Research paper

Episodic CLF learning for a simulated Segway

The framework repeatedly learns Lyapunov-derivative errors and updates a stabilizing quadratic-program controller. Its stated evaluation is a planar Segway simulation under uncertain dynamics.

Reviewed 2026-11-05 · Source and bibliography checked

Bibliographic details and the editorial overview were checked against the original source. Access conditions and editions are identified with the source.

Original title: Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems
Publisher: IEEE
Authors: Andrew J. Taylor, Victor D. Dorobantu, Hoang M. Le, Yisong Yue, Aaron D. Ames
DOI: 10.1109/iros40897.2019.8967820
Conference date: 2019-11
Source language: en
Edition: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Access: Publisher metadata and open author manuscript
Publication status: Published

Source overview

The framework repeatedly learns Lyapunov-derivative errors and updates a stabilizing quadratic-program controller. Its stated evaluation is a planar Segway simulation under uncertain dynamics.

Use and review

Only simulated stability was assessed in the reviewed abstract. A stabilizing controller does not by itself establish collision avoidance, contact safety or a validated safety function.

Sources & editions

Episodic Learning with Control Lyapunov Functions for Uncertain Robotic Systems ↗

IEEE · 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Archivev1abstract/authors explicitly link IROS2019publisherDOI. Retained to distinguish learnedstability evidence from stronger robot-safety claims; no collision/contactguarantee inferred.