Research paper
Learning quadrotor dynamics · Exploring within barrier-certified regions
Gaussian processes learn uncertain dynamics while barrier certificates constrain exploration to a safe region. Adaptive sampling expands that region and recursive GP updates support model learning; the author version reports simulation results.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- Safe Learning of Quadrotor Dynamics Using Barrier Certificates
- Publisher
- IEEE
- Authors
- Li Wang, Evangelos A. Theodorou, Magnus Egerstedt
- DOI
- 10.1109/icra.2018.8460471
- Publication date
- 2018-05
- Source language
- en
- Edition
- 2018 IEEE International Conference on Robotics and Automation (ICRA); 2018; DOI 10.1109/icra.2018.8460471
- Access
- Publisher metadata and open author manuscript
- Publication status
- Published
Related resources and engineering notes
Source overview
Gaussian processes learn uncertain dynamics while barrier certificates constrain exploration to a safe region. Adaptive sampling expands that region and recursive GP updates support model learning; the author version reports simulation results.
Use and review
Checked publication metadata and the submitted author abstract. High-probability claims depend on GP statistics and model assumptions; hardware validation and identity with the final proceedings text were not established.
Sources & editions
Safe Learning of Quadrotor Dynamics Using Barrier Certificates ↗
IEEE · 2018 IEEE International Conference on Robotics and Automation (ICRA); 2018; DOI 10.1109/icra.2018.8460471
ICRA 2018 registered bibliography; matching author preprint abstract https://arxiv.org/abs/1710.05472v1. Conference publication date 2018-05 retained, not the 2017 preprint date.