Adaptive Robotic Information Gathering via non-stationary Gaussian processes
The International Journal of Robotics Research · 2024-04 · 43 (4) · 405-436
DOI: 10.1177/02783649231184498 ↗Kurz gefasst
Fachartikel in der Zeitschrift The International Journal of Robotics Research, online erschienen am 27.06.2023. Verfasst von Weizhe Chen und 2 weiteren Autor:innen. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 178 Literaturangaben. Gefördert von: RI: Small: Exploiting Symmetries of Decision-Theoretic Planning for Autonomous Vehicles, III: Small: Algorithms and Theoretical Foundations for Approximate Bayesian Inference in Machine Learning, CAREER: Autonomous Live Sketching of Dynamic Environments by Exploiting Spatiotemporal Variations.
Abstract (Originalsprache)
Robotic Information Gathering (RIG) is a foundational research topic that answers how a robot (team) collects informative data to efficiently build an accurate model of an unknown target function under robot embodiment constraints. RIG has many applications, including but not limited to autonomous exploration and mapping, 3D reconstruction or inspection, search and rescue, and environmental monitoring. A RIG system relies on a probabilistic model’s prediction uncertainty to identify critical areas for informative data collection. Gaussian processes (GPs) with stationary kernels have been widely adopted for spatial modeling. However, real-world spatial data is typically non-stationary —different locations do not have the same degree of variability. As a result, the prediction uncertainty does not accurately reveal prediction error, limiting the success of RIG algorithms. We propose a family of non-stationary kernels named Attentive Kernel (AK), which is simple and robust and can extend any existing kernel to a non-stationary one. We evaluate the new kernel in elevation mapping tasks, where AK provides better accuracy and uncertainty quantification over the commonly used stationary kernels and the leading non-stationary kernels. The improved uncertainty quantification guides the downstream informative planner to collect more valuable data around the high-error area, further increasing prediction accuracy. A field experiment demonstrates that the proposed method can guide an Autonomous Surface Vehicle (ASV) to prioritize data collection in locations with significant spatial variations, enabling the model to characterize salient environmental features.
Förderung
- RI: Small: Exploiting Symmetries of Decision-Theoretic Planning for Autonomous Vehicles
- III: Small: Algorithms and Theoretical Foundations for Approximate Bayesian Inference in Machine Learning
- CAREER: Autonomous Live Sketching of Dynamic Environments by Exploiting Spatiotemporal Variations
Zitieren
APA
Chen, W., Khardon, R., & Liu, L. (2024). Adaptive Robotic Information Gathering via non-stationary Gaussian processes. The International Journal of Robotics Research, 43(4), 405-436. https://doi.org/10.1177/02783649231184498
Vancouver
Chen W, Khardon R, Liu L. Adaptive Robotic Information Gathering via non-stationary Gaussian processes. The International Journal of Robotics Research. 2024;43(4):405-436. doi:10.1177/02783649231184498
BibTeX
@article{Chen2024,
author = {Chen, Weizhe and Khardon, Roni and Liu, Lantao},
title = {Adaptive Robotic Information Gathering via non-stationary Gaussian processes},
journal = {The International Journal of Robotics Research},
year = {2024},
volume = {43},
number = {4},
pages = {405--436},
doi = {10.1177/02783649231184498}
}
EUVIMED