Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning
This addresses the problem of efficient robotic data collection in unknown 3D environments for applications like orchard monitoring, representing an incremental improvement over existing methods.
The paper tackles adaptive online path planning for robots in unknown 3D environments by proposing a deep reinforcement learning approach with a dynamic graph to restrict actions locally and a new reward function balancing exploration and exploitation, resulting in more efficient target discovery compared to state-of-the-art baselines.
Autonomous robots are often employed for data collection due to their efficiency and low labour costs. A key task in robotic data acquisition is planning paths through an initially unknown environment to collect observations given platform-specific resource constraints, such as limited battery life. Adaptive online path planning in 3D environments is challenging due to the large set of valid actions and the presence of unknown occlusions. To address these issues, we propose a novel deep reinforcement learning approach for adaptively replanning robot paths to map targets of interest in unknown 3D environments. A key aspect of our approach is a dynamically constructed graph that restricts planning actions local to the robot, allowing us to react to newly discovered static obstacles and targets of interest. For replanning, we propose a new reward function that balances between exploring the unknown environment and exploiting online-discovered targets of interest. Our experiments show that our method enables more efficient target discovery compared to state-of-the-art learning and non-learning baselines. We also showcase our approach for orchard monitoring using an unmanned aerial vehicle in a photorealistic simulator. We open-source our code and model at: https://github.com/dmar-bonn/ipp-rl-3d.