Sequential Bayesian Optimisation as a POMDP for Environment Monitoring with UAVs

TL;DR

This paper introduces a novel approach combining Bayesian Optimization with POMDPs and Monte-Carlo Tree Search to enable UAVs to efficiently monitor environments while respecting physical and trajectory constraints.

Contribution

It formulates Bayesian Optimization as a POMDP for continuous trajectories and adapts MCTS for solving it, addressing practical constraints in robotic environment monitoring.

Findings

BO-POMDP outperforms existing methods in UAV environment monitoring

The approach effectively balances exploration and exploitation

Experiments demonstrate improved sampling efficiency

Abstract

Bayesian Optimisation has gained much popularity lately, as a global optimisation technique for functions that are expensive to evaluate or unknown a priori. While classical BO focuses on where to gather an observation next, it does not take into account practical constraints for a robotic system such as where it is physically possible to gather samples from, nor the sequential nature of the problem while executing a trajectory. In field robotics and other real-life situations, physical and trajectory constraints are inherent problems. This paper addresses these issues by formulating Bayesian Optimisation for continuous trajectories within a Partially Observable Markov Decision Process (POMDP) framework. The resulting POMDP is solved using Monte-Carlo Tree Search (MCTS), which we adapt to using a reward function balancing exploration and exploitation. Experiments on monitoring a spatial phenomenon with a UAV illustrate how our BO-POMDP algorithm outperforms competing techniques.