Towards smart and adaptive agents for active sensing on edge devices
cs.RO, cs.AI, eess.IV
Submitted: 2025-01-09
Updated: 2025-10-16
Journal ref: Pervasive Intelligence - From Architectures to Sustainable Edge AI Systems-of-Systems 2026
DOI: 10.13052/rp-9788743815204
Code: https://github.com/onnx/onnx
License: http://creativecommons.org/licenses/by/4.0/
The gist: TinyML has made deploying deep learning models on low-power edge devices feasible, creating new opportunities for real-time perception in constrained environments.
Terminology
Abstract
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.
Sources
- On-Device Domain Learning for Keyword Spotting on Low-Power Extreme Edge Embedded Systems
- YOLOv10: Real-Time End-to-End Object Detection
- pymdp: A Python library for active inference in discrete state spaces
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
- Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving