Robot safety research · standards · engineering
Robot Safety ForumROBOT SAFETY FORUM
한국어English简体中文
← Back to the library

Research paper

Learning model-error corrections for bipedal safety constraints

The paper learns uncertainty terms inside a barrier/Lyapunov quadratic-program controller. Its stated evaluation concerns underactuated bipedal walking on randomly spaced stepping stones with a limited preview.

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
Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions
Publisher
Robotics: Science and Systems Foundation
Authors
Jason Choi, Fernando Castañeda, Claire Tomlin, Koushil Sreenath
DOI
10.15607/rss.2020.xvi.088
Publication date
2020-07-12
Source language
en
Edition
Robotics: Science and Systems XVI
Access
Publisher metadata and open author manuscript
Publication status
Published

Source overview

The paper learns uncertainty terms inside a barrier/Lyapunov quadratic-program controller. Its stated evaluation concerns underactuated bipedal walking on randomly spaced stepping stones with a limited preview.

Use and review

Simulation evidence does not establish physical-robot safety. Model fidelity, constraint coverage and implementation effects require separate validation.

Sources & editions

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions ↗

Robotics: Science and Systems Foundation · Robotics: Science and Systems XVI

Owning RSS2020proceedings HTML title/authors/abstract/DOI/BibTeX checked. Abstract does not establish a physical-robot deployment; no full method validation performed.