Adaptive Informative Path Planning Using Deep Reinforcement Learning for UAV-based Active Sensing

Aerial robots are increasingly being utilized for environmental monitoring and exploration. However, a key challenge is efficiently planning paths to maximize the information value of acquired data as an initially unknown environment is explored. To address this, we propose a new approach for informative path planning based on deep reinforcement learning (RL). Combining recent advances in RL and robotic applications, our method combines tree search with an offline-learned neural network predicting informative sensing actions. We introduce several components making our approach applicable for robotic tasks with high-dimensional state and large action spaces. By deploying the trained network during a mission, our method enables sample-efficient online replanning on platforms with limited computational resources. Simulations show that our approach performs on par with existing methods while reducing runtime by 8 - 10x. We validate its performance using real-world surface temperature data.

Automated summary

Aerial robots are being used more often for environmental monitoring and exploration, but efficiently planning paths to maximize the value of collected data in unknown environments is a challenge. To tackle this problem, the authors propose a new approach for informative path planning using deep reinforcement learning. By combining tree search with an offline-learned neural network, their method is able to handle high-dimensional state and large action spaces. Simulation results show that the approach performs as well as existing methods while reducing runtime by 8-10x.