Reinforcement Learning-Based Multi-AUV Adaptive Trajectory Planning for Under-Ice Field Estimation

• Published in: Sensors (Basel, Switzerland) Vol. 18; no. 11; p. 3859
• Main Authors: Wang, Chaofeng, Wei, Li, Wang, Zhaohui, Song, Min, Mahmoudian, Nina
• Format: Journal Article
• Language: English
• Published: Switzerland MDPI 09.11.2018; MDPI AG
• Subjects: adaptive trajectory planning; AUVs; field estimation; reinforcement learning; under-ice exploration; underwater communication networks; under-ice exploration; adaptive trajectory planning; field estimation; AUVs; reinforcement learning; underwater communication networks
• ISSN: 1424-8220; 1424-8220
• DOI: 10.3390/s18113859

This work studies online learning-based trajectory planning for multiple autonomous underwater vehicles (AUVs) to estimate a water parameter field of interest in the under-ice environment. A centralized system is considered, where several fixed access points on the ice layer are introduced as gateways for communications between the AUVs and a remote data fusion center. We model the water parameter field of interest as a Gaussian process with unknown hyper-parameters. The AUV trajectories for sampling are determined on an epoch-by-epoch basis. At the end of each epoch, the access points relay the observed field samples from all the AUVs to the fusion center, which computes the posterior distribution of the field based on the Gaussian process regression and estimates the field hyper-parameters. The optimal trajectories of all the AUVs in the next epoch are determined to maximize a long-term reward that is defined based on the field uncertainty reduction and the AUV mobility cost, subject to the kinematics constraint, the communication constraint and the sensing area constraint. We formulate the adaptive trajectory planning problem as a Markov decision process (MDP). A reinforcement learning-based online learning algorithm is designed to determine the optimal AUV trajectories in a constrained continuous space. Simulation results show that the proposed learning-based trajectory planning algorithm has performance similar to a benchmark method that assumes perfect knowledge of the field hyper-parameters.