要：
TinyML has made deploying deep learning models on low-power edge devices feasible, creating new opportunities for real-time perception in constrained environments. However, the adaptability of such deep learning methods remains limited to data drift adaptation, lacking broader capabilities that account for the environment's underlying dynamics and inherent uncertainty. Deep learning's scaling laws, which counterbalance this limitation by massively up-scaling data and model size, cannot be applied when deploying on the Edge, where deep learning limitations are further amplified as models are scaled down for deployment on resource-constrained devices. This paper presents an innovative agentic system capable of performing on-device perception and planning, enabling active sensing on the edge. By incorporating active inference into our solution, our approach extends beyond deep learning capabilities, allowing the system to plan in dynamic environments while operating in real-time with a compact memory footprint of as little as 300 MB. We showcase our proposed system by creating and deploying a saccade agent connected to an IoT camera with pan and tilt capabilities on an NVIDIA Jetson embedded device. The saccade agent controls the camera's field of view following optimal policies derived from the active inference principles, simulating human-like saccadic motion for surveillance and robotics applications.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
