Visual Sensor Network Reconfiguration with Deep Reinforcement Learning
This addresses the challenge of efficient sensor network management for surveillance or monitoring applications, but it appears incremental as it builds on existing RL methods and simulation techniques.
The paper tackles the problem of reconfiguring dynamic visual sensor networks by using deep reinforcement learning, achieving validation in a real-world scenario with preexisting object detection and tracking algorithms.
We present an approach for reconfiguration of dynamic visual sensor networks with deep reinforcement learning (RL). Our RL agent uses a modified asynchronous advantage actor-critic framework and the recently proposed Relational Network module at the foundation of its network architecture. To address the issue of sample inefficiency in current approaches to model-free reinforcement learning, we train our system in an abstract simulation environment that represents inputs from a dynamic scene. Our system is validated using inputs from a real-world scenario and preexisting object detection and tracking algorithms.