Multi-Robot Information Gathering for Spatiotemporal Environment Modelling

Abstract

Learning to predict or forecast spatiotemporal (ST) environmental processes from a sparse set of samples collected autonomously is a difficult task from both a sampling perspective (collecting the best sparse samples) and from a learning perspective (predicting unseen locations or forecasting the next timestep). We investigate two avenues of work concerning this problem. Firstly, we investigate coordinating a team of robots to adaptively sample a spatiotemporal environment to procure a dataset for learning a parametric neural model for forecasting. Recent work in spatiotemporal process learning focuses on using deep learning to forecast from dense samples. Moreover, collecting the best set of sparse samples is understudied within robotics. An example of this is robotic sampling for information gathering, such as using UAVs/UGVs for weather monitoring. Thus, we propose a methodology that leverages a neural methodology called Recurrent Neural Processes to learn spatiotemporal environmental dynamics for forecasting from selective samples gathered by a team of robots using a mixture of Gaussian Processes model in an online learning fashion. Thus, we combine two learning paradigms in that we use an active learning approach to adaptively gather informative samples and a supervised learning approach to capture and predict complex spatiotemporal environmental phenomena. Secondly, we investigate the multi-robot informative path planning problem by leveraging a multi-robot spatiotemporal adaptive sampling scheme and integrating informative path planning in a coordinated manner. Thus, we focus on investigating the sample collection process via multi-robot informative path planning. We present an approach for incorporating multi-robot informative path planning into a spatiotemporal adaptive sampling framework. We demonstrate this by modifying our previous methodology to consider path length constraints for sampling location selection. We also incorporate informative path planning to determine the best path to collect samples along while en route to collecting the desired sample. We achieve this in a decentralized manner by decoupling the process into two stages: the first stage uses our spatiotemporal mixture of Gaussian Processes (STMGP) model to determine the most informative sampling location via a mutual information lower bound heuristic and the second stage plans an informative path to collect the desired sample and other additional informative samples via submodular function optimization. Moreover, we effectively leverage peer-to-peer communication to enable coordination. Simulation results are provided to validate the effectiveness of our proposed approaches.