Research paper
Updating reachability bounds while learning disturbances
IGSOLR learns state-dependent worst-case disturbances and recomputes reachability-based safe sets around a learning controller. The proceedings abstract describes a physical quadrotor altitude hardware-in-the-loop evaluation.
Reviewed 2026-11-05 · Source and bibliography checked
- Original title
- Reducing Conservativeness in Safety Guarantees by Learning Disturbances Online: Iterated Guaranteed Safe Online Learning
- Publisher
- Robotics: Science and Systems Foundation
- Authors
- Jeremy Gillula, Claire Tomlin
- DOI
- 10.15607/rss.2012.viii.011
- Proceedings publication date
- 2012-07-09
- Source language
- en
- Edition
- Robotics: Science and Systems VIII
- Access
- Public bibliography and abstract
- Publication status
- Published
Source overview
IGSOLR learns state-dependent worst-case disturbances and recomputes reachability-based safe sets around a learning controller. The proceedings abstract describes a physical quadrotor altitude hardware-in-the-loop evaluation.
Use and review
Guarantees are conditional on the stated dynamics, sensing and constraint assumptions. Abstract/source screening does not validate a complete robot installation or an ISO13849 safety function.
Sources & editions
Reducing Conservativeness in Safety Guarantees by Learning Disturbances Online: Iterated Guaranteed Safe Online Learning ↗
Robotics: Science and Systems Foundation · Robotics: Science and Systems VIII
Owning RSS2012 title/authors/DOI/abstract/BibTeX checked. This is distinct from GillulaICRA2012 paper retained as an access gap in generation1.