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.

翻译：TinyML技术使得在低功耗边缘设备上部署深度学习模型成为可能，为受限环境下的实时感知创造了新机遇。然而，此类深度学习方法的适应性仍局限于数据漂移适应，缺乏考虑环境潜在动态特性和固有不确定性的更广泛能力。深度学习的缩放定律通过大规模扩展数据和模型规模来抵消这一局限性，但在边缘部署场景中无法适用——当模型为部署于资源受限设备而缩小时，深度学习的局限性会被进一步放大。本文提出了一种创新的代理系统，能够执行设备端感知与规划，实现边缘端的主动感知。通过将主动推理融入解决方案，我们的方法超越了深度学习的能力范畴，使系统能够在动态环境中进行规划，并以低至300MB的紧凑内存占用实现实时运行。我们通过创建并部署连接云台物联网摄像头的扫视代理（部署于NVIDIA Jetson嵌入式设备）来展示所提出的系统。该扫视代理依据主动推理原理推导的最优策略控制摄像机视场，模拟类人扫视运动，可应用于监控和机器人领域。