Exploration–Exploitation Tradeoff in the Adaptive Information Sampling of Unknown Spatial Fields with Mobile Robots

Aiman Munir, Ramviyas Parasuraman, Andrey V Savkin · 2023

Read Exploration–Exploitation Tradeoff in the Adaptive Information Sampling of Unknown Spatial Fields with Mobile Robots by Aiman Munir, Ramviyas Parasuraman, Andrey V Savkin (2023) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-10708738.txt.

Description

Aiman Munir and co-authors study how mobile robots should balance exploring a space against using what they have already learned, in a 2023 paper. Robots that sample a field, such as radiation spread, must pick waypoints that teach them the most. Past work often assumed endless energy or equal batteries across robots. This team asks how the balance point shifts when energy is a real limit.

They use a standard statistical method to forecast the field and its uncertainty at each point. Sweeping the settings of the sampling rule, they log map accuracy, doubt width, energy spent, and time taken, for lone robots and teams alike. Giving weight only to uncertainty, they warn, blows up energy use. Giving weight only to the forecast mean wastes chances to learn. The paper ends with guidance for picking settings by goal, whether that goal is finding a source or mapping a whole field.

Catalog record

CREATORAiman Munir, Ramviyas Parasuraman, Andrey V Savkin
YEAR2023
COLLECTIONPAPERS
FORMATTXT
FILE SIZE61 KB
VERSION1.0
LICENSECC BY 4.0
RIGHTSCC BY
SOURCEEurope PMC

Source: https://europepmc.org/articles/PMC10708738

Browse the full library · About the Tower of Babel