Gaussian Process-based Learning Control of Aerial Robots for Precise Visualization of Geological Outcrops

TY - GEN

T1 - Gaussian Process-based Learning Control of Aerial Robots for Precise Visualization of Geological Outcrops

AU - Mehndiratta, Mohit

AU - Kayacan, Erdal

PY - 2020/5

Y1 - 2020/5

N2 - To generate 3D virtual maps of outcrops in geoscience, manual flights of aerial robots are often employed which is challenging due to various reasons: 1) piloted flight over curved/uneven surfaces requires auto-focusing, 2) wind disturbances make it difficult to precisely maintain the desired overlap, and 3) hiring a skilled pilot is expensive as the process requires hours of data collection. In this work, we propose to fully automate the visualization process using a learning-based control framework, i.e., position tracking nonlinear model predictive controller in conjunction with Gaussian process (GP)-based disturbance regression which facilitates a precise tracking of the generated path. Thanks to the long-short term memory feature of the designed GP model, the disturbance forces are accurately estimated even for increasing magnitude levels and time-periods. The simulation and real-world tests manifest that the proposed method could provide a time- and cost-saving yet reliable visualization framework.

AB - To generate 3D virtual maps of outcrops in geoscience, manual flights of aerial robots are often employed which is challenging due to various reasons: 1) piloted flight over curved/uneven surfaces requires auto-focusing, 2) wind disturbances make it difficult to precisely maintain the desired overlap, and 3) hiring a skilled pilot is expensive as the process requires hours of data collection. In this work, we propose to fully automate the visualization process using a learning-based control framework, i.e., position tracking nonlinear model predictive controller in conjunction with Gaussian process (GP)-based disturbance regression which facilitates a precise tracking of the generated path. Thanks to the long-short term memory feature of the designed GP model, the disturbance forces are accurately estimated even for increasing magnitude levels and time-periods. The simulation and real-world tests manifest that the proposed method could provide a time- and cost-saving yet reliable visualization framework.

UR - http://www.scopus.com/inward/record.url?scp=85090124572&partnerID=8YFLogxK

M3 - Article in proceedings

AN - SCOPUS:85090124572

SP - 10

EP - 16

BT - 2020 European Control Conference (ECC)

PB - IEEE

T2 - 18th European Control Conference, ECC 2020

Y2 - 12 May 2020 through 15 May 2020

ER -