Cognitive GPR for Subsurface Object Detection Based on Deep Reinforcement Learning

Abstract

Ground penetrating radars (GPRs) carried by mobile platforms, such as vehicles and drones, have been applied in various applications, for instance, subsurface utility detection, structural health inspection, and autonomous driving. However, existing GPR systems are not able to operate autonomously and adaptively due to several challenges, including the lack of intelligence, uncertain and dynamic nature of sensing environments, and huge state and action spaces. To overcome these challenges, in this article, we propose an autonomous cognitive GPR (AC-GPR) enabled by a deep reinforcement learning (DRL) approach. Specifically, the operation of the proposed AC-GPR is first formulated as a sequential decision process. A novel reward function is developed for the DRL model by defining and combining two different types of entropy-based rewards resulting from object detection and recognition, respectively. A deep Q-learning network (DQN) is developed to address the extreme curse of dimensionality in the state space and learn a policy directing the actions of the AC-GPR. The AC-GPR is evaluated using software called GprMax by combining DRL with GPR modeling and simulation. Results show that our proposed DRL-based AC-GPR outperforms other GPR systems using different approaches in terms of detection accuracy and operating time.