# Adaptive Selection of Informative Path Planning Strategies via Reinforcement Learning

arXiv: https://arxiv.org/abs/2108.06618 · HTML: https://mlsanity.com/paper/2108.06618/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 16 references that are in the map.
- First posted on arXiv 14 Aug 2021.

## Builds on (most cited first, 7 of 7)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [Learning how to Active Learn: A Deep Reinforcement Learning Approach](https://mlsanity.com/paper/1708.02383/) (2017)
- [Informative Planning and Online Learning with Sparse Gaussian Processes](https://mlsanity.com/paper/1609.07560/) (2016)
- [Informative Path Planning for Mobile Sensing with Reinforcement Learning](https://mlsanity.com/paper/2002.07890/) (2020)
- [Kriging-Based Robotic Exploration for Soil Moisture Mapping Using a Cosmic-Ray Sensor](https://mlsanity.com/paper/1811.05384/) (2018)
- [Blending Controllers via Multi-Objective Bandits](https://mlsanity.com/paper/2007.15755/) (2020)
- [3D Soil Compaction Mapping through Kriging-based Exploration with a Mobile Robot](https://mlsanity.com/paper/1803.08069/) (2018)

## Built on by (most cited first, 2 of 2)

- [Deep Reinforcement Learning with Dynamic Graphs for Adaptive Informative Path Planning](https://mlsanity.com/paper/2402.04894/) (2024)
- [DyPNIPP: Predicting Environment Dynamics for RL-based Robust Informative Path Planning](https://mlsanity.com/paper/2410.17186/) (2024)

## Abstract (arXiv)

In our previous work, we designed a systematic policy to prioritize sampling locations to lead significant accuracy improvement in spatial interpolation by using the prediction uncertainty of Gaussian Process Regression (GPR) as "attraction force" to deployed robots in path planning. Although the integration with Traveling Salesman Problem (TSP) solvers was also shown to produce relatively short travel distance, we here hypothesise several factors that could decrease the overall prediction precision as well because sub-optimal locations may eventually be included in their paths. To address this issue, in this paper, we first explore "local planning" approaches adopting various spatial ranges within which next sampling locations are prioritized to investigate their effects on the prediction performance as well as incurred travel distance. Also, Reinforcement Learning (RL)-based high-level controllers are trained to adaptively produce blended plans from a particular set of local planners to inherit unique strengths from that selection depending on latest prediction states. Our experiments on use cases of temperature monitoring robots demonstrate that the dynamic mixtures of planners can not only generate sophisticated, informative plans that a single planner could not create alone but also ensure significantly reduced travel distances at no cost of prediction reliability without any assist of additional modules for shortest path calculation.