Sequential Bayesian Optimization for Adaptive Informative Path Planning with Multimodal Sensing

TL;DR

This paper introduces a sequential Bayesian optimization method for adaptive informative path planning with multimodal sensing, effectively balancing sensing accuracy, energy costs, and resource constraints in complex environments.

Contribution

It formulates the AIPPMS problem as a belief MDP with Gaussian process beliefs and provides an online planning solution that outperforms previous methods.

Findings

Doubled average reward in experiments

Reduced belief error by 50%

Outperformed previous solutions significantly

Abstract

Adaptive Informative Path Planning with Multimodal Sensing (AIPPMS) considers the problem of an agent equipped with multiple sensors, each with different sensing accuracy and energy costs. The agent's goal is to explore the environment and gather information subject to its resource constraints in unknown, partially observable environments. Previous work has focused on the less general Adaptive Informative Path Planning (AIPP) problem, which considers only the effect of the agent's movement on received observations. The AIPPMS problem adds additional complexity by requiring that the agent reasons jointly about the effects of sensing and movement while balancing resource constraints with information objectives. We formulate the AIPPMS problem as a belief Markov decision process with Gaussian process beliefs and solve it using a sequential Bayesian optimization approach with online planning. Our approach consistently outperforms previous AIPPMS solutions by more than doubling the average reward received in almost every experiment while also reducing the root-mean-square error in the environment belief by 50%. We completely open-source our implementation to aid in further development and comparison.