Stability (learning theory)

Related papers: 20

About

Stability in learning theory refers to the property of a learning algorithm or control system whereby small changes in input, training data, or disturbances produce only bounded, predictable changes in output or behavior. In robotics and AI, stability analysis ensures that learned controllers, motion planners, and adaptive systems converge reliably to desired states rather than diverging or oscillating unpredictably. Techniques such as Lyapunov functions, passivity analysis, and contraction theory are commonly used to formally prove stability guarantees for systems ranging from bipedal walking robots and mobile platforms to neural network-based motion learning and adaptive manipulator control. Stability matters because deploying learning-based systems in physical environments — where unexpected disturbances, model errors, and hardware constraints are unavoidable — demands provable safety and predictability. Without stability guarantees, a robot learning from demonstrations or adapting online risks catastrophic failures. Establishing theoretical stability bounds thus bridges the gap between powerful but opaque machine learning methods and the rigorous reliability standards required for real-world robotic deployment.

Top Cited Papers

Trends in extreme learning machines: A review

Gao Huang, Guang-Bin Huang, Shiji Song, Keyou You

Citations: 1738 • 2014

Disturbance Observer Based Control for Nonlinear Systems

Wen‐Hua Chen

Citations: 1423 • 2004

A stable tracking control method for an autonomous mobile robot

Yutaka Kanayama, Yuuki Kimura, F. Miyazaki, Takao Noguchi

Citations: 1414 • 2002

A new approach to visual servoing in robotics

Bernard Espiau, François Chaumette, Patrick Rives

Citations: 1357 • 1993

A new approach to visual servoing in robotics

Bernard Espiau, François Chaumette, Patrick Rives

Citations: 1330 • 1992

A vision-based formation control framework

Arindam Das, Rafael Fierro, Vijay Kumar, J.P. Ostrowski, John Spletzer, Camillo J. Taylor

Citations: 1151 • 2002

Initial Experiments on the End-Point Control of a Flexible One-Link Robot

Robert H. Cannon, Eric Schmitz

Citations: 1143 • 1984

The central nervous system stabilizes unstable dynamics by learning optimal impedance

Etienne Burdet, Rieko Osu, David W. Franklin, Theodore E. Milner, Mitsuo Kawato

Citations: 1116 • 2001

Asymptotically stable walking for biped robots: analysis via systems with impulse effects

J.W. Grizzle, Gabriel Abba, Franck Plestan

Citations: 992 • 2001

Planning walking patterns for a biped robot

Qiang Huang, Kazuhito Yokoi, Shuuji Kajita, Kenji Kaneko, Hirohiko Arai, Noriho Koyachi, K. Tanie

Citations: 852 • 2001

An autonomous laboratory for the accelerated synthesis of inorganic materials

Nathan J. Szymanski, Bernardus Rendy, Yuxing Fei, Rishi E. Kumar, Tanjin He, David Milsted, Matthew J. McDermott, Max C. Gallant, Ekin D. Cubuk, Amil Merchant, Haegyeom Kim, Anubhav Jain, Christopher J. Bartel, Kristin A. Persson, Yan Zeng, Gerbrand Ceder

Citations: 785 • 2023

Iterative learning control and repetitive control for engineering practice

Richard W. Longman

Citations: 778 • 2000

Learning Stable Nonlinear Dynamical Systems With Gaussian Mixture Models

Seyed Mohammad Khansari-Zadeh, Aude Billard

Citations: 764 • 2011

Historical Perspective and State of the Art in Robot Force Control

Daniel E. Whitney

Citations: 761 • 1987

A calculus for computing Filippov's differential inclusion with application to the variable structure control of robot manipulators

B. Paden, Shankar Sastry

Citations: 734 • 1987

Robot Grasp Synthesis Algorithms: A Survey

K.B. Shimoga

Citations: 666 • 1996

Adaptive Fuzzy Neural Network Control for a Constrained Robot Using Impedance Learning

Wei He, Yiting Dong

Citations: 638 • 2017

A compliant, underactuated hand for robust manipulation

Lael U. Odhner, Leif P. Jentoft, Mark R. Claffee, Nicholas Corson, Yaroslav Tenzer, R. Raymond, M. Buehler, Robert Kohout, Robert D. Howe, Aaron M. Dollar

Citations: 597 • 2014

The Application of Model-Referenced Adaptive Control to Robotic Manipulators

Steven Dubowsky, Daniel Desforges

Citations: 536 • 1979

A survey of spacecraft formation flying guidance and control. Part II: control

Daniel P. Scharf, Fred Y. Hadaegh, Scott Ploen

Citations: 528 • 2004