Deep Reinforcement Learning With Dynamic Graphs for Adaptive Informative Path Planning

Journal Article (2024)
Author(s)

Apoorva Vashisth (Indian Institute of Technology Kharagpur)

Julius Rückin (Universität Bonn)

Federico Magistri (Universität Bonn)

Cyrill Stachniss (Universität Bonn, University of Oxford)

M. Popović (Universität Bonn, TU Delft - Control & Simulation)

Research Group
Control & Simulation
DOI related publication
https://doi.org/10.1109/LRA.2024.3421188
More Info
expand_more
Publication Year
2024
Language
English
Research Group
Control & Simulation
Issue number
9
Volume number
9
Pages (from-to)
7747-7754
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

Autonomousrobots 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.

Files

Deep_Reinforcement_Learning_Wi... (pdf)
(pdf | 1.5 Mb)
- Embargo expired in 06-01-2025
License info not available