Robot learning

Related papers: 20

About

Robot learning refers to the set of methods and frameworks that enable robotic systems to autonomously acquire, refine, and generalize skills through experience rather than relying solely on hand-coded instructions. It encompasses several interconnected paradigms: reinforcement learning, where robots improve behavior by maximizing cumulative rewards through trial-and-error interaction with an environment; learning from demonstration, where robots observe and imitate human or expert performance to acquire new motor skills; and continual or lifelong learning, where robots incrementally build on prior knowledge without forgetting previously learned tasks. These approaches are complemented by techniques such as Gaussian process-based data-efficient learning, active learning, and deep imitation learning from teleoperation. Robot learning matters because manually engineering behaviors for complex, unstructured real-world environments is impractical — robots must adapt to variability in tasks, objects, and human collaborators. By enabling machines to learn from data and interaction, robot learning accelerates deployment in manufacturing, healthcare, and service domains while making systems more flexible, robust, and capable of improving over time.

Top Cited Papers

Reinforcement learning in robotics: A survey

Jens Kober, J. Andrew Bagnell, Jan Peters

Citations: 3055 • 2013

Continual lifelong learning with neural networks: A review

German I. Parisi, Ronald Kemker, Jose L. Part, Christopher Kanan, Stefan Wermter

Citations: 2977 • 2019

Robot Programming by Demonstration

Aude Billard, Sylvain Calinon, Rüdiger Dillmann, Stefan Schaal

Citations: 984 • 2008

Reinforcement learning for robots using neural networks

Long-Ji Lin

Citations: 887 • 1992

Reinforcement learning of motor skills with policy gradients

Jan Peters, Stefan Schaal

Citations: 863 • 2008

Matching robot appearance and behavior to tasks to improve human-robot cooperation

Jennifer L. Goetz, Sara Kiesler, Aaron Powers

Citations: 775 • 2004

Recent Advances in Robot Learning from Demonstration

Harish Ravichandar, Athanasios Polydoros, Sonia Chernova, Aude Billard

Citations: 716 • 2019

Gaussian Processes for Data-Efficient Learning in Robotics and Control

Marc Peter Deisenroth, Dieter Fox, Carl Edward Rasmussen

Citations: 656 • 2013

Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learning

Lukas Brunke, Melissa Greeff, Adam W. Hall, Zhaocong Yuan, Siqi Zhou, Jacopo Panerati, Angela P. Schoellig

Citations: 654 • 2022

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Tianhao Zhang, Zoe McCarthy, Owen Jow, Dennis Lee, Xi Chen, Ken Goldberg, Pieter Abbeel

Citations: 590 • 2018

Learning in Embedded Systems

Leslie Pack Kaelbling

Citations: 586 • 1993

Lifelong robot learning

Sebastian Thrun, Tom M. Mitchell

Citations: 507 • 1995

Continual Learning for Robotics: Definition, Framework, Learning\n Strategies, Opportunities and Challenges

Timothée Lesort, Vincenzo Lomonaco, Andrei Stoian, Davide Maltoni, David Filliat, Natalia Díaz-Rodríguez

Citations: 492 • 2019

Active learning of inverse models with intrinsically motivated goal exploration in robots

Adrien Baranès, Pierre‐Yves Oudeyer

Citations: 448 • 2012

Policy search for motor primitives in robotics

Jens Kober, Jan Peters

Citations: 437 • 2010

Reinforcement Learning in the Multi-Robot Domain

Maja J. Matarić

Citations: 410 • 1997

Learning to select and generalize striking movements in robot table tennis

Katharina Mülling, Jens Kober, Oliver Kroemer, Jan Peters

Citations: 404 • 2013

An Algorithmic Perspective on Imitation Learning

Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J. Andrew Bagnell, Pieter Abbeel, Jan Peters

Citations: 379 • 2018

An Algorithmic Perspective on Imitation Learning

Takayuki Osa, Joni Pajarinen, Gerhard Neumann, J. Andrew Bagnell, Pieter Abbeel, Jan Peters

Citations: 370 • 2018

Learning Object Affordances: From Sensory--Motor Coordination to Imitation

Luis Montesano, Manuel Lopes, Alexandre Bernardino, José Santos-Victor

Citations: 354 • 2008